JPH0799534B2 - Character figure recognition method - Google Patents

Description

The present invention relates to a character / figure recognition system for recognizing character / figure on a medium.

(Prior Art) Conventionally, a character / graphics recognition apparatus has often adopted a method of extracting strokes from a character / graphics pattern and recognizing them by using the positions, lengths, mutual relationships between the strokes, and the like of the extracted strokes. There is. The method is as follows: (1) The curvature is calculated for the contour point series detected by tracing the contour of the character figure, the contour series is divided with the point having a large curvature value as the division point, and the divided series is combined. Strokes are extracted by combining them, or (2) the character / graphic pattern is thinned to form a skeleton, the connectivity of the skeleton pattern and the skeleton pattern are traced, and a sudden angle change point is detected to make a stroke. And extract (1) and (2) above
The strokes thus extracted are identified by extracting geometrical features and the like.

(Problems to be Solved by the Invention) However, the conventional character / graphics recognition method has the following problems.

In the method (1), if the character / graphic pattern becomes large and the character / graphic pattern becomes complicated, the processing amount increases and the processing speed decreases. In the method (2), it is necessary to make the character / graphic pattern thin, and there are problems such as pattern distortion and beard due to the thinning, and the subsequent processing is complicated.

SUMMARY OF THE INVENTION It is an object of the present invention to solve the above-mentioned problems and provide a character / graphics recognition method capable of recognizing a character / graphics at high speed with simple processing.

(Means for Solving Problems) In order to solve the above problems, the present invention reads a character graphic on a medium, quantizes it, and binarizes it. For example, a character line part is a black bit and a background part is white. In a character / figure recognition system for recognizing a character / figure based on the pattern, comprising: a storage unit for storing a pattern obtained as a bit; (a) a first pattern for scanning the pattern to detect a circumscribing frame of the character / figure; (B) scanning the pattern on two predetermined axes (for example, a horizontal direction and a vertical direction in a two-dimensional coordinate).
Hereinafter, these are referred to as X axis and Y axis. ) Creating means for creating a projected black bit number distribution in each axial direction, (c) Determining the barycentric coordinates of each black bit number distribution within the range of the circumscribing frame in the two axial directions, and the determined barycentric coordinates Second detection means for detecting the barycentric coordinate series in each axial direction by repeating the process of determining the barycentric coordinates of each black bit number distribution for each of the divided ranges obtained by dividing the range in the circumscribing frame, (d) the barycenter Determination means for determining a division coordinate series in each axis direction based on the coordinate series,
(E) Calculation means for calculating a divided area length series in each axial direction in which the length of each area of the circumscribed frame divided by the divided coordinate series is normalized by the length of the corresponding circumscribed frame in the axial direction, and (F) A recognition means is provided for recognizing the character pattern of the pattern by collating the divided area length series with the previously calculated standard area divided area length series.

(Operation) According to the present invention, since the character recognition method is configured as described above, the technical means operates as follows. By scanning the pattern stored in the storage means, the circumscribing frame (character frame) of the character graphic is detected by the first detecting means, and the creating means detects the circumscribing frame in each axial direction (for example, X-axis, Y-axis direction). A black bit number distribution is created. Based on the circumscribing frame and black bit number distribution thus obtained, the barycentric coordinate series in each axial direction is detected by the second detecting means. Based on the detected barycentric coordinate series, the determining means determines the divided coordinate series in each axial direction. For example, the number of divisions in each axial direction is determined according to the complexity of the character graphic, and the divisional coordinate series in each axial direction that substantially evenly corresponds to the barycentric coordinate series is determined. A series of divided area lengths in each axial direction (divided area length series) obtained by normalizing the length of each area of the circumscribed frame divided by the determined divided coordinate series by the length of the corresponding circumscribed frame in the axial direction It is calculated by the calculation means. The normalized divided area length series and the standard area divided area length series calculated in advance are collated by the recognizing means, and the category name of the corresponding standard pattern is output as a character graphic name. As described above, according to the present invention, a pattern of a character graphic is scanned to calculate a divided area length series as characteristic information of the character graphic, and the character graphic is recognized by this characteristic information. Is possible.

(Embodiment) An embodiment of the present invention will be described below with reference to FIGS. 1 to 4.

FIG. 1 is a functional block diagram showing an embodiment of a character / graphics recognition system of the present invention.

Reference numeral 1 is an optical input from a medium such as a form in which characters, figures, symbols and the like (hereinafter referred to as characters) are described. The optical input 1 is input to the photoelectric conversion unit 2. The photoelectric conversion unit 2 decomposes one character planned area into 128 × 128 pixels and converts each pixel into a binary digital signal (hereinafter referred to as an input character pattern), and has an average size. One character is represented by an input character pattern of about 60 x 60 bits. The pattern register 3 stores the input character pattern in a format capable of reproducing the X and Y coordinates of each pixel in the character planned area, and has a capacity of 128 × 128 bits corresponding to the character planned area.

The character frame detection unit 4, for example, defines a circumscribing frame (character frame) of a character as the left end coordinate X _l , the right end coordinate X _r ,
The upper limit coordinate Y _t and the lower limit coordinate Y _b are used for detection.

The character projection creating unit 5 projects the input character pattern of the pattern register 3 on a predetermined axis, for example, the X axis and the Y axis (horizontal direction and vertical direction in the two-dimensional coordinates of the husband and wife pattern register 3) to distribute the number of black bits. , The black bit number distribution SX
Create (x) and SY (y).

Here, x and y are two-dimensional coordinates 0 to 127 in the pattern register 3, Y _t and Y _b are upper and lower coordinates in the Y axis direction of the character frame, and X _l and X _r are X axis directions. Is the left and right coordinates of P, and P (x, y) means black bit or white bit. In case of black bit (significant color), in case of P (x, y) = 1, white bit (background color) Take P (x, y) = 0.

FIG. 2 (a) shows an example of the input character pattern in the case of the Chinese characters "ten" and "husband", and FIG. 2 (b), (c).
The black bit number distribution SX for each pattern in Fig. 2 (a)
(X) and SY (y) are shown.

The center-of-gravity detection unit 6 determines the entire range X _{l to} X _r , in the X and Y axis directions of the character frame.
Y _t ~ Y _b and its range X _l ~ in the barycentric coordinates detected in the previous process
Targeting each range obtained by dividing Y _r , Y _{t to} Y _b , the barycentric coordinate series X (M _p ), Y (M _q of the black bit number distributions SX (x) and SY (y) of the input character pattern ) Is obtained by dividing the sum of the first moments in each range by the black bit sum in that range. However, M _p and M _q are barycentric coordinate numbers given in order of magnitude of coordinate values, and M _p = 1
~ MX (MX is the odd number of the center of gravity in the X-axis direction) M _q = 1
To MY (MY is the number of centers of gravity in the Y-axis direction). As the number MX of the barycentric coordinates in the X-axis direction, it is desirable to use a relatively large number (about the number of divisions) of about 15, but for the sake of simplification of explanation, 7 barycentric coordinates X (M _The case of detecting _p ) will be described.

First, for the range X _{l to} X _r in the X-axis direction of the character frame, the black bit number distribution SX of the input character pattern is calculated as shown in the following equation.
The centroid coordinate X (4) of the center centroid coordinate number M ₄ is obtained by dividing the first moment sum of (x) by the black bit sum in that range. Then, the barycentric coordinates X divided range severally in _{(4), X l ~X (} 4), X (X 4) a to X _r as a target two barycentric coordinates X (2), X (6) Ask for.

Next, the barycentric coordinates X (2), X detected so far
Range X _{l to} X (2), X (2) divided by (4), X (6)
~X (4), X (4 ) ~X (6), X (6) 4 pieces of the center of gravity to X _r as object coordinates X (1), X (3 ), X (5), X (7) Ask for.

If the number of barycentric coordinates MY, which also detects the barycentric coordinate Y (M _q ) in the Y-axis direction, is set to 7, first, the black bit distribution SY (of the input character pattern is targeted for the range Y _{t to} Y _b of the character frame). detecting the center of gravity coordinates Y of y) (4), then the range Y _t for 2 min character frame center of gravity coordinates ~Y (4), Y (4 ) ~Y b black respectively as the target bit distribution SY (y) Center of gravity coordinates Y (2), Y (4)
Is detected, and the barycentric coordinate Y detected so far
(2), Y (4) , Y (6) range and each divided character frame in the Y-axis direction by _{Y t ~Y (2), Y} (2) ~Y (4), Y (4) ~
Black bit distribution SY for Y (6), Y (6) to Y _b
By detecting the barycentric coordinates of (y), a total of seven barycentric coordinates Y (1) to Y (7) are detected.

In the case of the input character patterns of the Chinese characters “ten” and “husband” (FIG. 2 (a)), the black bit number distributions (SX (x), SY (y) in FIGS. 2 (b) and (c) are shown. ) Center of gravity X
(1) to X (7) and Y (1) to Y (7) are shown.

The character frame division point determination unit 7 sets the number of divisions in the X and Y axis directions to NX and NY, and sets the divided coordinate series in each of the X and Y axis directions received from the center of gravity detection unit 6 to DX (k _i ), DY (k _j ), the barycentric coordinate series X (M _p ), Y (M _q ) in each direction of the X and Y axes are used as the divisional coordinate candidates, and the barycentric coordinate numbers M _p , M _q are set to the divisional coordinate numbers k _i , k _j . The divided coordinate series DX (k _i ) and DY (k _j ) are determined by being associated with each other evenly.

The division format of the division unit area in this embodiment can take four formats as NX = 4,5,6,8 as the division number in the X-axis direction, and similarly, the division number NY in the Y-axis direction is NY.
= 4,5,6,8, and the divided coordinate numbers in the X-axis direction are k _i (k _i = 1 to NX-1, NX = 4,5,6,8) and Y The division coordinate numbers in the axial direction are k _j (k _j = 1 to NY-1, NY = 4,5,
6, 8), the divided coordinate series DX (k _i ) and DY (k _j ) for dividing the character frame into the regions NX and NY, respectively, are determined. Center of gravity coordinate number in each direction of X, Y axis M _p , M _q and divided coordinate number in X, Y axis direction
Divided coordinate sequence DX (k _i ), DY with almost equal correspondence between k _i and k _j
The table used to determine (k _j ) is shown in Table 1.

Referring to this table, X, division number NX of Y-axis in each direction, the centroid coordinate number M _p from the table in response to NY, reads the M _q, centroid corresponding to the barycentric coordinate number M _p, M _q Coordinate X
(M _p ) and Y (M _q ) are determined as the division coordinates DX (k _i ) and DY (k _j ).

The table in Table 1 shows a case where the number of barycentric coordinates MX and MY detected by the barycentric detecting unit 6 is 7, but in a general case, the barycentric coordinates of the number of divisions in each of the X and Y directions are included. It is possible to make it by making correspondence so as to include one more barycentric coordinate in order from the regions at both ends when extra barycentric coordinates remain.

In Fig. 3, NX = NY = as the number of divisions NX, NY in each direction of the X and Y axes.
When a division number of 5 is specified, the division coordinate series
The correspondence between DX (k _i ), DY (k _j ) and the barycentric coordinate series X (M _p ), Y (M _q ) is shown.

The number of divisions NX, NY is N depending on the complexity of the input characters.
It decides X, NY, or changes the number of divisions NX, NY when it is rejected, and makes character recognition again.

As described above, in the character frame division point determination unit 7, the division format of the division unit area is NX = 4,5,6, as the number of divisions in the X-axis direction.
8 formats, the number of divisions in the Y-axis direction is NY = 4,5,
It can take four formats: 6,8. In the present embodiment, the number of divisions will be described below with NX = NY = 4 for simplification of description. In this case, the barycentric coordinate X in the X-axis direction
Division coordinates DX (1), D corresponding to (M ₂ ), X (M ₄ ), X (M ₆ ).
About X (2), DX (3), Y axis direction, barycentric coordinate Y
Division coordinates DY (1), D corresponding to (M ₂ ), Y (M ₄ ), Y (M ₆ ).
Determine Y (2) and DY (3).

The normalized divided area length calculation unit 8 calculates the character frame coordinates X _l , X _r in the X direction detected by the character frame detection unit 4 and the character frame coordinate Y in the Y axis direction.
_t , Y _b , and the division coordinates DX (1), DX (2), DX (3) in the X-axis direction and the division coordinates DY (1), DY in the Y-axis direction determined by the character frame division point determination unit 7. (2), receiving DY (3), the length of each area divided by each divided coordinate on each axis is normalized by the length between the above-mentioned both ends coordinates Calculate by formula.

X-axis normalized division coordinate series; Length between both X-axis coordinates; LX = X _r −X _l +1 (7) Y-axis normalized division coordinate series; Length between Y-axis coordinates; LY = Y _b −Y _t +1 (9) However, DX (0) = X _l , DX (4) = X _r , DY (0) = Y _t ,
DY (4) = Y _b .

Division coordinates DX (0) to DX (4), DY (0) to DY (4) in the input character patterns of the Chinese characters “ten” and “husband”, normalized division area length BEX (1) to X axis direction FIG. 2A shows BEX (4) and the normalized divided area lengths BEY (1) to BEY (4) in the Y-axis direction together with the respective input character patterns.

Normalized divided area sequence f _i = {BEX as feature information of the input character pattern obtained by the normalized divided area length calculation unit 8
(I) and BEY (I) | I = 1 to 4} are given to the identification unit 9.

In the dictionary memory 10, the normalized divided area series g _i as the characteristic information for the standard pattern calculated in the same manner as for the input character pattern is registered in advance.

The identification unit 9 measures the degree of similarity between the input character pattern and the characteristic information of the standard pattern, recognizes the character code of the most similar standard pattern as the input character pattern name, and outputs the character code to the character code output terminal 11. In this embodiment, the following minimum value of the Euclidean distance (D) between the normalized divided area length series g _i of the standard pattern in the dictionary memory 10 and the normalized divided area length series f _i of the input character pattern is given. Let the standard pattern be the most similar standard pattern.

Further, in the above-described embodiment, the barycentric coordinates and the divided coordinates are associated with each other by using the table, but they can be associated with each other by executing the flow chart arithmetic processing of a predetermined procedure. . The flow chart in this case is shown in FIG. The results of the division in FIG. 4 are all rounded down to the right of the decimal point.

The In Figure 4, obtains a divided ivy number M _alpha gravity number MX by dividing the number NX at step S1, obtaining a quotient R ₂ obtained by dividing the remainder R ₁ and its R ₁ of MX / NX 2 at step S2, S3 . Further, the number of divisions calculated median k _alpha in step S4, the excisional division number k _i and the center of gravity number M _p to 0 in step S5, S6. Also, steps S7, S8, S9
Every time the division number k _i is incremented by 1, the set quotient R ₂ is decremented by 1 and the center of gravity number M _p is incremented by M _α . It is checked in step S10 that the quotient R ₂ is not negative. If the quotient R ₂ is not negative, the number of the center of gravity number M _r is incremented by 1 in step S11, and the center of gravity number M _{p is associated} with the division number k _i in step S12. , The division coordinate DX (k _i ) is determined. If the quotient R ₂ is negative,
In step S13, it is determined whether or not the current division number k _i is larger than the median k _α. If it is larger, the center of gravity number M _r is incremented by 1, and if it is smaller, the center of gravity number set in step S9 is set.
M _{r is associated} with the division number k _i in step S12, the division coordinate DX (k _i ) is determined, and it is detected in step S14 that the division number k _i matches (NX-1), and the process ends.

The effectiveness of the divided area length series, which is the characteristic information of the character / graphics recognition method of the present embodiment described above, will be described below.

For example, "heaven" and "husband" shown in Fig. 2 (a), respectively.
In the input character pattern of BEY, whether there is a protrusion at the top of the central vertical stroke, which is the difference between both patterns, is BEY.
In (1), a noticeable difference appears, and it is clear that the normalized divided area length series effectively reflects the difference in the character / graphic pattern.

As described above, according to the present embodiment, since the normalized divided area length series obtained by the scanning of the input character pattern and the predetermined calculation is used as the characteristic information, it is possible to realize the high-speed character and graphic recognition with a simple process. .

(Effects of the Invention) As described in detail above, according to the present invention, an input character / graphic pattern is scanned without performing complicated pattern processing such as contour tracking and thinning in the feature information extraction of the conventional recognition method. From the black bit number distribution on the predetermined axis obtained by simply performing the above, since the normalized divided region length sequence, which is the characteristic information, is obtained by using the center of gravity, it is possible to realize simple processing and high-speed character recognition.

[Brief description of drawings]

FIG. 1 is a functional block diagram showing an embodiment of a character / figure recognition system according to the present invention, and FIG. 2 shows the relationship between an input character pattern example and a barycentric coordinate series, divided coordinate series, and normalized divided area length series. FIGS. 3A and 3B are diagrams showing the correspondence relationship between the barycentric coordinate series and the divided coordinate series, and FIG. 4 is a flow chart showing another method of determining the divided coordinate series. 1 ... Optical input, 2 ... Photoelectric conversion unit, 3 ... Pattern register, 4 ... Character frame detection unit, 5 ... Character projection creation unit, 6
...... Center of gravity detection unit, 7 ... Character frame division point determination unit, 8 ... Normalized division area length calculation unit, 9 ... Identification unit, 10 ... Dictionary memory, 11 ... Output terminal

Front page continued (72) Inventor Yoshiyuki Yamashita 1-7-12 Toranomon, Minato-ku, Tokyo Oki Electric Industry Co., Ltd. (56) Reference JP 58-123171 (JP, A) JP 61- 150086 (JP, A)

Claims (1)

[Claims] 1. A character / figure recognition system for recognizing a character / figure based on the pattern, comprising a storage unit for storing a pattern obtained by reading and quantizing the character / figure on a medium. First detecting means for scanning to detect a circumscribing frame of a character figure; (b) creating means for scanning the pattern to create black bit number distribution in each axial direction projected onto two predetermined axes; ) The barycentric coordinates of each black bit number distribution are determined within the range of the circumscribing frame in the two axial directions, and the black bit number distribution is obtained for each of the divided ranges obtained by dividing the range within the circumscribing frame with each determined barycentric coordinate Second detecting means for detecting the barycentric coordinate series in each axial direction by repeating the process of determining the barycentric coordinates of (d) determining means for determining the divided coordinate series in each axial direction based on the barycentric coordinate series, e) In the divided coordinate series Calculating means for calculating a divided area length series in each axial direction in which the length of each area of the circumscribed frame to be divided is normalized by the length of the corresponding circumscribed frame in the axial direction, (f) the divided area series and the divided area series in advance A character / figure recognition method, comprising: a recognition unit that recognizes a character / figure of the pattern by collating the calculated divided area length series of the standard pattern.