JP2812705B2 - Character extraction device - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a character extracting device for extracting characters from a character line with ruled lines.

(Prior Art) In recent years, in order to increase the processing efficiency of a large amount of documents, there is an increasing demand for enabling information written in the documents to be mechanically input to a computer. The character recognition device used for this mechanical input separates (cuts out) an image of one character from a printed or handwritten character group image in character units, and performs character recognition of the separated image of one character. .

Generally used documents are often provided with ruled lines in addition to characters, but for character recognition, it is necessary to cut out an image of one character so as not to include the added ruled lines.

Examples of a device and a method for cutting out so as not to include a ruled line include an optical character reading device disclosed in JP-A-60-160487 and a character disclosed in JP-A-62-217385. There is a separation method.

In the former conventional apparatus, a row direction and a column direction are virtually set on an image memory storing image data from the reading unit (the column direction is a direction perpendicular to the row direction. Hereinafter, virtually set). The row direction and the column direction are referred to as a predetermined row direction and a predetermined column direction), and the image data of the document is scanned in the row direction.
In this scanning, the number of black pixels is accumulated in the row direction to create a peripheral distribution in the row direction, and the area of the peripheral distribution exceeding the predetermined number of black pixels is defined as an underline portion and the area of the peripheral distribution less than the predetermined number of black pixels. The position of the edge of the character portion in the column direction is detected as the start position and the end position of the character in the column direction. Then, only the character portion is scanned except for the underline portion, and the number of black pixels is accumulated in the column direction by this scanning to create a peripheral distribution in the column direction. Detect start and end positions.

In this conventional device, in order to accurately detect the start and end positions of characters in the line direction when the ruled line is added along the line direction, the true line direction of the image is made to coincide with the predetermined line direction. Image data such as manuscript
At the time of creating the marginal distribution, the overlapping of characters and ruled lines in a predetermined line direction is reduced.

In the latter conventional method, a plurality of local regions are set on an image including a character line with a straight line such as an underline,
The images of these local regions are symbolized into predetermined direction elements by pattern matching, and the direction elements are further classified. Then, a line segment having a predetermined condition (for example, length or existing area) is selected from line segments composed of direction line elements (for example, horizontal straight line components) having the same direction as a line segment unnecessary for character recognition such as an underline. Is detected, and the detected line segment is removed from the image as an unnecessary line segment. After obtaining an image from which unnecessary line segments have been removed in this way, this image is scanned to create a peripheral distribution in the row and column directions, and the starting position of the character in a predetermined row and column direction is determined from the created peripheral distribution. The end position was detected.

(Problems to be Solved by the Invention) However, in the former conventional apparatus described above, if the predetermined row direction set in the image memory is deviated from the true row direction of the image, the predetermined The overlap of characters and ruled lines in the direction increases, so that black pixels of the character and black lines of the ruled line are mixed on the same main scanning line. As a result, the position of the character and the position of the ruled line can be accurately determined from the peripheral distribution in a predetermined line direction. It is difficult to detect well.

Further, in the former conventional device described above, even if the predetermined line direction is deviated from the true line direction, the character start and end positions in the predetermined line direction are all the same within the same character line. An incomplete character that is practically unrecognizable due to a missing end is cut out. The degree of the lack of this character becomes more severe near the end of the line.

Moreover, if the character and the ruled line are in contact with each other in addition to the mismatch between the predetermined line direction and the true line direction, the accuracy of detecting the position of the character and the ruled line is further deteriorated, and the degree of missing of the character is further increased.

In the latter conventional method described above, the read image is divided into a plurality of local areas, the read image of each local area is compared with a predetermined plurality of basic patterns by matching, and the local area is oriented based on the comparison result. Convert to line elements. Such a local matching process is complicated, and therefore, the device configuration of the device adopting the conventional method is complicated, which causes a problem that the size of the device is increased and the cost of the device is increased.

SUMMARY OF THE INVENTION An object of the present invention is to solve the above-described conventional problems, so that even when the predetermined row direction and the true row direction do not match, the predetermined row direction and column direction are determined based on the change in the number of accumulated black pixels. It is an object of the present invention to provide a character cutout device that can accurately detect the start position and the end position of a character so that the character is not lost.

(Means for Solving the Problems) In order to achieve this object, a character extracting device according to the present invention optically reads an information medium in which a character line with a ruled line is described and outputs image data of the information medium. An image data storage unit for storing image data from the reading unit; and scanning the image data in the character line area with a ruled line in the image data storage unit to detect a cumulative number of black pixels in a predetermined column direction for each scanning line. Then, the number of column-direction cumulative black pixels equal to or greater than the block threshold is detected as a black block element and the number of column-direction cumulative black pixels less than the block threshold is detected as a white block element, and the black block whose length in a predetermined row direction exceeds the length threshold is detected. Is detected, the block threshold is increased by a predetermined amount, and the black and white block elements are detected again from the start position of the black block exceeding the length threshold, and the end of the black block having the length threshold or less is detected. When the position is detected, the start position and end position of the black block having the length threshold or less are detected as the character start position and end position in the predetermined line direction, and the block threshold value is initialized, and the character start position in the predetermined line direction is detected. And based on the end position
The first ruled line detection area is set for each character so as to include a ruled line at a position adjacent to the character start position in the predetermined line direction and opposite to the character end position in the predetermined line direction. A ruled line detection area setting unit that sets, for each character, a ruled line adjacent to the character end position in the predetermined line direction and opposite to the character start position in the predetermined line direction; and an image data storage unit Scanning the image data in the first and second ruled line detection areas to detect the cumulative number of black pixels in a predetermined row direction for each scanning line, and based on the change in the cumulative number of black pixels in the row direction, the first and second The ruled line detection processing in the ruled line detection area is performed for each character, and based on the ruled line detection processing result, the character start and end positions in a predetermined column direction are positioned closer to the center of the ruled line character line area than the ruled lines. To set character ruled line for each character And controls the operation of the reading unit, the ruled line detection area setting unit and the character ruled line separating unit, and sets the character start and end positions in a predetermined row direction and the character start and end positions in a predetermined column direction as a character with a ruled line. And a control unit for outputting for each character in the line area.

(Operation) According to the character extracting device having such a configuration, the reading unit optically reads the information medium in which the character line with the ruled line is described, outputs image data of the information medium, and the image data storage unit And the image data from the reading unit.

The ruled line detection area setting unit scans the image data in the character line area with a ruled line in the image data storage unit and detects the cumulative number of black pixels in a predetermined column direction for each scanning line. Then, the number of column-direction cumulative black pixels greater than or equal to the block threshold is detected as a black block element and the number of column-direction cumulative black pixels less than the block threshold is detected as a white block element, and the black block whose length in a predetermined row direction exceeds the length threshold is detected. Is detected, the block threshold is increased by a predetermined amount, the black and white block elements are detected again from the start position of the black block exceeding the length threshold, and the end position of the black block having the length threshold or less is detected. Detects the start position and end position of the black block having the length threshold or less as the character start position and end position in a predetermined line direction, and initializes the block threshold.

Further, the ruled line detection area setting unit may set the first ruled line detection area at a position adjacent to the character start end position in the predetermined line direction based on the character start end position and the end position in the predetermined line direction. It is set for each character so as to include a ruled line on the side opposite to the end position, and the second ruled line detection area is a position adjacent to the character end position in the predetermined line direction and opposite to the character start position in the predetermined line direction. Set for each character so that a ruled line is included on the side.

The character ruled line separation unit scans the image data in the first and second ruled line detection areas of the image data storage unit, detects the cumulative number of black pixels in a predetermined row direction for each scan line, A ruled line detection process in the first and second ruled line detection areas is performed based on a change in the number of pixels. Further, based on the result of the ruled line detection processing, the character start and end positions in the predetermined column direction are set for each character so as to be located closer to the center of the ruled line character line area than the ruled line.

The control unit controls the operation of the reading unit, the ruled line detection area setting unit, and the character ruled line separating unit, and determines the start and end positions of the character in the predetermined row direction and the start and end positions in the predetermined column direction with a ruled line. Output for each character in the character line area.

As described above, when a black block whose length in the predetermined row direction exceeds the length threshold is detected, the block threshold is increased by a predetermined amount and the black and white block elements are shifted from the start position of the black block exceeding the length threshold. Is detected again, and when the end position of the black block equal to or less than the threshold value is detected, the start position and end position of the black block equal to or less than the length threshold value are detected as the character start position and end position in the predetermined line direction. Therefore, by setting the length threshold arbitrarily, it is not necessary to detect a black block whose length exceeds the character width, and re-detection of black and white block elements is repeated until the length becomes equal to or less than the length threshold. Therefore, only the black block within the character width can be detected, so that the detection accuracy of the character start position and the character end position can be improved.

Further, the start and end positions of the characters in the predetermined column direction are detected based on the change in the cumulative number of black pixels in the predetermined row direction in the first and second ruled line detection areas, so that these start and end positions are detected. Detection processing can be simplified.

Moreover, since the first ruled line detection area is set to include a ruled line at a position adjacent to the character start position in the predetermined line direction and opposite to the character end position in the predetermined line direction,
The black pixels constituting the character can be prevented from being counted or almost not counted as the cumulative number of black pixels in the predetermined column direction in the first ruled line detection area. As a result, the position of the ruled line in the first ruled line detection area can be detected with high accuracy. Similarly, the second ruled line detection area is set to include a ruled line at a position adjacent to the character end position in the predetermined line direction and opposite to the character start position in the predetermined line direction. The constituent black pixels can be prevented from being counted or hardly counted as the cumulative number of black pixels in a predetermined row direction in the second ruled line detection area. As a result, the position of the ruled line in the second ruled line detection area can be detected with high accuracy.

Therefore, since the position of the ruled line in the first and second ruled line detection areas can be detected with high accuracy, the character can be cut out so that the character is not lost or the character is reduced less than before. .

Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be noted that the drawings are only schematically shown to the extent that the present invention can be understood. It is not limited to.

FIG. 1 is a functional block diagram schematically showing a configuration of an embodiment of the present invention.

The character extracting apparatus according to this embodiment includes a reading unit 10, an image data storage unit 12, a ruled line detection area setting unit 14, a character ruled line separating unit 16
And a control unit 18.

The reading unit 10 optically reads the information medium on which the character line with the ruled line is described, and outputs image data of the information medium. The image data storage unit 12 stores the image data from the reading unit 10.

The ruled line detection area setting unit 14 scans the image data in the character line area with a ruled line in the image data storage unit 12 and detects the cumulative number of black pixels in a predetermined column direction for each scanning line. Then, the number of column-direction cumulative black pixels equal to or greater than the block threshold is detected as a black block element and the number of column-direction cumulative black pixels less than the block threshold is detected as a white block element, and a black block whose length in a predetermined row direction exceeds the length threshold is detected. When detected, the block threshold is increased by a predetermined amount, the black and white block elements are detected again from the start end position of the black block exceeding the length threshold, and the end position of the black block below the length threshold is detected. The start and end positions of the black block having the length threshold or less are detected as the character start and end positions in a predetermined line direction, and the block threshold is initialized.

Further, the ruled line detection area setting unit 14 sets the first ruled line detection area at a position adjacent to the character start end position in the predetermined line direction based on the character start position and end position in the predetermined line direction. It is set for each character so as to include a ruled line on the side opposite to the character end position, and the second ruled line detection area is a position adjacent to the character end position in the predetermined line direction and the character start position in the predetermined line direction. Set for each character so as to include a ruled line on the opposite side.

Further, the character ruled line separating section 16 scans the image data in the first and second ruled line detection areas of the image data storage section 12, detects the cumulative number of black pixels in a predetermined row direction for each scanning line, and A ruled line detection process in the first and second ruled line detection areas is performed based on the change in the number of black pixels. Further, based on the result of the ruled line detection processing, the character start and end positions in the predetermined column direction are set for each character so as to be positioned closer to the center of the ruled character line area than the ruled line.

The control unit 18 includes the reading unit 10 and the ruled line detection area setting unit 14 described above.
In addition to controlling the operation of the character ruled line separating unit 16, the character start position and end position in the predetermined line direction and the character start position and end position in the predetermined column direction are output for each character in the character line region with ruled lines. I do.

 Hereinafter, this embodiment will be described in more detail.

(Reading Unit) The reading unit 10 of this embodiment converts the reflected light P from a recording medium such as a manuscript into a black and white binary quantized electric signal (image data), not shown, and converts this image data. It comprises a photoelectric conversion unit for outputting in pixel units, and a scanning mechanism for relatively moving the photoelectric conversion unit and the recording medium for scanning the recording medium.

(Image Data Storage Unit) The image data storage unit 12 of this embodiment is configured using an image memory that stores the image data from the reading unit 10 in a scanning order, and stores one line or more of the image data.

An XY coordinate system is set on the image memory. For example, assuming a horizontally written document, the X-axis direction is a predetermined row direction and the X-axis direction is a predetermined column direction.

The true row direction of the image may coincide with the X-axis direction or may slightly deviate from the X-axis direction.

It is most preferable that the true line direction of the image coincides with the X-axis direction in order to cut out the characters without causing the loss of characters. However, even if the true line direction is slightly deviated from the X-axis direction, Characters can be cut out with less chipping than before or without chipping.

(Ruled line detection area setting unit) The ruled line detection area setting unit 14 of this embodiment includes a first marginal distribution creation unit 20, a row marginal distribution storage unit 22, a black block detection unit
24, a black block width determination unit 26, and a detection area setting unit 26.

The first marginal distribution creating unit 20 determines one and the other edge positions Y _T1 and Y _B1 in a predetermined column direction of a ruled character line area including one character line and a ruled line added to the character line. an input from one and the other of the end edge positions _S and X _E and the control unit 18 in a given row. Range from position Y _T1 from the position X _S in the range of up to Y _B1 to X _E is ruled with character line region.

Then, the first marginal distribution creating unit 20 includes the image data storage unit 12
The image data in the character line area with a ruled line is scanned, and for each position X in the predetermined row direction, the black pixels on the scanning line in the predetermined column direction are accumulated to accumulate the number of black pixels (column accumulated pixel number) And stores the detected column cumulative pixel number in the first marginal distribution storage unit 22.

The black block detection unit 24 reads the number of column accumulated pixels detected for each position X in order of increasing (or decreasing) position X, compares the read column accumulated pixel number with a block threshold THL, The number of column accumulated pixels equal to or greater than THL is detected as a black block element and the number of column accumulated pixels smaller than the threshold THL is detected as a white block element, and the change in the number of column accumulated pixels is checked.

Here, a black block is a block of blocks consisting only of black block elements that are continuous in a predetermined row direction, and assuming that the length of the black block is the length in the predetermined row direction, the black block detection unit 24 detecting the position X of the block elements when a black block element to the next white block elements as starting position X _BS of the black block. Start position X _BS
Each for detecting a black block elements black block contiguous to the black block element positions X _BS upon detecting, detects a distance for example X-X _BS +1 of the position X and the starting end position X _BS in the detection black block element (The separation distance is, for example, X-X _BS +1
, The detected separation distance is the length of the black block). Then, the length of the black block is output to the black block width determination unit 26, and the determination result from the black block width determination unit 26 is obtained.

When the first determination result indicating that the length of the black block exceeds the threshold BWJ is input from the black block width determination unit 26, the black block detection unit 24 sets the threshold THL to a predetermined amount UT.
Only then increased again detects black and white block element examine changes in the column cumulative number of pixels from the starting position X _BS to X becomes large order (or smaller order) of the black blocks exceeding the threshold BWJ again. As a result, the black block detection unit 24 sets the threshold value BWJ
Rather than detecting the end position X _BL of black block beyond, can detect only the end position of the following black block threshold BWJ. A black block equal to or smaller than the threshold value BWJK can be regarded as a block of black pixels constituting a character. Therefore, the start position and end position of this black block are the character start position and end position in a predetermined line direction.

The threshold value THL and the predetermined amount UT are arbitrarily and appropriately set constants. For example, the initial value 1 of the threshold value THL and UT = 2 are set.

When the black block detection unit 24 receives the second determination result indicating that the length of the black block is within the threshold value BWJ from the black block width determination unit 26, the black block element of the black block within the threshold value BWJ is input. Is read from the first peripheral distribution storage unit 22, and the change of the black and white block elements at the next position X is examined.

Further, when the black block detection unit 24 detects the white block element next to the black block element (since the position X of the black block element is the black block end position _XBL ), the black block end position _XBL is detected. was a considered black block width determination unit to start position X _BS and the end position X _BL of the black block with character position detection signal indicating the detection of the start position X _L and the end position X _R of the characters in a given row 26, and the threshold value THL is initialized. Position X _BS detected this time, a character start position X _BL is in the row direction X _L and the end position X _R (hereinafter, the row direction is referred to as starting position X _L and the row direction end position X _R). Then, the black block detection unit 24 increases X from the position X next to the end position _XBL just detected in order to detect the start position X _L and end position X _R in the line direction of the remaining characters in the character line with ruled lines. Examine the changes in black and white block elements in order (or smaller). In addition, the position _XL and
Between X _R regarded as the one character exists, hereinafter referred to the region between the position X _L and X _R of the border with character line area as the character region.

Upon receiving the length of the black block from the black block detection unit 24, the black block width determination unit 28 compares the length of the black block with the block threshold BWJ. When the length of the black block exceeds the threshold value BWJ, the first determination result is output to the black block detection unit 24, and when the length of the black block is equal to or less than the threshold value BWJ, the second determination result is output to the black block detection unit 24. Output the judgment result. Further, when the black block width determination unit 28 inputs the start position X _BS and the end position X _BL of black block with character position detection signal from the black block detection unit 24, the row direction starting end position X _L and these positions X _BS and X _BL detected as the row direction end position X _R region determining section 28
Output to

The threshold value BWJ is set to any suitable value larger than the character width (expressed by the number of pixels in the predetermined line direction) of one character in the storage medium to be read in the predetermined line direction. When the character width is 3 mm and the resolution of optical reading in the reading unit 10 is 16 pixels / mm, BWJ =
It should be 56.

Detection area position determining unit 28, the starting end position X _L and the end position X _R
Is input, the first ruled line detection area is set so as to include a ruled line at a position adjacent to the line direction start position X _L and on the opposite side of the line direction end position X _R. outside to be adjacent in the row direction starting end position X _L side of character area of the set by.

In order to improve the detection accuracy of the ruled line in the first ruled line detection area, the width of the first ruled line detection area in a predetermined row direction is set to a width within the distance between adjacent characters, and the black pixels constituting the character are the first ruled line. It is preferable to reduce the number included in the detection area.

Similarly detection area position determining unit 28, the position X _L and X _R entering the the row direction end position X _R on adjacent Shikatsu row direction starting end position X _L
And sets the second ruled line detection area so as to include a border position opposite, thus the second ruled line detection area adjacent to the outside of the character region in the row direction end position X _R side of character area is set. In order to improve the detection accuracy of the ruled line in the second ruled line detection area, the width of the second ruled line detection area in a predetermined line direction is set to a width within the distance between adjacent characters, and the black pixels constituting the character are defined by the second ruled line. It is desirable to reduce the number included in the region.

The detection area position determination unit 28 sets first and second ruled line detection areas of individual characters in a character line.

For example, the first ruled line detection area is set according to the following equations (1) and (2), and the second ruled line detection area is set according to the following equations (3) and (4).

However, sequentially counted n-th character coordinate X of a predetermined row direction to progressively larger direction (hereinafter, simply referred to as n-th character) the position X _L and X _L (n) and the position X _R of X _R (n), n
X _LL (n) represents one edge position of the first ruled line detection area of the second character in the predetermined line direction, and X represents the other edge position.
_LR (n), one edge position in a predetermined line direction of the second ruled line detection area of the n-th character is X _RL (n), the other edge position is X _RR (n), and one character line is within one line. _Is the total number of characters detected in, n is a natural number in the range of 1 ≦ n ≦ n _LS , β
Is a constant that is arbitrarily and suitably set. If the resolution of the optical reading of the reading unit 10 is 16 pixels / mm, for example, β
= 32.

X _LR (n) = _XL (n) -1 (1) When n = 1 or _XL (n) -1-β> X _R (n-1) +1, X _LL (n) = X _{L (n) -1-β ·} n ≧ 2 and _{X L (n) -1-β} ≦ X R (n-1) +1 when _{X LL (n) = X R} (n-1) +1 ...... ( 2) X _RL (n) = X _R (n) +1 (3) n = n _LS or X _R (n) + 1 + β < _XL (n + 1) -1
_{X RR (n) = X R} (n) + 1 + β · n ≦ n LS -1 and _{X R (n) + 1 +} β ≧ X L (n + 1) when the -
_XRR (n) = _XL (n + 1) -1 when (1) (character ruled line separating unit) The character ruled line separating unit 16 of this embodiment includes a second marginal distribution creating unit 30 and a second marginal distribution. It comprises a storage unit 32, a ruled line detection unit 34, and a ruled line separation position determination unit 36.

The second peripheral distribution creating unit 30 scans the image data in the first ruled line detection area of the image data storage unit 12 and, for each position Y in a predetermined column direction, a black pixel on a scanning line in a predetermined row direction. Is accumulated to detect the cumulative number of black pixels (the first row cumulative pixel number), and the detected first row cumulative pixel number is stored in the second peripheral distribution storage unit 32. Similarly, the image data in the second ruled line detection area of the image data storage unit 12 is scanned, and each position Y in the predetermined column direction is scanned.
Each time, the black pixels on the scanning line in the predetermined row direction are accumulated to detect the cumulative black pixel number (second row cumulative pixel number), and the detected second row cumulative pixel number is stored in the second peripheral distribution storage unit 32. save.

The ruled line detector 34, one end edge position of the side of the first ruled line detection area at a predetermined column direction and Y _T1, the first ruled line position Y _LS1 from the first ruled line detection of character line margin of the detection area Y is sequentially reduced to the edge position Y _T1 on one side of the area, and the first row accumulated pixel number is read out (where Y _LS1 > Y _T1 and Y
Y so that ruled lines and margins are included between _LS1 and Y _T1
Set _LS1 . For example, Y _LS1 = (Y _T1 + Y _B1 ) / 2 may be set. ), The read first row accumulated pixel number is set to a predetermined threshold value THL _L
Compare with By this comparison, a change in the row accumulated pixel number is examined.

When the cumulative number of pixels in the first row changes from less than the threshold to greater than or equal to the threshold, the position Y of the cumulative number of pixels in the first row that is greater than or equal to the threshold is detected as the first ruled line detection processing result _YLT . However, it is assumed that the position Y when the first row accumulated pixel number first changes is the first ruled line detection result _YLT .

When finishing the first line reads all the cumulative number of pixels from the first row accumulated without detecting a change in the number of pixel positions Y _LS1 to Y _T1 is the first ruled line detection result Y _LT and edge position Y _T1.

Furthermore ruled line detector 34, the other side of the first ruled line detection area in a given column direction edge positions and Y _B1, from the position Y _LS2 character line margin of the first border region of the first ruled line area Y is sequentially increased from the edge position Y _B1 on the other side to read out the accumulated pixel number of the first row (however, Y _LS2 <Y _B1 and Y _LS2 to Y _LS2
Set _YLS2 to include ruled lines and margins before _B1 . For example, Y = _LS2 = (Y _T1 + Y _B1 ) / 2. ), And examine the change in the cumulative number of pixels in the first row.

When the first row accumulated pixel number changes from less than the threshold to more than the threshold, the position Y of the first row accumulated pixel number equal to or greater than the threshold is detected as the second ruled line detection processing result _YLB . However, the position Y when the first row cumulative number of pixels is first changed is assumed to be the second ruled line detection processing result Y _LB.

When all the first-row accumulated pixel numbers from the positions Y _LS2 to Y _{B1 have} been read out without detecting a change in the first-row accumulated pixel number, the second ruled line detection processing result Y _{LB is set} to the edge position Y _B1 . .

Further, the ruled line detection unit 34 detects the second ruled line from the position Y _RS1 of the character line blank portion in the second ruled line detection region with the edge position on one side in the predetermined column direction as Y _T1. Y is sequentially reduced to the edge position Y _T1 on one side of the area, and the second row accumulated pixel number is read out (where Y _RS1 > Y _T1 and Y
Y so that ruled lines and margins are included between _RS1 and Y _T1
Set _RS1 . For example, Y _RS1 = (Y _T1 + Y _B1 ) / 2 may be set. ), Examine the change in the second row cumulative number of pixels, the third detection processing result Y _RT corresponding to the result of investigating changes obtained in the same manner as in the first ruled line detection region described above. Further, the ruled line detection unit 34 sets the edge position on the other side of the second ruled line detection area to Y
_B1 and to the second ruled line read a second row cumulative number of pixels Yuki from position Y _RS2 of character lines margin and turn increase the other of Y to the edge position Y _B1 side of the second border regions within the region (where Y _RS2 <Y _B1
Setting the Y _RS2 to include ruled lines and blank between be from Y _RS2 to Y _B1. For example, Y _RS2 = (Y _T1 + Y _B1 ) / 2 may be set. A change in the number of accumulated pixels in the second row is checked, and a fourth detection processing result Y _RB corresponding to the result of checking the change is obtained in the same manner as in the above-described first ruled line detection area.

The appearance of the change in the first and second row cumulative pixel numbers can be regarded as a ruled line being detected, and the detection processing result Y _LT , Y _LB , Y _RT or Y Y when these row cumulative pixel numbers have changed.
_RB can be regarded as indicating the edge position of the ruled line in the center of the ruled character line area. In addition, the detection processing results Y _LT = Y _T1 , Y _LB = Y _B1 ,
When the Y _RT = Y _T1 or _{Y RB = Y B1, Y T1} ≦ Y first ruled line detection area in the range of _{≦ Y LS1, Y LS2 ≦ Y} ≦ Y B1 first ruled line detection area in the range of, Y _T1 ≦ A second ruled line detection area in the range of Y ≦ Y _RS1 ,
Alternatively, it can be considered that no ruled line is detected in the second ruled line detection area in the range of Y _RS2 ≦ Y ≦ Y _B1 .

Borders separating position determination unit 36, for example, the following determination formula (5) and (6) thus set to the center side of the character line region with borders than the position of the border column start position Y _T and the column end position Y _B.

• When Y _LT ≥ Y _RT Y _T = Y _LT · When Y _LT <Y _RT Y _T = Y _RT ... (5) • When Y _LB ≥ Y _RB Y _B = Y _RB · Y _LB <Y _RB In the case of Y _B = Y _LB (6) (Control Unit) The control unit 18 determines the edge position in the predetermined column direction of the character line area with ruled lines according to the format of the recording medium set in the reading unit 10. Y _T1 , Y _B1 and the edge position in the predetermined row direction
Load X _S, and X _E format information storage unit (not shown).
The read positions Y _T1 and Y _B1 and the positions X _S and X _E are output to the ruled line detection area setting unit.

Note that not only those previously stored in the format information storage unit as the positions Y _T1 and Y _B1 and the positions X _S and X _E but also a part or the entire image data of the recording medium is scanned by a conventionally known line detecting unit. Positions Y _T1 and Y _B1 and positions X _S and X _{E of} the detected character line
May be used.

The position X _L and X _R of character control unit 18 which borders the detection area setting unit 14 detects the position X of the first and second ruled line detection area
_LL and X _LR , and positions X _RL and X _RR are input, and these positions are stored for each character in the character line area with ruled lines.

Then, the control unit 18 determines the positions of the first and second ruled line detection areas.
X _LL, X _LR and position X _RL, the X _RR, output to the character ruled line separating section 16 on an individual character.

Character line separation unit 16 determines the position of the character with respect to one character
When the detection of Y _T and Y _B is completed, the control unit 18 returns to the character ruled line separation unit 16.
Position Y _T from the position and stored and stored by entering Y _B Y _T, Y _B and the position Y _T, the position of the character to obtain a Y _B X _L, as character extraction information in association with X _R save. At the same time, when the control unit 18 inputs the positions Y _T and Y _B , the control unit 18 transmits the positions X _LL and X _LR and the positions X _RL and X _RR of the first and second ruled line detection areas for the next character to the character ruled line separation unit 16. Output.

The control unit 18 determines that the character ruled line separation unit 16 has one character Y _T , Y _B
Of the finish detection of the character of the character Y _T, Y _B and X _L, a plurality of X to _R and it may be outputted, or the separation unit 16 is all or any suitable number of character rows in the region with borders After the detection of the characters Y _T and Y _B is completed, the detected characters Y _T , Y _B , X _L and X _R may be output for each character.

Description of Operation Next, in order to deepen the understanding of the present invention, the operation of this embodiment will be described using a more specific example of operation.
In the following description, a character extracting operation for one character line will be described. However, it is apparent that the present invention can be applied to character extracting for a plurality of character lines.

When a processing start signal is input to the control unit 18 via an input unit (not shown), the control unit 18 outputs a reading start signal to the reading unit 10 and outputs the edge position of the character line area with ruled lines from the format information storage unit. Enter Y _T1 , Y _B1 , X _S , X _E and enter these positions Y _T1 , Y _B1 ,
X _S, and outputs the X _E in the first row peripheral distribution generator 20.

When a reading start signal is input, the reading unit 10 starts optical reading within a predetermined reading range of a recording medium, and outputs image data in pixel units. Image data is output by setting white pixels constituting the ground of the recording medium to "0" and black pixels constituting the uncle to "1", for example. The image data storage unit 12 stores the image data from the reading unit 10 in a scanning order.

When reading of the entire surface of the predetermined reading range is completed and storage of image data of the entire surface of the reading range is completed, the ruled line detection area setting unit 14 starts operating. Hereinafter, the ruled line detection area setting section
The operation 14 will be described with reference to FIGS. 2 and 3.

FIGS. 2A and 2B are diagrams showing an example of the distribution of image data and the number of column accumulated pixels. FIG. 2A shows image data of one character line included in a predetermined reading range 38 of the recording medium. In FIG. 2A, the X axis and the Y axis are based on the XY coordinate system set on the image memory. Represents a coordinate axis. FIG. 2B shows the distribution of the cumulative number of columns detected for the character row shown in FIG. 2A. The horizontal axis in FIG. 2B indicates the position X in a predetermined row direction, and the vertical axis indicates the position X in the position X. Represents the number of column accumulated black pixels.
FIGS. 3A and 3B are diagrams showing an example of the operation flow of the ruled line detection area setting unit. In FIG. 2A, a region surrounded by a dashed line and denoted by reference numeral 40 is an example of a character line region with a ruled line.

When the ruled line detection area setting unit 14 starts operation, first, the first marginal distribution creating unit 20 starts detecting the column cumulative pixel number of the ruled line character line area 40.

The first row peripheral distribution generator 20, a scanning position X in a ruled line with a character row region 40 and X _S (S1), the scanning image data on a predetermined column from the Y _T1 at position X to Y _B1 The number of black pixels between them, and thus the cumulative number of pixels in the column at position X
HL (X) is detected (S2). Then, the detected column accumulated pixel number HL (X) is stored in the first circumference distribution storage unit 22 as HL (X) of the position X.

 The column accumulated pixel number HL (X) can be expressed by the following equation (7).

Here, P (X, Y) represents image data, and P (X, Y)
Y) = 1 represents a black pixel and P (X, Y) = 0 represents a white pixel.

Next, the first marginal distribution creating unit 20 determines whether or not the column accumulated pixel number HL (X) at all positions X in the ruled-lined character line area 40 has been detected (S3). Returning to the first peripheral creation unit 20 adds 1 to X to detect a column cumulative number of pixels at the position X = X _E unless the next position X (S4) then S2, also if the position X = X _E Column cumulative number of pixels at all positions X
Assuming that HL (X) has been detected, the detection of the column cumulative pixel number is completed.

When the detection of the column accumulated pixel number is completed, the black block detection unit 24
Starts detection of the row direction starting end position X _L and the end position X _R,
The detection number n and the reading position X of HL (X) of the character is initialized to an initial value 1 and the initial value X _S. This together with the position X _S of the previous position X _S columns in -1 accumulated pixel number HL (X _S -1) of virtually HL (X _S -1) = 0 to (S5). Then position X
Is read from the first marginal distribution storage unit 22, and the read HL (X) is set to a predetermined threshold THL (for example, THL =
It is determined whether or not the HL (X) is a black block element in comparison with 1) (S6). Black block detector 24 is HL (X) ≧ THL
HL (X) is regarded as a black block element constituting a character, and HL (X) satisfying HL (X) <THL is regarded as a white block element constituting the ground of a recording medium.

When a black block element is detected in S6, the black block detection unit 24 calculates the column accumulated pixel number HL (X-1) of the position X-1 immediately before the position X where the black block element is detected by the first peripheral distribution. The HL (X-1) read from the storage unit 22 is compared with the threshold value THL to determine whether HL (X-1) is a white block element (S7). If the result of the determination in S7 is a white block element, the black block detection unit 24 indicates that a white block element has been detected at position X-1 and a black block element has been detected at position X. the Save as starting position X _BS (S8) and then subjected to S9 (S
9 will be described later). If the determination result in S7 is a black block element, the length of the black block X−
_XBS + 1 is calculated and the calculated length is used as the black block width determination unit 26.
Output to The black block width determination unit 26 that has input the length of the black block from the black block detection unit 24 sets the input length as a threshold.
Compare with BWJ (S10). The black block width determination unit 26 outputs the first determination result to the black block detection unit 24 when the input length exceeds the threshold BWJ, and outputs the second determination result when the input length is equal to or less than the threshold BWJ. . Black block detector 24
The position X to X for a column cumulative number of pixels read out to perform the re-detection of the black and white block element from the starting position X _BS of the black block of length exceeding the threshold BWJ if you enter the first determination result _The threshold value THL is set to _BS- 1, and the threshold value THL is increased by a predetermined amount UT (S11). Then, S9 is performed. If the second determination result is input, S9 is performed without performing S11.

Further, when detecting the white block element in S6, the black block detection unit 24 stores the column accumulated pixel number HL (X-1) of the position X-1 immediately before the position X of the white block element in the first peripheral distribution storage unit. 22 and read HL (X-1) to the threshold TH
It is determined whether or not HL (X-1) is a black block element by comparing with L (S1, 2). If the result of the determination in S12 is a black block element, the black block
In detects the end position X _BL black block detecting the white block element thus threshold BWJ less in length in the black block element and the position X (position X of the white block element
Is assumed to be _XBL before position X-1), and n =
It is determined whether it is 1 (S13).

When n = 1 in S13, the black block detection unit 24 regards a black block having a length equal to or less than the threshold value BWJ as a block forming a character, and determines the end position X _R ( n) represents the end position X _BL = X−1 of the black block having a length equal to or less than the threshold value BWJ and the start position X _{L of the} character
(N) as to store the start position X _BS of the black block of the threshold BWJ following length (S14). Next, the black block detection unit 24 initializes the threshold value THL to detect the line direction start position X _L (n) and line direction end position X _R (n) of the next character, and resets n to 1
Is added and the position X is set to X _R (n) (S15) and then S9
Perform

The distance between the black block when a black block detection unit 24 is not n = 1 in S13 constituting the character detected before one start position X _BS and the black block in the black block X _BS - (X _It is determined whether or not _R (n-1) +1) becomes zero (S16). Black block detector 24 is separated distance in S16
If X _BS − (X _R (n−1) +1) becomes zero, the corresponding B
A black block having a length equal to or less than WJ is regarded as a block constituting a ruled line, so that S9 is performed without performing S14 and S15,
If the separation distance X _BS − (X _R (n−1) +1) is not zero at 16, the black block having a length equal to or less than the BWJ is regarded as a block that constitutes a character, and thus S 14 and S 15 are replaced. Then, S9 is performed.

In S9, the black block detection unit 24 determines whether or not all the column accumulated pixel numbers HL (X) in the character part area 38 have been read. Black block detection unit 24, adds 1 because not finished reading the X = X _E unless all columns accumulated pixel number HL (X) in the X to read the next position X HL (X) in S9 and (S17) and then returns to S6, also X = X _E a long if black block detection unit 24 all columns cumulative number of pixels in S9 HL
(X) indicates that the detection of the start position X _L and the end position X _{R in} the line direction for all the characters in the character portion area 38 has been completed.

When black block detecting unit 24 finishes the detection of the position X _L and X _R, the detection area position determining unit 28 starts the setting of the first and second ruled line detection area. The detection area position determination unit 28 detects a black block at the start position X _L (n) and end position X _R (n) of the n-th character in the line direction, counting X in the ruled-lined character line area 40 in a gradually increasing direction. Read from part 24, read position X
_L (n), X _R from (n) and the equation (1) ~ (4), n -th of the first ruled line detection area of the character edge position X _LL (n), X
_LR (n) and edge positions X _RL (n), X _{RR of} the second ruled line detection area
(N) to set the ruled line detection area (S1
8), these positions _{X L (n), X R} (n) and the position X _LL (n),
X _LR (n), X _RL (n), and X _RR (n) are output to the control unit 18. The control unit 18 inputs the start and end positions in the row direction of the first to _nLS- th characters and the edge positions of the first and second ruled line detection areas, and stores them in each character.

When the detection area position determination unit 28 outputs the _nLS- th start and end positions in the row direction and the edge positions of the first and second ruled line detection areas, the ruled line detection area setting unit 14 ends the operation.

Here, the effect of the ruled line detection area setting unit 14 in the operation flow shown in FIG. 3 will be described with reference to FIG. In FIG. 2 (B), the region where the black block constituting the character exists is indicated by a solid line arrow, and the region where the black block having a length exceeding the threshold value BWJ exists is indicated by a chain line arrow. Here, the positions X ₂ and X ₄ shown in FIG. 2B are detected as the positions X _L (1) and X _R (1) shown in FIG. 2A, and similarly, the positions X ₅ and X _6. There position X _L (2), as X _R (2), position X _7, X ₈ is positioned X _L (3), the position as X _R (3)
X ₉ and X ₁₁ are as positions X _L (4), X _R (4) and at positions
X _12, X ₁₄ is positioned X _L (5), it shall be detected as X _R (5).

For example, when it is assumed that the distribution of the column cumulative pixel number shown in FIG. 2 (B) is obtained, the threshold THL is set as the initial value (THL1), and there is no restriction that the length of the black block constituting the character is BWJ or less. When, black block elements constituting the ruled lines and characters from the position X ₁ to X ₄ is detected as a black block Ichikatamariri. However, as is evident from FIG. 2 (B), a constraint is set so that the length of the black block is not more than the threshold value BWJ.
When a black block exceeding WJ is detected, the threshold value THL is changed from THL1 to T.
By changing to HL2 (= THL1 + UT) and re-detecting the black and white block elements, the positions X ₁ to X ₄
The black block consisting only of the black block elements constituting the characters up to is detected, the position X _{2 is set} to X _L (1) and the position X ₄
Can be detected as X _R (1).

When the threshold value THL is fixed to THL2, as shown in FIGS. 2A and 2B, a hyphen “−” exists between characters and a ruled line exists between adjacent characters A and B. In some cases, the hyphen "-" cannot be detected when there is no part. However, after detecting the start and end positions of one character in the line direction, the end position X of the detected character is detected.
_BL, for example, from the position X ₄ +1 next to X _R (1) = X _{4, using} the threshold value THL as the initial value THL1 to detect black and white block elements, thereby detecting the starting position and the ending position of the hyphen “−” in the row direction. Can also do. That hyphen "-" row starting position and end position of X ₅ and X ₆ position X _L (2), X
_R (2) can be detected.

According to this embodiment, when a black block equal to or less than the threshold BWJ is detected, the separation distance between the black block equal to or less than the threshold BWJ and the black block that constitutes the previous character is checked.
When the separation distance is zero, that is, when the black block of the value BWJ or less is in contact with the black block of the immediately preceding character, the black block of the threshold BWJ or less is converted to a block forming a ruled line. The start position and the end position of the black block that is equal to or less than the threshold value BWJK are not detected as the start position and the end position in the row direction. When the separation distance is not zero, that is, when the black block of the threshold BWJ or less and the black block of the previous character are separated from each other, the black block of the threshold BWJ or less is defined as a block forming the character. The start position and the end position of the black block that is not more than the threshold value BWJ are detected as the start position and the end position in the row direction. By this arrangement, when detecting a black block constituting the A and borders a black block having a length less than the threshold BWJ between from the position X ₁₄ to X ₁₅ in the case of setting the THL1 example as a threshold value THL However, the start and end positions of the black block need not be detected as the start and end positions in the row direction.

Next, the description returns to the flow of the operation after the ruled line detection area setting unit 14 ends the operation. If ruled line detection area setting unit 14 ends the operation, the control unit 18 row start position and end position and the edge position of the first and second ruled line detection area, one character from the first character to the n _LS-th character It is output to the character ruled line separation unit 16 every time. The character rule separation unit 16 inputs the start position and end position of one character in the row direction and the edge positions of the first and second rule detection areas, and based on these positions, detects the character string of one character whose position is detected. The start position and the end position in the direction (hereinafter, referred to as the start position in the column direction and the end position in the column direction) are detected and output to the control unit 18. The control unit 18 is a character line separation unit
When the start and end positions in the column direction for one character from 16 are input, the input start and end positions in the column direction and the start and end positions in the row direction of the detected character in the column direction are extracted as character extraction information. At the same time, the start and end positions of the next character in the line direction and the edge positions of the first and second ruled line detection areas are output to the character ruled line separation unit 16.

When the control unit 18 inputs the column start and end positions of the n _LS th character from the character ruled line separating section 16, and a column start position and end position in the row direction starting end position and the end position of the n _LS-th character After the output, the character extraction for one character line ends.

Hereinafter, with reference to FIG. 4 and FIG.
Will be described in detail.

FIG. 4 (A) is a diagram mainly showing image data of one character, and FIGS. 4 (B) and (C) are the first row cumulative pixel count and the second row cumulative of the image data shown in FIG. 4 (A). It is a figure showing distribution of the number of pixels. FIGS. 5A and 5B are diagrams showing an example of the operation flow of the character ruled line separation unit.

Character ruled line separating section 16, to the row direction starting end position and the end position X _L (n) and X _R (n) from the control unit 18, end edge positions X _LL of the first ruled line detection area (n), X _LR (n ) And the edge positions X _RL (n) and X _RR (n) of the second ruled line detection area, the
Th detected by the start of the column start position and end position Y _T and Y _B character, first the second peripheral distribution creation unit 30 of the n-th character first ruled line detection area 42 the number of rows accumulated pixel BLH (Y)
Then, the detection of the row cumulative pixel number BRH (Y) in the second ruled line detection area 44 is started. In FIG. 4, the first ruled line detection area 42 is indicated by a three-dot chain line, and the second detection area 44 is indicated by a four-dot chain line.

Second marginal distribution creating unit 30 that has started detecting the row cumulative pixel count
Sets the scanning position Y in the predetermined column direction to Y _T1 (* S1), and then scans the image data in the predetermined row direction at the position Y to determine the position from X _LL (n) to X _LR (n). The number of black pixels between them is counted, the first row cumulative pixel number BLH (Y) is detected, and the detected BLH (Y) is stored in the second peripheral distribution storage unit 32 as the first row cumulative pixel number at the position Y. . At the same time, the image data is scanned at the position Y and X _RL (n) is
_The number of black pixels up to _RR (n) is counted, the second row cumulative pixel number BRH (Y) is detected, and the detected BRH (Y) is used as the second row cumulative pixel number at the position Y to obtain the second peripheral distribution. It is stored in the storage unit 32 (* S2).

The row accumulated pixel numbers BLH (Y) and BRH (Y) can be expressed by the following equations (8) and (9).

Next, the second margin distribution creating unit 30 sets the ruled line detection areas 42 and 44
It is determined whether or not the total number of row pixels has been detected at all the positions Y in (* S3). If the position Y is not equal to Y _B1 , one is added to the position Y (* S4) in order to detect the number of accumulated pixels at the next position Y (* S4), and then the process returns to * S2. If the position Y = Y _E , the column cumulative pixel numbers BLH (Y) and BRH (Y) at all the positions Y
Is detected, and the detection of the row cumulative pixel number is completed.

Row Upon completion of the cumulative number of pixels detecting ruled line detection unit 34 starts the detection of the column direction starting end position Y _T and the column end position Y _B, BL
Reading position Y H (Y) is set to Y _S as Y _LS1 (* S5). Here, Y _S = (Y _T1 −Y _B1 ) / 2. Next, the column accumulated pixel number BLH (Y) at the position Y is stored in the second peripheral distribution storage unit 32.
The BLH (Y) by comparing the read, the read BLH a (Y) with a predetermined threshold value THL _L from determines whether black block elements (* S6).

The value of THL _L may be any suitable value to obtain the THL _L, for example by the following equation (10) in this example.

When detecting a black block element in * S6, the ruled line detection unit 34 detects a ruled line, and stores the detection position Y of the black block element as a ruled line detection processing result _YLT (* S7), and then * S10 Do. * If it does not detect the black block in S6, judges read Taka whether all BLH a (Y) from Y _LS1 to Y _T1 (* S8). * If Y = Y _T1 in S7, all the BLH (Y) have been read out without detecting the ruled line. Therefore, the position Y = Y _T1 is stored as the ruled line detection processing result _YLT (* S7) and then * Perform S10. * Unless Y = Y _{T1 at} S7, 1 from position Y to read BLH (Y) at next position Y
Subtract (* S9), then return to * S6.

The ruled line detector 34 sets the read position Y of BLH (Y) to Y by * 10.
It is set to Y _B2 as the _LS2. Then read position Y column cumulative number of pixels BLH a (Y) from the second peripheral distribution storage unit 32, the reading BLH a (Y) is compared with a threshold value THL _L BLH (Y) is determined whether the black block elements (* S11).

When detecting a black block element in * S11, the ruled line detection unit 34 detects a ruled line, and stores the detected position Y of the black block element as a ruled line detection processing result _YLB (S12), and then performs * S15. . * If it does not detect the black block elements in S11, determines read Taka whether all BLH a (Y) from Y _LS2 to Y _B1 (* S13). * Y = Y _{B1 in} S13
Because it if finished reading of all BLH without detecting a ruled line (Y) is to store the position Y = Y _B1 as ruled line detection processing result Y _LB (* S12) then * S15 performs. * Y in S13
If not = Y _B1 , 1 is added to position Y to read BLH (Y) at the next position Y (* S14), and then the process returns to * S11.

The ruled line detection unit 34 sets the read position Y of BRH (Y) in * S15.
Set to Y _T2 as Y _RS1 . Then read position Y column cumulative number of pixels BRH a (Y) from the second peripheral distribution storage unit 32, the BRH the read BRH a (Y) compared with a threshold value THL _R (Y) is whether black block elements Judge (* S16).

The value of THL _R can be any suitable value. In this example, THL _R is obtained by, for example, the following equation (11).

Border detector 34 when detecting the black block elements * S16 stores the detection position Y of the black block element as ruled line detection processing result Y _RB (* S17), then * S20 performs. If no black block element is detected in * S17, it is determined whether or not all BRH (Y) from Y _RS1 to Y _T1 have been read (* S18). * If Y = Y _T1 in S18, all the BRH (Y) have been read out without detecting the ruled line, and the position Y = Y _T1 is stored as the ruled line detection processing result Y _RT (*
S17) Then, * S20 is performed. Unless Y = Y _{T1 in} * S18, 1 is subtracted from the position Y to read the BRH (Y) at the next position Y (* S19), and then the process returns to * S16.

The ruled line detection unit 34 sets the read position Y of BRH (Y) in * S20.
Set to Y _B2 as Y _RS2 . Then read position Y column cumulative number of pixels BRH a (Y) from the second peripheral distribution storage unit 32, the BRH the read BRH a (Y) compared with a threshold value THL _R (Y) is whether black block elements It is determined (* S21).

When detecting a black block element in * S21, the ruled line detection unit 34 stores the detected position Y of the black block element as a ruled line detection processing result Y _RB (* S22), and executes the ruled line detection processing of the nth character. The detected Y _LT , Y _LB , Y _RT, and Y _RB are output to the ruled line separation position determining unit 36, and the ruled line detection process is completed. * If it does not detect the black block elements in S21, determines read Taka whether all BRH a (Y) from Y _RS2 to Y _B1 (* S23). * If Y = Y _B1 in S23, all the BRH (Y) have been read out without detecting the ruled line, and the position Y = Y _B1 is stored as the ruled line detection processing result Y _RB (*
S22), the n-th character in the ruled line detection processing result as the detected Y _LT, Y _LB, ends the output was ruled line detection process with respect to Y _RT and Y _RB borders separating position determination unit 36. * Unless Y = Y _{B1 in} S23, 1 is set at position Y to read out BRH (Y) at next position Y
Add (* S24) and then return to * S21.

Borders separating position determination unit 36 inputs the ruled line detection processing result from the border detector 34 in accordance with Equation (5) and (6), the n-th column start position of a character Y _T and the column end position Y _B detected (* S25), and outputs the detected Y _T and Y _B to the control unit 18.

For example, from the image data shown in FIG. 4, yet it is offset as a column start position Y _T letter Y _LT Y _RB is detected as the and column end position, thus the true row direction of the image from a given row direction Even if the character 46 and the ruled line 48 are in contact,
The character 46 and the ruled line 48 can be separated and cut out.

The present invention is not limited to the above-described embodiment. Therefore, the operation flow of each component, input / output signals, operation timing, connection relationship, and configuration can be arbitrarily and suitably changed.

For example, in the above-described embodiment, a description has been given of an example in which the character start and end positions in a predetermined line direction and the character start and end positions in a predetermined column direction are detected using image data of a horizontally written document as an example. Obviously, can be applied to vertically written documents.

FIG. 6 is a diagram showing an example of image data of a vertically written document. For example, as shown in the figure, if an XY coordinate system is set on the image memory and the X axis is set to a predetermined row direction, the character starting position in the predetermined row and column direction characters and The end position can be detected.

(Effects of the Invention) As is clear from the above description, according to the character extracting apparatus of the present invention, when a black block whose length in a predetermined line direction exceeds a length threshold is detected, the block threshold is increased by a predetermined amount. Increase and re-detect the black and white block elements from the starting position of the black block exceeding the length threshold again,
When the end position of the black block equal to or less than the threshold value is detected, the start position and the end position of the black block equal to or less than the length threshold value are detected as the character start position and the end position in a predetermined line direction. Therefore, it is not necessary to detect a black block whose length exceeds the character width by setting the length threshold arbitrarily and appropriately,
Moreover, since re-detection of black and white block elements is repeated until the length becomes equal to or less than the length threshold value, only black blocks within the character width can be detected, so that the detection accuracy of the character start position and the character end position can be improved.

Further, the detection of the character start position and the end position in the predetermined column direction is performed based on the change of the cumulative black pixel number in the predetermined row direction in the first and second ruled line detection areas. Since the processing is started from the processing, the detection processing of these start and end positions can be simplified.

Moreover, since the first ruled line detection area is set to include a ruled line at a position adjacent to the character start position in the predetermined line direction and opposite to the character end position in the predetermined line direction,
It is possible to prevent black pixels constituting a character from being counted or hardly counted as the cumulative number of black pixels in the predetermined row direction in the first ruled line detection area. As a result, the position of the ruled line in the first ruled line detection area can be detected with high accuracy. Similarly, the second ruled line detection area is set to include a ruled line at a position adjacent to the character end position in the predetermined line direction and opposite to the character start position in the predetermined line direction. The constituent black pixels can be prevented from being counted or hardly counted as the cumulative number of black pixels in a predetermined row direction in the second ruled line detection area. As a result, the position of the ruled line in the second ruled line detection area can be detected with high accuracy.

Therefore, since the position of the ruled line in the first and second ruled line detection areas can be detected with high accuracy, even if the predetermined line direction is slightly shifted from the true line direction of the image, and / or the ruled line is in contact with the character. However, a character can be cut out at a character start position and an end position in a predetermined column direction so that the character is not chipped or the character is cut less than before.

Further, since the ruled line detection in the first and second ruled line detection areas is performed based on the change in the cumulative number of pixels, and therefore the detection of the cumulative black pixel number and the threshold processing are performed, the ruled line detection in these areas can be performed by simple processing. You.

Therefore, according to the character extracting apparatus of the present invention, even if the predetermined line direction is deviated from the true line direction, it is possible to accurately detect the start and end positions of characters in the predetermined line and column directions by simple processing. Can be provided. In addition, since the processing is simple, the structure of the apparatus can be reduced in size and simplified, so that a low-cost character extracting apparatus can be obtained.

If the present invention is applied to a character recognition device, for example, when characters or ruled lines are printed on the document with a slight inclination, even if the reading unit main-scans the document in a direction that deviates from the true line direction, characters are not recognized. It is possible to cut out with high accuracy, and therefore, it is possible to perform accurate character recognition.

[Brief description of the drawings]

FIG. 1 is a functional block diagram showing an example of the configuration of an embodiment of the present invention. FIGS. 2 (A) and (B) are diagrams showing the distribution of image data and the cumulative number of black pixels in a column. FIG. 3 (A) 4A and 4B are diagrams showing an example of the flow of the operation of the ruled line detection area setting unit, FIG. 4A is a diagram showing an example of one character image data, and FIGS. 4B and 4C are first diagrams. FIGS. 5A and 5B are diagrams showing an example of the distribution of the cumulative number of row pixels in the ruled line detection area and an example of the distribution of the cumulative number of row black pixels in the second ruled line detection area. FIGS. FIG. 6 is a diagram showing an example of an operation flow. FIG. 6 is a diagram showing an example of image data of a vertically written document. 10 reading unit 12 image data storage unit 14 ruled line detection area setting unit 16 character ruled line separation unit 18 control unit 20 first peripheral distribution creating unit 22 first peripheral distribution storage Unit 24 Black block detecting unit 26 Black block width determining unit 28 Detection area position determining unit 30 Second peripheral distribution creating unit 32 Second peripheral distribution storage unit 34 Ruled line detecting unit 36 ... Ruled line separation position determination unit.

Continued on the front page (58) Fields surveyed (Int.Cl. ⁶ , DB name) G06K 9/20 G06K 9/34

Claims (1)

(57) [Claims] A reading unit that optically reads an information medium on which a character line with a ruled line is described and outputs image data of the information medium; an image data storage unit that stores image data from the reading unit; The image data in the character line area with a ruled line in the image data storage unit is scanned, and the cumulative number of black pixels in a predetermined column direction is detected for each scanning line. The number of accumulated black pixels in the column direction less than the block threshold is detected as a white block element, and when a black block exceeding the length threshold in a predetermined row direction is detected, the block threshold is increased by a predetermined amount to exceed the length threshold. When the black and white block elements are detected again from the start position of the black block, and the end position of the black block having the length threshold or less is detected, the start position of the black block having the length threshold or less is detected. And the end position are detected as a character start position and end position in a predetermined line direction, and the block threshold value is initialized. Based on the character start position and end position in the predetermined line direction, the first ruled line detection area is set to a predetermined line direction. Is set for each character so as to include a ruled line at a position adjacent to the character start position in the direction and opposite to the character end position in the predetermined line direction, and the second ruled line detection area is set to the character end position in the predetermined line direction A ruled line detection area setting unit that sets a ruled line for each character so as to include a ruled line on a side adjacent to a character starting end position in a predetermined line direction and a first and second ruled line detection in the image data storage unit The image data in the area is scanned to detect the cumulative number of black pixels in a predetermined row direction for each scanning line, and based on the change in the cumulative number of black pixels in the row direction, the ruled lines in the first and second ruled line detection areas are detected. Perform the processing for each character, A character ruler separating unit configured to set a character start position and an end position in the predetermined column direction for each character based on the ruled line detection processing result.