JP4497974B2 - Image processing apparatus, image processing method, program, and storage medium - Google Patents

Description

  The present invention relates to an image processing apparatus, an image processing method, a program, and a storage medium that automatically detect the inclination of a document image.

  By automatically correcting the inclination of the document image read from the scanner or the like, it is possible to improve the accuracy of document image analysis processing such as area division and character recognition. For example, the document direction is automatically detected, the projections in the row direction are obtained in two search windows arranged along the row direction, one window is fixed, and the other window is set as the row direction. A technique is disclosed in which the tilt amount of the document image is obtained from the vertical shift amount of the two windows and the distance in the row direction when the correlation between projections is maximized while shifting in the vertical direction (see, for example, Patent Document 1). .)

  According to the invention described in Patent Document 1, the projection indicates the position of the character line existing inside the window, and the correlation between the projections of both windows is maximized when the positions of the lines match. Then, the inclination of the document image can be determined from the inclination of the character line.

In addition, a plurality of window sets are set so as to spread over the entire document image, and the inclination as the document image is obtained based on the magnitude of the inclination obtained from the plurality of positions. As described above, according to the invention described in Patent Document 1, by using the projection in the row direction in the set window on the character image, the character image can be processed at a high processing speed and with a small storage area. A tilt detection method is disclosed.
Japanese Patent Laid-Open No. 9-6914

  However, the invention described in Patent Document 1 has a drawback in that when two windows arranged in the line direction do not exist on the same character line, the inclination of the character line cannot be extracted appropriately. It was. For example, because two windows are arranged at a predetermined interval, the same column (same character line) may not be present in the two windows, or a column present in one window may be the other window. If it does not exist in the document, the invention described in Patent Document 1 cannot properly extract the inclination of the document image.

  The present invention has been made in consideration of such circumstances, and it is possible to reliably acquire the range in which the character lines are continuous in the document image and appropriately acquire the inclination of the character lines. An object of the present invention is to provide an image processing apparatus, an image processing method, a program, and a storage medium that can determine the inclination of a document image with higher accuracy.

In order to solve the above problems, an image processing apparatus according to the present invention, a predetermined position in the document image input, a reference setting means for setting the partial image area of a predetermined size as a reference partial image area A reference projection detecting means for detecting a projection of a character line included in the reference partial image area, and a first part at a position slid by the width of the partial image area from the position of the reference partial image area toward the line leading end. A first partial image area setting means for setting an image area; a projection position of a character line detected from the newly set first partial image area; and a line end direction of the first partial image area. A first determination unit that determines whether the projection of the character line has continuity by comparing the position of the projection of the character line detected from within the adjacent partial image region; and the first determination unit Determined to be non-continuous Until the position of the first partial image area set at that time is shifted by the width of the partial image area in the row leading direction, a new first partial image area is set and the first determination means The first partial image area set immediately before the first partial image area set when the first determination means determines that there is no continuity is repeated at the end of the row. And a second partial image that sets a second partial image region at a position slid by the width of the partial image region in the row end direction from the position of the reference partial image region. Area setting means, the projection position of the character line detected from the newly set second partial image area, and the partial image area detected in the line leading direction of the second partial image area. The position of the projected character line The second determination means for determining whether or not the projection of the character line has continuity by comparing the above and the second determination means is set at that time until it is determined that there is no continuity. A new second partial image area is set at a position slid by the width of the partial image area from the position of the second partial image area in the row end direction, and the determination by the second determination unit is repeated, and the second determination is performed. A row end partial image for determining a second partial image region set immediately before the second partial image region set when it is determined by the means that there is no continuity as a partial image region at the end of the row Detected from an area determination means, a projection detected from the partial image area at the line leading end determined by the line leading end partial image area determining means, and a line end partial image area determined by the line end partial image area determining means And the correlation between , Based on the distance between the destination end of the partial image region and the line termination of the partial image area, characterized in that it comprises a determination means for determining the inclination of the document image.

The image processing method according to the present invention is an image processing method in an image processing apparatus, wherein the reference setting means of the image processing apparatus is determined in advance at a predetermined position in a document image input to the image processing apparatus. A reference setting step of setting a partial image region of a specified size as a reference partial image region , and a reference projection detection in which a reference projection detection means of the image processing device detects a projection of a character line included in the reference partial image region And a first partial image area setting unit of the image processing apparatus sets the first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area in the row leading direction. A first partial image region setting step, and the first determination unit of the image processing apparatus detects a projection of a character line detected from the newly set first partial image region, and the first partial image region of A first determination step of determining whether or not the projection of the character line has continuity by comparing the projection position of the character line detected from within the partial image region adjacent in the end direction; and the image processing The partial image area in the line leading direction from the position of the first partial image area set at that time until the line leading partial image area determining means of the apparatus determines that there is no continuity in the first determination step A new first partial image area is set at a position slid by the width of, and the determination in the first determination step is repeated, and is set when it is determined that there is no continuity in the first determination step. A line leading edge partial image area determining step of determining a first partial image area set immediately before the first partial image area as a partial image area at the line leading edge; and second partial image area setting of the image processing apparatus Means for the reference partial image A second partial image area setting step of setting a second partial image area from the position of the band in a position to width of the slide of the partial image area in the row end direction, the second judging means of the image processing apparatus, the new The position of the projection of the character line detected from within the second partial image area set to the position of the character line and the position of the projection of the character line detected from within the partial image area adjacent to the line tip direction of the second partial image area And a second determination step for determining whether or not the projection of the character line has continuity, and a line end partial image region determination means of the image processing device in the second determination step. Until it is determined that there is no image, a new second partial image area is set at a position slid by the width of the partial image area in the row end direction from the position of the second partial image area set at that time. Repeat the determination in the second determination step. The second partial image area set immediately before the second partial image area set when it is determined that there is no continuity in the second determination step is determined as the partial image area at the end of the row. A line end partial image region determining step to be performed, and a projection detected by the determining means of the image processing device from the partial image region at the line front end determined in the line leading end partial image region determining step and the line end partial image region determining The document image based on the correlation between the projection detected from the partial image area at the end of the line determined in the process and the interval between the partial image area at the top of the line and the partial image area at the end of the line And a determining step for determining the slope of the.

Further, according to the present invention, a reference setting means for setting a computer as a reference partial image area at a predetermined position in the inputted document image as a reference partial image area with a predetermined size is provided. A reference projection detecting means for detecting a projection of the included character line, and a first part for setting the first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area toward the leading edge of the line Detecting from the image area setting means, the position of the projection of the character line detected from the newly set first partial image area, and the partial image area adjacent to the line end direction of the first partial image area The first determination means for determining whether or not the projection of the character line has continuity by comparing the position of the projected character line with the projection position, and the first determination means determines that there is no continuity. Until then A new first partial image area is set at a position slid by the width of the partial image area from the position of the first partial image area in the row leading direction, and the determination by the first determination unit is repeated, A row for determining the first partial image region set immediately before the first partial image region set when the first determination unit determines that there is no continuity as the partial image region at the head of the row. Tip partial image region determining means; second partial image region setting means for setting a second partial image region at a position slid by the width of the partial image region in the row end direction from the position of the reference partial image region; The projection position of the character line detected from the newly set second partial image area and the projection of the character line detected from the partial image area adjacent to the second partial image area in the line leading direction. By comparing with the position A second determination means for determining whether the projection of the character line has continuity, the second until it is determined that there is no continuity at decision means, said second partial image that is set at that time A new second partial image area is set at a position slid by the width of the partial image area in the row end direction from the position of the area, and the determination by the second determination means is repeated. A line end partial image area determining means for determining a second partial image area set immediately before the second partial image area set at the time when it is determined that there is no line end as a line end partial image area; Between the projection detected from the partial image area at the line leading end determined by the line leading end partial image area determining means and the projection detected from the partial image area at the line end determined by the line end partial image area determining means And the partial image at the top of the line It is a program for functioning as a determining means for determining an inclination of the document image based on an interval between an image region and the partial image region at the end of the line.

  Furthermore, the present invention is a computer-readable storage medium characterized by storing the above program.

  According to the present invention, it is possible to reliably acquire a range in which character lines are continuous in a document image and appropriately acquire the inclination of the character line, so that the inclination of the document image can be obtained with higher accuracy. it can.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

<First Embodiment>
FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to the first embodiment of the present invention. In FIG. 1, reference numeral 101 denotes a CPU that controls the entire image processing apparatus according to a control program stored in the ROM 102. Reference numeral 102 denotes a ROM that stores a control program of the image processing apparatus executed by the CPU 101 in accordance with a processing procedure shown in a flowchart to be described later. Reference numeral 103 denotes a RAM for storing document images and the like, and 104 denotes an external storage device such as a magnetic disk. Furthermore, 105 is a display, 106 is a keyboard, 107 is a pointing device such as a mouse, and 108 is a scanner for reading an image from a paper document or the like.

  Furthermore, the CPU 101, ROM 102, RAM 103, external storage device 104, display 105, and scanner 108 described above are connected to each other via a bus 110.

  Note that the image processing performed by the image processing apparatus according to the present embodiment can also be performed by a general-purpose computer. In this case, a control program provided on a storage medium or the like is stored in the external storage device 104 and the operator's It may be configured to be executed by the CPU 101 according to an instruction or the like. FIG. 7 is a diagram for explaining an example of a memory map of a storage medium that stores various data processing programs that can be read by the image processing apparatus according to the first embodiment. A group of program codes to be executed by a computer is stored. Reference numeral 109 denotes a network interface (I / F) that communicates with an information processing apparatus or the like that exists in a remote place, and that reads and writes programs and data, and is connected to the bus 110. Has been.

  The devices such as the scanner 108 and the display 105 may not be directly connected to the bus 110 but may be connected via the network I / F 109.

  The image processed by the image processing apparatus is an image optically read from a paper document or the like by the scanner 108, an image stored in the external storage device 104, or a network from another image input device or the like. What was received via I / F109 can be used. Further, in the present embodiment, the inspection area for detecting the tilt and the document direction in the inspection area are determined for the image obtained in this manner using a known technique. For example, the inspection area can be determined by removing margins of the input image, or can be determined by extracting a text area from document layout information.

  FIG. 2 is a flowchart for explaining a processing procedure for detecting a tilt amount of a document image input from the inspection area by the image processing apparatus according to the first embodiment. First, a detection position for detecting a local inclination of a character line or the like existing in the inspection area is determined for the inspection area in the document image determined using a known technique (step S201). For example, the detection positions are distributed at equal intervals over the entire inspection region, or are varied using random numbers.

  Next, a detection window having a predetermined size is set at the detection position determined in step S201, and is set as a reference detection window (step S202). In this embodiment, as an example, a rectangular partial image region is used as a detection window.

  Then, the projection in the row direction within the reference detection window is acquired (step S203). Here, the projection means that each pixel is scanned in the row direction, and if there is a black pixel (a pixel constituting the character portion), it is determined that the row is projected. As a result, the height of the character line existing in the detection window is obtained as a projection. Then, it is determined whether or not the obtained projection includes a projection of a character line (step S204).

  FIG. 4 is a diagram for explaining detection windows and projections in the row direction set by the image processing apparatus according to the first embodiment. In FIG. 4, 401 is the detection window set in step S202, and 402 is the projection acquired in step S203. As shown in FIG. 4, when a character line is included in the detection window, a projection corresponding to the line height of the character line exists in the detection window. The projection does not exist in the detection window, the projection length is short relative to the height of the detection window, or the projection extends over the entire height of the detection window. In this case, it is determined that the line projection is not included (No), and the process proceeds to step S216 to check whether the inclination angles have been obtained at all the detection positions. As a result, when there is a remaining detection position (that is, a reference detection window for which the inclination angle has not been obtained) (No), the process moves to the next detection position (step S217) and returns to step S201 again. Repeat the above process.

  On the other hand, if it is determined in step S204 that the projection of the character line is included (Yes), a new detection window is set at a position shifted by the width of the detection window in the line direction (step S205). For example, in the case of horizontal writing, it is shifted by the width of the detection window in the right direction (slides by the width of one detection window in the right direction). Then, the projection in the row direction in the new detection window is acquired (step S206).

  Next, the projection of the new detection window is compared with the projection of the adjacent detection window processed immediately before to check whether the projection of the character line has continuity (step S207). For example, when the projection overlap is sufficiently large, it is assumed that the projections are continuous. As a result, if it is determined that there is continuity (Yes), the process returns to step S205, and the detection window is further shifted to the right by the width of one detection window to see the continuity. On the other hand, when it is determined that there is no continuity (No), it is considered that the reference detection window is a continuous range of character lines until the previous detection window is processed. A window at the end of the line is set (step S208).

  Next, a new detection window is set at a position where the detection window of interest is shifted from the reference detection window by the width of the detection window in the direction opposite to the character line (step S209). For example, in horizontal writing, the detection window is shifted to the left by the width of the detection window. Then, a projection in the row direction of the new detection window is acquired (step S210).

  Then, the projection of the new detection window is compared with the projection of the adjacent detection window that was processed immediately before, and in the same way as described above, whether or not the projection of the character line is continuous. Check (step S211). As a result, if it is determined that there is continuity (Yes), the process returns to step S209, and the detection window is further shifted to the left by one detection window to perform the same processing. On the other hand, when it is determined that there is no continuity (No), it is determined that the character line is continuous from the reference detection window to the previously processed detection window, and the detection window is defined as the window at the top of the line. (Step S212). In addition, you may comprise so that it may shift to the direction opposite to a row | line | column first, and may be shifted to a row direction (right direction) after that.

  The state of the processing so far will be described with reference to FIG. FIG. 5 is a diagram for explaining continuity determination processing using detection windows set on the same character line by the image processing apparatus according to the first embodiment. In FIG. 5, reference numeral 501 denotes a reference detection window. If the window is shifted in the row direction (right direction) and it is determined that there is no continuity of the row at the position 503, the immediately preceding 502 position is the row end window. Further, when the window is shifted in the direction opposite to the row direction (left direction) and it is determined that there is no continuity of the row at the position 505, the previous position 504 becomes the window at the front end of the row.

  Next, it is determined whether or not the detection window at the line leading end determined at step S212 and the line end detecting window determined at step S208 are the same (step S213). As a result, if it is determined that they are the same (Yes), it is determined that there is no continuity of the character line, and the process proceeds to step S216, where it is determined whether the inclination angles have been obtained at all the detection positions as described above. That is, the case where it is determined that they are the same is a case where it is determined that the detection windows set so as to be shifted to the left and right of the reference detection window set first do not include any row projection.

  On the other hand, when it is determined in step S213 that they are not the same (No), the local inclination angle is obtained using the projection information of the detection window existing between the detection window at the front end and the end of the line (step S214). ). Then, the obtained inclination angle is stored (step S215), and the process proceeds to step S216.

  If it is determined in step S216 that the processing at all detection positions has been completed (Yes), the inclination angle of the input image is determined from the stored local inclination angle (step S218). For example, they can be determined by using the average value or median value of all inclination angles.

  Next, how to determine the tilt angle in step S214 will be described using the flowchart of FIG. That is, FIG. 3 is a flowchart for explaining details of the detailed processing in step S214 in the flowchart of FIG. First, the detection window at the front end is fixed, and the detection window at the end is shifted in the direction perpendicular to the row (step S301). Then, the shift amount of both windows when the projections of both detection windows have the maximum correlation is obtained (step S302). Then, the inclination angle is obtained from the deviation amount obtained in step S302 and the interval between the two detection windows (step S303).

  FIG. 6 is a diagram for explaining the correlation of the projection of the detection window in the image processing apparatus according to the first embodiment. In FIG. 6A, 601a is a set first detection window, and 602a is a projection in the detection window 601a. Similarly, 601b is a second detection window set as a pair of detection windows 601a, and 602b is a projection in the detection window 601b. FIG. 6B is a graph 605 showing the detection window 604 shifted up and down with respect to the fixed detection window 607 and the magnitude of the correlation. Here, the inclination angle θ has a relationship of tan θ = t / d using the shift amount t when the correlation is maximum and the distance d of the detection window. Note that if the shift upward to t is positive and the shift downward is negative, it is possible to determine which is inclined by the sign. The same is true if the detection window at the end is fixed and the detection window at the end is shifted.

  As described above, according to the image processing apparatus according to the present embodiment, two detection windows can be reliably set within the same character line range, and the column width in the character direction included in each window can be set. Since the tilt angle of the character line can be appropriately calculated by making full use, the tilt of the document image can be detected with high accuracy.

  In the above-described embodiment, the description is given with the minimum configuration requirements for implementing the technical idea of the present invention. For example, an image processing program that performs processing for implementing the present invention on a general-purpose computer Such data may be provided from the outside, or may be stored in advance in the external storage device 107 and stored in the RAM 103. Further, an input image stored in advance in the external storage device 107 may be processed.

<Second Embodiment>
Next, a second embodiment executed by an image processing apparatus similar to the image processing apparatus shown in FIG. 1 will be described. In this embodiment, as another embodiment for obtaining the tilt angle from the projection information, a detection window just before the front-end detection window and a terminal detection window obtained by the same method as in the first embodiment are used. A detection window in front is used to obtain a correlation between projections in both detection windows. By doing so, it is possible to avoid the use of the projection of the leading and trailing portions of a character line that is likely to include symbols such as punctuation marks, and to further improve the accuracy of inclination detection.

  Moreover, you may comprise so that the inclination | tilt angle of the said character line may be calculated | required by several combinations using the some detection window judged to be in the same character line. In this case, an average of a plurality of inclination angles obtained from a plurality of combinations may be obtained to obtain a final inclination angle. Or you may make it obtain | require an average value by the value except the maximum value and minimum value of several inclination angles. Furthermore, a median value or mode value of a plurality of inclination angles may be used as the final inclination angle.

  Further, all of the deviation amounts from which the maximum correlation between adjacent detection windows can be obtained may be obtained, and the tilt angle may be calculated using a least square method or other optimization method.

  According to the present embodiment, it is possible to increase the detection accuracy when obtaining the amount of deviation from which the maximum correlation can be obtained, so that the inclination of the document image can be obtained more accurately and stably.

<Third Embodiment>
Next, a third embodiment executed by an image processing apparatus similar to the image processing apparatus shown in FIG. 1 will be described. In the present embodiment, as another embodiment for determining the same character line, a new detection window is set at a position further away from the width of the reference detection window. Note that the distance from the adjacent detection window is a predetermined value within a range in which it can be determined that they are the same character line. Alternatively, the character line height may be estimated from the projection obtained from the reference detection window, and the setting position of the next detection window may be determined from the value.

In the above-described embodiment, when the leading and trailing ends of the character lines included in the reference detection window are not the same window (in the case of No in step S214), the character lines of at least two detection window widths or more are consecutive. Therefore, the inclination of the character line is calculated. However, in step S214, the inclination of the character line may be calculated only when the detected length of the character line is equal to or greater than a certain value. Thus, since the inclination is not calculated for a short character line, the inclination of the document image can be obtained with higher accuracy.

  According to the present embodiment, the effect that the number of detection windows is reduced and the processing speed is increased can be obtained.

<Other embodiments>
As described above, the embodiment has been described in detail. However, the present invention can take an embodiment as a system, apparatus, method, program, storage medium, or the like, and specifically includes a plurality of devices. The present invention may be applied to a system that is configured, or may be applied to an apparatus that includes a single device.

  In the present invention, a software program (in the embodiment, a program corresponding to the flowchart shown in the drawing) that realizes the functions of the above-described embodiment is directly or remotely supplied to the system or apparatus, and the computer of the system or apparatus Is also achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, or the like.

  As a recording medium for supplying the program, for example, floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card ROM, DVD (DVD-ROM, DVD-R) and the like.

  As another program supply method, a client computer browser is used to connect to an Internet homepage, and the computer program of the present invention itself or a compressed file including an automatic installation function is downloaded from the homepage to a recording medium such as a hard disk. Can also be supplied. It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, the present invention includes a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer.

  In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. It is also possible to execute the encrypted program by using the key information and install the program on a computer.

  In addition to the functions of the above-described embodiments being realized by the computer executing the read program, the OS running on the computer based on the instruction of the program is a part of the actual processing. Alternatively, the functions of the above-described embodiment can be realized by performing all of the processes.

  Furthermore, after the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion board or The CPU or the like provided in the function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing.

1 is a block diagram illustrating a configuration of an image processing apparatus according to a first embodiment of the present invention. 6 is a flowchart for explaining a processing procedure for detecting a tilt amount of a document image input from within an inspection area by the image processing apparatus according to the first embodiment. It is a flowchart for demonstrating the detailed processing content of step S214 in the flowchart of FIG. It is a figure for demonstrating the projection of the detection window and row direction which are set with the image processing apparatus which concerns on 1st Embodiment. It is a figure for demonstrating the acquisition process of the detection window of the same character line by the image processing apparatus which concerns on 1st Embodiment. It is a figure for demonstrating the correlation of the projection of the detection window in the image processing apparatus which concerns on 1st Embodiment. It is a figure for demonstrating an example of the memory map of the storage medium which stores the various data processing program which can be read by the image processing apparatus which concerns on 1st Embodiment.

Explanation of symbols

101 CPU
102 ROM
103 RAM
104 External storage device 105 Display 106 Keyboard 107 Pointing device 108 Scanner 109 Network interface 110 Bus

Claims (14)

Reference setting means for setting a partial image area having a predetermined size as a reference partial image area at a predetermined position in the input document image;
Reference projection detection means for detecting a projection of a character line included in the reference partial image region;
First partial image area setting means for setting the first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area in the row leading direction;
The projection position of the character line detected from the newly set first partial image area and the projection of the character line detected from the partial image area adjacent to the line end direction of the first partial image area A first determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the first determination means determines that there is no continuity, a new second position is set at a position that is slid by the width of the partial image area from the position of the first partial image area set at that time in the row leading direction. 1 partial image region is set and the determination by the first determination unit is repeated, and the first determination unit determines that there is no continuity, and immediately before the first partial image region set. A line leading edge partial image area determining means for determining the set first partial image area as a partial image area at the line leading edge;
Second partial image area setting means for setting a second partial image area at a position slid by the width of the partial image area in the row end direction from the position of the reference partial image area;
Projection position of the character line detected from the newly set second partial image area, and projection of the character line detected from the partial image area adjacent to the second partial image area in the line leading direction A second determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the second determination means determines that there is no continuity, a new second position is obtained by sliding the position of the second partial image area set at that time from the position of the second partial image area by the width of the partial image area. 2 partial image areas are set and the determination by the second determining means is repeated, and the second partial image area is set immediately before the second partial image area determined when the second determining means determines that there is no continuity. A line end partial image area determining means for determining the set second partial image area as a line end partial image area;
Between the projection detected from the partial image area at the line leading end determined by the line leading end partial image area determining means and the projection detected from the partial image area at the line end determined by the line end partial image area determining means And determining means for determining an inclination of the document image based on the correlation between the partial image area and the interval between the partial image area at the front end of the line and the partial image area at the end of the line.   The determining means fixes one of the partial image region at the top of the row or the partial image region at the end of the row and vertically moves the other to obtain a correlation of projections detected from each partial image region, and The image processing apparatus according to claim 1, wherein the inclination of the document image is determined based on a positional relationship between the partial image areas when the maximum value of the document image becomes maximum and the interval. The reference setting means sets the reference partial image region of the predetermined size at a plurality of predetermined positions in the document image;
The first partial image area setting means, the first determining means, the row leading edge partial image area determining means, and the second partial image area with respect to the reference partial image areas set at each of the plurality of predetermined positions. By performing processing by the setting unit, the second determination unit, the line end partial image region determination unit, and the determination unit, the inclinations at the plurality of predetermined positions are determined, and the determined plurality of inclinations are determined. The image processing apparatus according to claim 1, wherein an inclination of the document image is determined based on the document image.   Of the plurality of reference partial image areas, for the reference partial image area determined by the reference projection detection means that no projection of a character line has been detected, the first partial image area setting means and the first determination means And the line end partial image area determining means, the second partial image area setting means, the second determining means, the line end partial image area determining means, and the determining means are excluded from processing. Item 4. The image processing apparatus according to Item 3.   The determining means is such that the line leading partial image area determined by the line leading partial image area determining means and the line terminating partial image area determined by the line end partial image area determining means are the same area. 5. The image processing apparatus according to claim 3, wherein, when determined, the partial image region determined to be the same is not a calculation target when determining the inclination of the document image. 6. Reference setting means for setting a partial image area having a predetermined size as a reference partial image area at a predetermined position in the input document image;
Reference projection detection means for detecting a projection of a character line included in the reference partial image region;
First partial image area setting means for setting the first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area in the row leading direction;
The projection position of the character line detected from the newly set first partial image area and the projection of the character line detected from the partial image area adjacent to the line end direction of the first partial image area A first determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the first determination means determines that there is no continuity, a new second position is set at a position that is slid by the width of the partial image area from the position of the first partial image area set at that time in the row leading direction. One partial image area is set and the determination by the first determination unit is repeated, and the first determination unit determines that there is no continuity, and is two before the first partial image area set. A line leading edge partial image area determining means for determining the set first partial image area as a partial image area at the line leading edge;
Second partial image area setting means for setting a second partial image area at a position slid by the width of the partial image area in the row end direction from the position of the reference partial image area;
Projection position of the character line detected from the newly set second partial image area, and projection of the character line detected from the partial image area adjacent to the second partial image area in the line leading direction A second determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the second determination means determines that there is no continuity, a new second position is obtained by sliding the position of the second partial image area set at that time from the position of the second partial image area by the width of the partial image area. 2 partial image areas are set, the determination by the second determination unit is repeated, and the second determination unit determines that there is no continuity, and is two before the second partial image area set. A line end partial image area determining means for determining the set second partial image area as a line end partial image area;
Between the projection detected from the partial image area at the line leading end determined by the line leading end partial image area determining means and the projection detected from the partial image area at the line end determined by the line end partial image area determining means And determining means for determining an inclination of the document image based on the correlation between the partial image area and the interval between the partial image area at the front end of the line and the partial image area at the end of the line. An image processing method in an image processing apparatus,
A reference setting step in which a reference setting unit of the image processing apparatus sets a partial image area having a predetermined size as a reference partial image area at a predetermined position in a document image input to the image processing apparatus;
A reference projection detecting step of the image processing apparatus for detecting a projection of a character line included in the reference partial image region; and
A first partial image area setting unit of the image processing apparatus sets a first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area in the row leading direction. An area setting process;
A portion adjacent to the position of projection of the character line detected from the newly set first partial image area by the first determination means of the image processing device and the line end direction of the first partial image area A first determination step of determining whether the projection of the character line has continuity by comparing the position of the projection of the character line detected from within the image region;
From the position of the first partial image area set at that time in the direction of the line leading edge, until the line leading edge partial image area determining means of the image processing device determines that there is no continuity in the first determining step A new first partial image area is set at a position slid by the width of the partial image area, the determination in the first determination step is repeated, and is set when it is determined that there is no continuity in the first determination step. A line leading edge partial image area determining step for determining a first partial image area set immediately before the first partial image area being set as a partial image area at the leading edge of the line;
A second partial image area in which the second partial image area setting means of the image processing apparatus sets the second partial image area at a position slid from the position of the reference partial image area by the width of the partial image area in the row end direction. An area setting process;
A portion adjacent to the position of projection of the character line detected from the newly set second partial image area by the second determination means of the image processing apparatus and the line front end direction of the second partial image area A second determination step of determining whether the projection of the character line has continuity by comparing the position of the projection of the character line detected from within the image region;
Until the line end partial image area determining means of the image processing apparatus determines that there is no continuity in the second determination step, the position of the second partial image area set at that time is moved in the line end direction. A new second partial image area is set at a position slid by the width of the partial image area, the determination by the second determination step is repeated, and is set when it is determined that there is no continuity in the second determination step A line end partial image area determining step of determining a second partial image area set immediately before the second partial image area being set as a partial image area at the line end;
Projection detected by the determining means of the image processing device from the partial image region at the line leading end determined in the line leading partial image region determining step and the line end partial image determined in the line end partial image region determining step A determination step of determining an inclination of the document image based on a correlation between projections detected from the region and an interval between the partial image region at the top of the line and the partial image region at the end of the line. An image processing method. The line leading edge partial image region determining step determines the partial image region in the row leading direction from the position of the first partial image region set at that time until it is determined that there is no continuity in the first determining step. A new first partial image region is set at a position slid by a width, and the determination by the first determination step is repeated, and the first setting is set when it is determined that there is no continuity in the first determination step. A first partial image area set two times before one partial image area is determined as a partial image area at the top of a line;
In the line end partial image area determination step, until it is determined in the second determination step that there is no continuity, the position of the partial image area in the line end direction from the position of the second partial image area set at that time is determined. A new second partial image region is set at a position slid by a width, and the determination by the second determination step is repeated, and the second set is set when it is determined that there is no continuity in the second determination step. 8. The image processing method according to claim 7, wherein the second partial image area set immediately before the second partial image area is determined as the partial image area at the end of the line. In the determining step, one of the partial image region at the top of the row or the partial image region at the end of the row is fixed and the other is vertically moved to obtain a correlation of projections detected from the respective partial image regions, and the correlation 9. The image processing method according to claim 7, wherein an inclination of the document image is determined based on a positional relationship between the partial image regions when the maximum value of the document image becomes maximum and the interval . In the reference setting step, the reference partial image region having the predetermined size is set at a plurality of predetermined positions in the document image.
The first partial image area setting means, the first determining means, the row leading edge partial image area determining means, and the second partial image area with respect to the reference partial image areas set at each of the plurality of predetermined positions. By performing processing by the setting unit, the second determination unit, the line end partial image region determination unit, and the determination unit, the inclinations at the plurality of predetermined positions are determined, and the determined plurality of inclinations are determined. The image processing method according to claim 7, wherein an inclination of the document image is determined based on the document image.   Among the plurality of reference partial image areas, for the reference partial image area determined by the reference projection detection means that the projection of the character line has not been detected, the first partial image area setting step and the first determination step And the row end partial image region determination step, the second partial image region setting step, the second determination step, the line end partial image region determination step, and the determination step. Item 15. The image processing method according to Item 10.   In the determining step, the partial image region at the line leading end determined in the line leading partial image region determining step and the partial image region at the line end determined in the line end partial image region determining step are the same region. 12. The image processing method according to claim 10, wherein if it is determined, the partial image region determined to be the same is not a calculation target when determining the inclination of the document image. Computer
Reference setting means for setting a partial image area having a predetermined size as a reference partial image area at a predetermined position in the input document image;
Reference projection detection means for detecting a projection of a character line included in the reference partial image region;
First partial image area setting means for setting the first partial image area at a position slid by the width of the partial image area from the position of the reference partial image area in the row leading direction;
The projection position of the character line detected from the newly set first partial image area and the projection of the character line detected from the partial image area adjacent to the line end direction of the first partial image area A first determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the first determination means determines that there is no continuity, a new second position is set at a position that is slid by the width of the partial image area from the position of the first partial image area set at that time in the row leading direction. 1 partial image region is set and the determination by the first determination unit is repeated, and the first determination unit determines that there is no continuity, and immediately before the first partial image region set. A line leading edge partial image area determining means for determining the set first partial image area as a partial image area at the line leading edge;
Second partial image area setting means for setting a second partial image area at a position slid by the width of the partial image area in the row end direction from the position of the reference partial image area;
Projection position of the character line detected from the newly set second partial image area, and projection of the character line detected from the partial image area adjacent to the second partial image area in the line leading direction A second determination means for determining whether or not the projection of the character line has continuity by comparing with the position of
Until the second determination means determines that there is no continuity, a new second position is obtained by sliding the position of the second partial image area set at that time from the position of the second partial image area by the width of the partial image area. 2 partial image areas are set and the determination by the second determining means is repeated, and the second partial image area is set immediately before the second partial image area determined when the second determining means determines that there is no continuity. A line end partial image area determining means for determining the set second partial image area as a line end partial image area;
Between the projection detected from the partial image area at the line leading end determined by the line leading end partial image area determining means and the projection detected from the partial image area at the line end determined by the line end partial image area determining means And a program for causing the document image to function as a determination unit that determines the inclination of the document image based on the correlation between the partial image area and the interval between the partial image area at the top of the line and the partial image area at the line end.   A computer-readable storage medium storing the program according to claim 13.

Images