JP2006107534A - Character recognizing method and character recognizing device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a character recognizing method and character recognizing method which can perform more accurate determination than that when a single characteristic amount is used in the configuration of determining whether to be a printed character or a handwritten character by combining a plurality of characteristic amounts that can not independently attain accurate determination. <P>SOLUTION: A characteristic extracting means 103 extracts a plurality of types of characteristic amounts to be used to determine printed characters and handwritten characters for each character group extracted by a character extracting means 102. When the value of the characteristic amounts is not determined or is meaningless, "indeterminate" is outputted as an extraction result for a value. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a character recognition method for recognizing a character cut out from an input image. Furthermore, the present invention relates to a character recognition device that determines whether a character cut out from an input image is a printed type or a handwritten character, and performs character recognition based on the determination result.

  Conventionally, as a technique related to character recognition processing for switching between a character recognition method and a character recognition dictionary according to the determination result of printed type and handwritten character, a method of performing determination based on a feature amount representing variation in detected character height (Patent Document) 1) A method for determining the entropy of the frequency of the detected character size as a feature amount (Patent Document 2). If the variance of the character spacing is almost equal to the experimental value, it is determined as a print type, otherwise it is rejected. A method for performing determination based on the number of characters (Patent Document 3), and a method for performing determination based on one or a plurality of combinations of feature amounts such as the directionality, thickness, and linearity of a detected character stroke (prior art 4). , One or more combinations of features representing the area of the character rectangle, width, height, ratio of height to width, distance between the center of the rectangle and the center of the line, and variation in the distance between the centers of the rectangle A method using (Patent Document 5), and the like.

  Among the above-described conventional techniques, the methods disclosed in Patent Documents 1, 2, and 5 use that the character size of the print type is generally substantially constant, but it is caused by noise adhering to the print type or blurring. Due to the change in the character size, there may be variations in the character size even in the printed type. Therefore, there are cases in which the printed type and the handwritten character cannot be clearly distinguished by the feature amount representing the variation in the character size. In addition, when there are a large number of characters that are different from those of other characters such as “1” and “−” in terms of width, height, area, etc., or when there are few characters In some cases, variations in the size and area of the printed type may become large, and therefore determination based on variations in size and area becomes difficult.

  In addition, the method of Patent Document 3 has a high probability that a character recognition method suitable for print type rejects a handwritten character, and a character recognition method suitable for handwritten character has a high probability of rejecting a print type. However, depending on the character recognition method, such a difference in reject probability may not be expected at all, and if unrecognizable characters are mixed due to noise or blur, character recognition suitable for the wrong character type In some cases, the number of rejected characters is reduced when the method is used for recognition.

The feature amount related to the directionality and linearity of the stroke used in Patent Document 4 is a case where a character having a large linear stroke, such as Kanji, is targeted for recognition, or the number of characters in the target character group is large. It is effective when there are many straight strokes, but it is difficult to determine when dealing with numbers with small linear components, lower case letters of alphabet, hiragana, etc. because there are few linear components.
JP 05-189604 A Japanese Patent Publication No. 06-32074 Japanese Patent No. 3045086 Japanese Patent Laid-Open No. 10-162102 JP-A-10-214308

  As described above, conventionally, there has been a problem that it is often difficult to make a determination based on a single feature due to character deterioration due to noise or blurring, a lack of the number of characters, an exception such as the size of a character to be determined.

  The present invention has been made in view of the above circumstances, and it is possible to perform highly reliable character recognition that can accurately determine whether a read target character cut out from an input image is a printed type or a handwritten character. An object is to provide a character recognition method and a character recognition device.

  The present invention performs a more accurate determination than a case where a single feature amount is used as a configuration for determining whether it is a printed type or a handwritten character by combining a plurality of feature amounts that cannot be accurately determined alone. The character recognition method and the character recognition apparatus are made to be able to do this.

  Further, the present invention determines whether the character to be read cut out from the input image is a print type or a handwritten character, and determines whether the character type cannot be determined, and the determination result is suitable for the print type. Even if it is difficult to determine the character type as a configuration for character recognition using either a character recognition means, a character recognition means suitable for handwritten characters, or a character recognition means applicable to both printed and handwritten characters, It is characterized in that it is possible to prevent a decrease in accuracy due to an error in character type determination.

  That is, the present invention includes a preprocessing step of extracting a recognition target region from an input image, a character extraction step of extracting a character group from the recognition target region cut out of the preprocessing step, and a character group extracted in the character extraction step. A feature extraction step for extracting one or a plurality of feature amounts used for determination of print type and handwritten character, and a character group extracted in the character extraction step using the feature amount extracted in the feature extraction step is a print type A character type determination step for determining whether the character type is a handwritten character, a printed type or an unknown character type, and if the determination result by the character type determination step is a handwritten character, the character extraction step When the determination result by the handwritten character recognition step for recognizing the extracted character and the character type determination step is a print type A print type recognition step for recognizing the character extracted in the character extraction step, and an unknown for recognizing the character extracted in the character extraction step when the determination result in the character type determination step is determined to be an unknown character type A character recognition method comprising a character type recognition step.

  Further, the present invention provides a preprocessing means for performing a noise removal and binarization process on an input image to cut out a recognition target area, a character extraction means for extracting a character group from the recognition target area cut out by the preprocessing means, Feature extraction means for extracting one or a plurality of feature quantities used for determination of print characters and handwritten characters from the character group extracted by the character extraction means; and the character extraction means using the feature quantities extracted by the feature extraction means Character type determination means for determining whether the character group extracted in step 1 is a print type, a handwritten character, a print type, a handwritten character, or an unknown unknown character type, and the determination result by the character type determination unit is handwritten When the character is a character, the handwriting character recognition unit that recognizes the character extracted by the character extraction unit using a dictionary according to the determination result, and the determination result by the character type determination unit is a print activity. A printed type recognizing means for recognizing the character extracted by the character extracting means using a dictionary according to the determination result, and a dictionary according to the determination result when the determination result by the character type determining means is an unknown character type. And a character recognition device comprising unknown character type recognition means for recognizing the character extracted by the character extraction means.

  Thus, when character type determination is difficult, character type determination is possible even when character type determination is difficult by applying character recognition means (recognition dictionary) that can be applied to both printed and handwritten characters. It is possible to prevent a decrease in accuracy due to an error.

  ADVANTAGE OF THE INVENTION According to this invention, the reliable character recognition which can determine correctly whether the reading object character cut out from the input image is a printing type character or a handwritten character is attained. That is, according to the present invention, it is possible to perform more accurate determination by using a plurality of feature amounts that cannot be accurately determined by themselves than when a single feature amount is used. In addition, by introducing a mechanism that allows the evaluation value to be incorporated into the calculation formula for the feature value whose value may be indeterminate, it is possible to incorporate more feature values and perform more accurate determination. Is possible. In addition, by applying a character recognition method that can be applied to both printed and handwritten characters when character type determination is difficult, even if character type determination is difficult, accuracy degradation due to character type determination errors can be prevented. Can do.

  In the present invention, it is possible to perform accurate determination by combining a plurality of feature quantities that cannot be accurately determined alone, and feature quantities that may show abnormal values or feature quantities that may not be extracted. Is also used for judgment.

  As shown in FIG. 1, the first embodiment of the present invention comprises preprocessing means 101, character extraction means 102, feature extraction means 103, character type determination means 104, handwritten character recognition means 105, print type recognition means 106, and the like. Has an element.

  The preprocessing means 101 performs noise removal, binarization, form removal, and the like on the input image to cut out a recognition target area. The character extraction unit 102 extracts a character group as a recognition target from the recognition target region cut out by the preprocessing unit 101. The feature extraction unit 103 extracts one or a plurality of feature amounts for determining a print type and a handwritten character from the character group extracted by the character extraction unit 102.

  The character type determination unit 104 calculates an evaluation value for determining the handwritten character and the print type as a function of the feature amount extracted by the feature extraction unit 103, and compares it with a predetermined threshold value to determine “print type”. ”Or“ handwritten character ”. If the result is“ printed type ”, the printed character recognition unit 106 recognizes the extracted character group. If it is“ handwritten character ”, the handwritten character recognition unit 105 recognizes it. The extracted character group is recognized.

  Further, as shown in FIG. 10, the second embodiment of the present invention has an unknown character type recognition means 207 in addition to the components of the first embodiment shown in FIG.

  The character type determination unit 204 calculates an evaluation value for determining the handwritten character and the print type as a function of the feature amount extracted by the feature extraction unit 203, and compares it with a predetermined threshold value to determine “print type”. ”Or“ handwritten character ”or“ character type whose print type or handwritten character is unknown ”. If the result is“ print type ”, the print type recognition means 206 If it is “handwritten character”, the handwritten character recognition unit 205 recognizes the extracted character group, and if it is “unknown character type”, the unknown character type recognition unit 207 recognizes the extracted character group.

Here, the evaluation value is calculated by the character type determination means 104 and 204 by the function f (g ₁ (u ₁ ),..., G _N (u _N )) of the function g _i (u _i ) of each feature quantity u _i. However, the feature quantity u _i whose value is indefinite can be used by using a constant whose value is indefinite by using a constant instead of g _i (u _i ).

  Each embodiment of the present invention will be described below with specific examples. Note that the processing function and processing procedure of the present invention can be configured by incorporating character recognition software into a general-purpose computer, so the following description will be made assuming such a configuration. However, according to the present invention, each means can be configured as an aggregate of dedicated hardware or a network system of computers for distributed processing. If the structure includes all of the above-described means, it is not limited to the configuration described here. However, any method may be used.

  First, a first embodiment of the present invention will be described with reference to FIGS.

  In FIG. 1, the preprocessing unit 101 extracts, binarizes, removes noise, removes a form, and the like from an input image (a document image read by a scanner) in the vicinity of a processing target column. Image processing is performed. Further, when the recognition target is a character on a form, a form such as a ruled line or a preprint is also removed.

  The character extraction unit 102 extracts an image and position information for each character of the character group to be recognized from the output image of the preprocessing unit 101.

  The feature extraction unit 103 extracts one or more types of feature amounts used for determination of print type and handwritten character for each character group extracted by the character extraction unit 102. Further, depending on the feature amount and the input, the value of the feature amount may not be obtained or meaningless. In such a case, “undefined” is set as the extraction result.

As the feature quantity to be extracted, for example, as described below, a feature quantity u ₁ representing “deviation from the arrangement of the end of the character rectangle”, a feature quantity u ₂ representing “mismatch of the shape of the same character”, and “character recognition” There are three types of feature quantity u ₃ representing “difference in the number of rejected characters for each method”.

Here, it is assumed that these three types of feature quantities u ₁ , u ₂ , u ₃ are applied. A method for extracting these three types of feature quantities u ₁ , u ₂ , and u ₃ will be described.

First, a method of extracting the feature amount u ₁ representing the deviation from the end of the character rectangle will be described with reference to FIGS.

The feature quantity u ₁ representing the deviation from the end of the character rectangle is represented by N for the number of characters in the character group, y _t n for the upper end of the circumscribed rectangle of the nth character, and the circumscribed rectangle of the nth character. If the lower end Y coordinate is set to y _b n, y _t and y _b obtained by the following equations:

を計算することによって求める。ただし、ｍｅｄｉａｎ（ｘ_ｎ）は全ｎについてのｘ_ｎの中央値とする。 α that minimizes y _b −y _t is obtained by the gradient method, and the calculation formula

Is obtained by calculating However, median (x _n ) is the median value of x _n for all n.

The sequence of the upper and lower end of the character is determined by y _t , y _b , α obtained by the above method.

と近似されるので（図４参照）、
｜ｙ_ｔｎ−（ｎα＋ｙ_ｔ）｜，｜ｙ_ｂｎ−（ｎα＋ｙ_ｂ）｜
はｎ番目の文字の上端、下端の文字並びからのずれを表し、ｕ_１は文字矩形の端の並びからのずれの評価尺度として機能する（図５参照）。

(See FIG. 4),
| Y _tn − (nα + y _t ) |, | y _bn − (nα + y _b ) |
The upper end of the n-th character, represents the deviation from the character sequence of the lower end, u ₁ functions as an evaluation measure of the deviation from the sequence of character rectangle of the end (see FIG. 5).

The above (Equation 3) is always 0 when N = 1 and is irrelevant to the difference between the printed type and the handwritten character. Therefore, when N = 1, u ₁ is “undefined”.

Next, the feature quantity u ₂ representing the mismatch of the shape of the same character will be described with reference to FIGS.

によって求める。 The feature quantity u ₂ representing the mismatch of the shape of the same character is represented by C as the number of character types, c as the character type number, c _{n as} the character type number of the recognition result of the n th character, and the n th character. the number foreground pixels of the character image when a _n, the upper left corner of the n-th character and m-th character image overlaid combined as shown in FIG. 6, both of the image which the pixel a black pixel If the number is vm _{, n} ,

Ask for.

Here, the upper left corner is aligned when two character images are overlapped. However, as shown in FIG. 7, the center of gravity and the center of the circumscribed rectangle of the two character images are overlapped, as shown in FIG. Alternatively, the method may be a method in which the centers of the upper sides of the circumscribed rectangle (FIG. 5) are overlapped or a method of overlapping the centers of the lower sides as shown in FIG. At this time, if the same character is not included in the character group, since the above (Formula 6) cannot be calculated, u _{2 is set} to “undefined”.

Next, the feature quantity u ₃ representing the difference in the number of rejected characters for each character recognition method will be described. The feature quantity u ₃ representing the difference in the number of rejected characters for each character recognition method is a part of the character group obtained by two types of character recognition methods: a character recognition method suitable for printed characters and a character recognition method suitable for handwritten characters. or, after the recognition of all characters is obtained from the reject number r _h of the character recognition method suitable for the rejected characters r _p handwritten characters in the character recognition method suitable for printing print by the following equation.

The result of the character recognition performed to obtain the reject character numbers r _p and r _h may be discarded as it is, but is stored without discarding and is stored as cache data by the handwritten character recognition means and the print type recognition means 106. May be used.

  In the above, three types of feature quantities are shown as examples of the feature quantities extracted by the feature extraction unit 103. However, the feature quantities extracted by the feature extraction unit 103 represent the difference between printed characters and handwritten characters. Any amount other than those described above may be used, and the number of types is arbitrary.

  The character type determination unit 104 obtains an evaluation value s indicating whether the character group extracted by the character extraction unit 102 is a print type or a handwritten character based on the feature extracted by the feature extraction unit 103. When the evaluation value s is larger than the predetermined threshold value θ, it is determined that the printed character is printed, and when the evaluation value s is equal to or smaller than the threshold value θ, the character is a handwritten character.

と求められる。 When the number of feature quantities is d and the i-th feature quantity is u _i , the evaluation value s is expressed by the function f and the function group g _i.

Is required.

を用いることができる。ただし、ｃ_ｉは予め定められた定数である。この際の定数ｃ_ｉを選択的に用いる関数群ｇ_ｉの概念図を図２に示している。 g _i (u _i )

Can be used. However, c _i is a predetermined constant. A conceptual diagram of a function group g _i using constants c _i in this case selectively is shown in FIG.

を用いることができる。ただし、ｗ_ｉは予め定められた定数である。 As a function f, linear combination of g _i (u _i )

Can be used. However, w _i is a predetermined constant.

をはじめ、ｇ_ｉ（ｕ_ｉ）の関数ならば、いかなる関数を用いてもよい。 In the above example, g _i (u _i ) linear combination is used as f, but f is a quadratic form of g _i (u _i ).

As long as it is a function of g _i (u _i ), any function may be used.

であり、Ｗは予め定められた対称行列である。 However,

And W is a predetermined symmetric matrix.

を用いることもできる。この際の定数ｃ_ｉを選択的に用いる関数群ｇ_ｉの概念図を図３に示している。 Moreover, as g _i (u _i ),

Can also be used. And Figure 3 shows the conceptual diagram of the function group g _i using constants c _i in this case selectively.

をはじめ、ｕ_ｉの関数ならば、いかなる関数を用いてもよい。ただし、β_ｉ，γ_ｉは予め定められた定数である。 The h _i,

Any function may be used as long as it is a function of u _i . However, β _i and γ _i are predetermined constants.

  When the determination result by the character type determination unit 104 is a handwritten character, the character extracted by the character extraction unit 102 is recognized by the handwritten character recognition unit 105, and the determination result by the character type determination unit 104 is a print type Is recognized by the print type recognition means 106, and the recognition result is output. At this time, the handwritten character recognizing means 105 and the print type recognizing means 106 have different dictionary contents and recognition algorithms each including a learning function.

  Next, a second embodiment of the present invention will be described. In the second embodiment, as shown in FIG. 10, preprocessing means 201, character extraction means 202, feature extraction means 203, character type determination means 204, handwritten character recognition means 205, print type recognition means 206, unknown character type recognition. It has components such as means 207. Here, the preprocessing unit 201, the character extraction unit 202, the feature extraction unit 203, the handwritten character recognition unit 205, and the print type recognition unit 206 have the same functional configuration as that of the first embodiment shown in FIG. Now, a detailed description of the operation is omitted.

The character type determination unit 204 uses the feature amount extracted by the feature extraction unit 203 to determine whether the character group extracted by the character extraction unit 202 is a print type, a handwritten character, a print type, or a handwritten character. Judge whether the character type is unknown. In other words, the character type determination unit 204 uses the feature extracted by the feature extraction unit 203 to obtain an evaluation value s indicating whether the character group extracted by the character extraction unit 202 is a printed type or a handwritten character. determined, it determines the evaluation value s is a predetermined threshold theta _p larger than the printing print, when the evaluation value s is the threshold value theta _h is smaller than a predetermined and handwriting. Further, it is determined that when the evaluation value s is [s <= θ _p cutlet s> = θ _h] is whether handwritten character is printed print is unknown character type.

  When the determination result by the character type determination unit 204 is a handwritten character, the character extracted by the character extraction unit 202 is recognized by the handwritten character recognition unit 205, and when it is a print type, the character is recognized by the print type recognition unit 206. If it is determined that the character type is unknown whether it is a printed type or a handwritten character, it is recognized by the unknown character type recognizing means 207 and the recognition result is output. Also in the second embodiment, the handwritten character recognizing means 205, the print type recognizing means 206, and the unknown character type recognizing means 207 have different dictionary contents and recognition algorithms each including a learning function.

The block diagram which shows the structure of the principal part in 1st Embodiment of this invention. The conceptual diagram of (Formula 9) in the said embodiment. The conceptual diagram of (Formula 13) in the said embodiment. Diagram for explaining a method of extracting in feature quantity u ₁ in the above embodiment. Diagram for explaining a method of extracting in feature quantity u ₁ in the above embodiment. Diagram for explaining a method of extracting in feature quantity u ₂ in the above embodiment. Diagram for explaining a method of extracting in feature quantity u ₂ in the above embodiment. Diagram for explaining a method of extracting in feature quantity u ₂ in the above embodiment. Diagram for explaining a method of extracting in feature quantity u ₂ in the above embodiment. The block diagram which shows the structure of the principal part in 2nd Embodiment of this invention.

Explanation of symbols

  101, 201 ... Pre-processing means, 102, 202 ... Character extraction means, 103, 203 ... Feature extraction means, 104, 204 ... Character type determination means, 105, 205 ... Handwritten character recognition means, 106, 206 ... Print type recognition means, 207 ... Unknown character type recognition means.

Claims (6)

A preprocessing step of extracting a recognition target area from an input image;
A character extraction step of extracting a character group from the recognition target region cut out in the preprocessing step;
A feature extraction step for extracting one or a plurality of feature amounts to be used for determination of print type and handwritten character from the character group extracted in the character extraction step;
Using the feature amount extracted in the feature extraction step, it is determined whether the character group extracted in the character extraction step is a print type, a handwritten character, a print type or a character type whose handwritten character is unknown. A character type determination step for performing
A handwritten character recognition step for recognizing the character extracted in the character extraction step when the determination result of the character type determination step is a handwritten character;
A print type recognition step for recognizing the character extracted in the character extraction step when the determination result in the character type determination step is a print type;
A character recognition method comprising: an unknown character type recognition step for recognizing a character extracted in the character extraction step when it is determined that the determination result in the character type determination step is an unknown character type.   2. The character according to claim 1, wherein the feature amount extracted in the feature extraction step includes a feature amount extracted based on an amount representing a deviation from an end of the character rectangle of the character group extracted in the character extraction step. Recognition method.   The character recognition method according to claim 1, wherein the feature amount extracted in the feature extraction step includes a feature amount extracted using an amount representing a mismatch of character shapes of the same character for the character group extracted in the character extraction step. . Pre-processing means for performing noise removal and binarization processing on the input image to cut out a recognition target area;
Character extraction means for extracting a character group from the recognition target area cut out by the preprocessing means;
Feature extraction means for extracting one or a plurality of feature quantities used for determination of print type and handwritten character from the character group extracted by the character extraction means;
Whether the character group extracted by the character extraction unit using the feature amount extracted by the feature extraction unit is a print type, a handwritten character, a print type, a handwritten character or an unknown type of unknown character Character type determining means for determining;
When the determination result by the character type determination unit is a handwritten character, the handwritten character recognition unit recognizes the character extracted by the character extraction unit using a dictionary according to the determination result;
When the determination result by the character type determination unit is a print type, a print type recognition unit that recognizes the character extracted by the character extraction unit using a dictionary according to the determination result;
Characters comprising: an unknown character type recognition unit that recognizes a character extracted by the character extraction unit using a dictionary according to the determination result when the determination result by the character type determination unit is an unknown character type Recognition device.   5. The character according to claim 4, wherein the feature amount extracted by the feature extraction unit includes a feature amount extracted based on an amount representing a deviation of the character group extracted by the character extraction unit from the end of the character rectangle. Recognition device.   6. The character recognition device according to claim 4, wherein the feature amount extracted by the feature extraction means includes a feature amount extracted by using an amount representing a mismatch of character shapes of the same character in the character group extracted in the character extraction step. .

Images