JPH0773273A - Pattern cutting and recognition method and its system - Google Patents

Abstract

(57) [Abstract] [Purpose] A combination of a plurality of partial patterns when it is determined that the input 1 unit video pattern is a part of the pattern representing one category and is a character written under natural writing conditions. To provide a pattern cutting and recognizing method and system capable of recognizing the combined character as one character. [Structure] A pattern obtained by inputting a form that does not have a character frame in units of one character and performing a process on a region corresponding to one character line of a two-dimensional video pattern converted into an electrical signal by a cutting unit. Is not a complete (synonymous with “normal”) pattern but a part of one character (partial pattern), combine those partial patterns and output as information of one character. If multiple judgments are possible as a result, multiple hypotheses are created and sent to the recognition processing unit, and the recognition processing unit makes a comprehensive judgment on those hypotheses to resolve the ambiguity. A pattern cutting and recognizing method characterized by:

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a pattern cutting and recognizing method in an optical character reader (hereinafter referred to as "OCR") and its system, and particularly to cutting a pattern on a form written under natural writing conditions, BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a pattern cutting and recognition method suitable for recognizing it and a system thereof.

[0002]

2. Description of the Related Art Conventionally, the characters read by the OCR are:
As shown in FIG. 1A, it was necessary to write correctly in the character frame 11 set for each character. In that case, some protrusion from the frame is allowed, but as shown in Fig. 1 (b), the extent is about 1.0 to 1.5 mm in the vertical direction, and the adjacent frame in the horizontal direction. There was not much. By the way, in order to further spread OCR, as described above,
As shown in Fig. 2 (a) or (b), the characters and numbers are not written in the OCR unique character frame, and the character frame is not so particularized, and it is natural to write as usual. It is necessary to enable writing conditions. As is clear from a comparison between FIG. 1 and FIG. 2, the conventional character frame has a large size and the inter-character frame gap 5 is 0.5 to 1.0 mm. The frame is 1 in FIG.
As shown in Nos. 2 and 13, as the dimensions decrease,
The gaps 6 and 7 between the character frames are 0 mm.

[0003]

As a result of this, the amount of characters protruding from the frames 12 and 13 becomes large, and
There arises a problem that the characters overlap each other in the vertical direction or the characters easily contact each other. Further, when the character pattern components are separated, for example, in the case of the number "5" in FIG. 2 (a) or (b), most of the components may be in the adjacent frame, and the character reading Moreover, it causes difficult problems. In such a case, the conventional technology has not been able to correctly cut out characters or read them correctly. The present invention has been made in view of the above circumstances, and an object of the present invention is to solve the above-described problems in the related art, to largely protrude from a character frame, or to be in contact with an adjacent character. About the characters written under different writing conditions, especially the entered 1
A pattern cutout and recognition method capable of combining a plurality of partial patterns into one character when the unit image pattern is determined to be a part of a pattern representing one category and performing character recognition on the combined character. To provide that system.

[0004]

The above objects of the present invention are as follows:
Input a form that does not have a character frame for each character, cut out one or more patterns including characters from the two-dimensional image pattern converted into an electrical signal by the cutout unit, send the pattern to the recognition unit, and recognize the pattern. A pattern cutout and recognition method configured to recognize the pattern by comparing each pattern with each pattern in a pattern dictionary, wherein the cutout unit creates an area corresponding to one character line of the two-dimensional video pattern. After processing as a target, a region of consecutive black pixels is extracted as a pattern component, the pattern components are ordered in the horizontal direction, and then a character component list having the pattern component as an element is created. A component attribute list is created by calculating the attributes of each part of the component list, and one unit or a plurality of patterns forming each character by referring to the component attribute list. A hypothesis of a combination of components is established, the hypothesis of the combination is stored as a character list, and the recognition unit inputs the character list, constructs a combination of pattern components to be recognized from the character list, and forms the pattern dictionary. The pattern cutout and recognition method and its system are characterized in that the recognition process is performed by matching each pattern in the above, and the final judgment unit makes a comprehensive judgment of the recognition result for one character line.

[0005]

In the pattern cutout and recognition method according to the present invention, in the pattern cutout processing unit of the character reading device, the pattern (unit video pattern) cut out by the process for the area corresponding to one character line is completely If it is judged that it is not a pattern (synonymous with “normal”) but a part of one character (partial pattern), those partial patterns are combined and output as information of one character. As a result, when multiple judgments are possible, multiple hypotheses are created and sent to the recognition processing unit, and the recognition processing unit makes a comprehensive judgment on those hypotheses to eliminate ambiguity. It is in. In the pattern cutout and recognition system according to the present invention, in order to execute the above-mentioned operation, in addition to the complete pattern, the pattern dictionary includes a pattern (partial pattern) indicating at least a part of the complete pattern. The feature is that it has the configured one.

[0006]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The principle of the present invention will be described below, and then embodiments will be described in detail with reference to the drawings. The principle of the present invention lies in the following two points. That is, (1) When ambiguity occurs in the cutout of a pattern, the cutout unit makes a plurality of hypotheses and recognizes a unit pattern including a partial pattern according to each hypothesis without forcibly making a judgment. Send to the department. (2) The recognition unit discriminates the unit pattern described above, and checks the validity of the cutout from a comprehensive judgment to eliminate the ambiguity. Hereinafter, this will be described more specifically.

FIG. 3 is a diagram showing various states of adjacent character patterns. In FIG. 3A, the patterns 31 and 32 overlap in the vertical direction. In this case, a continuous black area can be cut out as a pattern component. The method of extracting a continuous black area as a pattern component is well known in the art, and not only when the characters are correctly written in the frame, but also when the text is simply overlapped, the black area is extracted. Since it is possible to extract even the portion that extends outside the frame along the line, the unit pattern can be cut out correctly. Regarding this, for example, A.Ro
senfeld et.al., “Sequential Operations in Digit
al Picture Processing ”(J. ACM, vol.14, No.4,
Oct., 1966, pp.471-494) can be referred to.

Next, in FIG. 3 (b), the pattern is a portion 33.
And 34, and most of the separated components 34 are contained in adjacent frames. If it is unknown whether the pattern 34 belongs to the frame 21 or the frame 22, it is assumed that both are “possible cases” and a multiple hypothesis is created. Then, both cases are sent to the recognition section separately, and which hypothesis is correct is determined from the recognition result. 3C is a case where the separated character patterns are in contact with each other, and FIG. 3D is a case where the separated patterns are in contact with each other. In the case of FIG. 3C, the separation pattern is only the number “5”, whereas in the case of FIG. 3D, both the numbers “5” and “7” are the separation patterns and Are in contact.

FIG. 3 (e) shows a case where perfect patterns are in contact with each other. That is, the patterns are not separated, but the adjacent patterns are in contact with each other. Figure 3
The recognition method for the cases (b) to (e) will be described below with reference to FIGS.
It will be described with reference to FIG. FIG. 4 is an operation explanatory diagram when the cutout unit makes a plurality of hypotheses, and describes a recognition method when the separated pattern component 34 is included in the adjacent frame as shown in FIG. 3B. is doing. In FIG. 4, 5
1,53 are two hypotheses output by the clipping unit, and 20
Reference numeral 0 is a recognition unit, 100 is a pattern dictionary, and 101 to 104 are partial dictionaries in the pattern dictionary 100.

The recognition unit 200 uses the above-mentioned two hypotheses 51, 5
3 is input to perform character recognition, and recognition results 52 and 54 for each are output. That is, the recognition results for the first hypothesis 51 are (SP.5) and (RJ.6). Here, (SP.5) means "5 sub patterns", which is recognized by referring to the partial dictionary 101, and
(RJ.6) means “reject (unread), but candidate is 6”. Furthermore, the recognition results for the second hypothesis 53 are (AC.5) and (AC.6), both of which are
It means acceptance as the number "5" or "6". Therefore, the second hypothesis is valid, and the recognition results are the numbers “5” and “6”.

The partial dictionaries 101 to 103 provided in the above-mentioned pattern dictionary 100 are newly provided in the present invention, and conventionally, only the dictionary 104 having a normal pattern is provided. . The above-mentioned partial dictionary 101 is a dictionary that stores partial patterns, the partial dictionary 102 stores a dictionary that stores patterns in which partial patterns come into contact with other characters, and the partial dictionary 103 stores contact character patterns. This is a dictionary. Next, FIG.
A recognition method when the separated pattern component is in contact with an adjacent character as shown in (c) will be described with reference to FIG.

In this case, as shown in FIG. 5, the cutout result is 55, and the recognition result 56 is (SP.5) and (SC.
5, 6). Here, (SC.5, 6) means that the partial pattern of the numeral "5" and the numeral 6 are in contact with each other, and is recognized by referring to the above-mentioned partial dictionary 102. From this result, the read character is the number "5".
And "6" can be determined. Next, a recognition method when the separated pattern components are in contact with each other as shown in FIG. 3D will be described with reference to FIG. In this case, as shown in FIG. 6A, two hypotheses 57 and 59 stand and recognition results 58 and 60 are obtained. Further, in this case, FIG.
As shown in (b), in particular, the sub-pattern 61, that is, 38 in FIG. 3 (d) is recognized alone, and as a result, the recognition result 62 (SS.5, 7) is obtained.

The above-mentioned hypothesis 57 is a hypothesis 59 when the sub-pattern 38 is assumed to be added to the right side.
Is a case where the sub-pattern 38 is assumed to be added on the left side. In addition, recognition results 58 (SP.5) and (R
J.? ) Is “5 sub-pattern” and “reject (totally unknown)”, and similarly, (RJ.?) And (S
P.7) is "reject (totally unknown)" and "7 sub-pattern". Further, (SS.5, 7) of the recognition result 62 means "a pattern in which the sub-pattern of the numeral 5 and the sub-pattern of the numeral 7 are in contact". These are partial dictionaries 1 of patterns in which partial patterns and other characters are in contact.
No. 02 is obtained. By summing up these results, the answer is judged to be the numbers "5" and "7".

Next, a recognition method in the case where perfect patterns are in contact with each other as shown in FIG. 3E will be described with reference to FIG. In this case, as shown in FIG. 7, the whole is sent to the recognition unit without being forcibly divided, the same is searched for and recognized by referring to the partial dictionary 103. Here, as a result, (CC.5, 6) is obtained, which means that the numbers "5" and "6" are in contact with each other.
As described above, the present invention is characterized in that the recognition results are combined to give the final answer. Actually, for example, it is realized by processing according to the following rules.

The processes performed on FIGS. 3A to 3E are summarized as follows. (a) (AC.5) (AC.6) → (AC.5) (AC.6) (b) (SP.5) (RJ.6) (AC.5) (AC.6) → (AC .5) (AC.6) (c) (SP.5) (SC.5,6) → (AC.5) (AC.6) (d) (SP.5) (RJ.?) (RJ. ?) (SP.7) (SS.5,7) → (AC.5) (AC.7) (e) (CC.5,6) → (AC.5) (AC.6) The recognition result code for each hypothesis on the left side of is rewritten to the recognition result code on the right side. A generalization of these will be called Rewriting Rules.

In the cutout method shown in this embodiment, the rewriting rule is as follows.

[Outer 1] Rule R1 corresponds to (a) and (b) shown on page 8. Even if there is a place that does not accept (recognize) a and b, there is another place that accepts. That is to say that it was recognized.

Rule R2 corresponds to the same (c), and
When the contact between the sub-pattern of a and the pattern of b is recognized while the sub-pattern of 1 is recognized, it means that a and b can be recognized. Rule R3 is
It corresponds to the same (d), and a sub-pattern of a is recognized and a candidate of an arbitrary value other than accept is given, for example, while a sub-pattern of b is recognized and a candidate of an arbitrary value other than accept is given. Is given, it indicates that only subpatterns that are separated are to be recognized. Further, the rule R4 also corresponds to the same (d), and shows the case of comprehensive recognition including the recognition result of only the sub-pattern processed by the rule R3. That is, when three patterns, that is, a pattern that cannot be recognized as the sub-pattern of a, a pattern that cannot be recognized as the sub-pattern of b, and a pattern in which the sub-pattern of a and the sub-pattern of b are in contact, are recognized by comprehensive recognition, a Accept and b accept.

Rule R5 corresponds to the same (e), and
The pattern in which b and b are in contact is a accept and b accept. FIG. 8 shows a block diagram of a character reading apparatus which is an embodiment of the present invention. The character reading device according to the present embodiment includes a pattern observation unit 800, a pattern cutout unit 900, a form format dictionary 950, a pattern recognition unit 200, a pattern dictionary 100, a recognition result final determination unit 400, and a recognition result rewriting rule dictionary 300. ing. The operation of this device will be described below. On the form 75 to be read, characters are written under natural writing conditions as shown in FIG. The form 75 is input to the pattern observation unit 800, and photoelectric conversion and preprocessing (2
When the two-dimensional video pattern is subjected to binarization and form skew correction), the two-dimensional video pattern is sent to the pattern cutout unit 900 as an electric signal.

The pattern cutout unit 900 refers to the frame position parameters from the form format dictionary 950,
Patterns judged to correspond to one character are cut out one by one from the image of one form and sent to the pattern recognition unit 200. The pattern recognition unit 200 compares and collates the input pattern for one character with each pattern stored in the pattern dictionary 100 whose contents are illustrated in FIG.
The recognition result is sent to the recognition result final determination unit 400. Note that the processing in the pattern recognition unit 200 is as described above.
It goes without saying that it also includes sub-patterns and patterns of two characters that have come into contact with each other. Further, in the present embodiment, the recognition result output from the pattern recognition unit 200 is symbolized for each input pattern and sent to the recognition result final determination unit 400. Recognition result final determination unit 40
0 applies the respective rewriting rules in the recognition result rewriting dictionary 300 to the received recognition result in order until there is no applicable rewriting rule, and performs the rewriting process.

That is, from the conditions of the above-mentioned rewriting rules R1 to R5, the one in which the above-mentioned symbolized recognition result matches this is selected and applied, and the result is adopted. The process of the pattern cutout unit 900 and subsequent processes will be described in more detail below. FIG. 9 exemplifies a flowchart of the above-described cutout processing and recognition processing and the content of data corresponding to this. In step 701, the video pattern 712 for one line is cut out from the video pattern 711 for one form.
In step 702, the continuity of the black background pattern is used to
After extracting the pattern component for each black background and performing ordering in the horizontal direction, a component list 713 is created. Furthermore, the attribute of each component is calculated, and the component attribute list 714 is created. Here, the attribute of a component means the upper and lower ends of each component,
The coordinates of the left and right edges, the total length of the contour, etc.

Next, in step 703, a hypothesis of a boundary between characters is set from the component attribute list 714 created above and the information in the form format dictionary 950, and the character list 71 is created.
Create 5. This character list 715 shows which component each character pattern is composed of. In FIG. 9, in the first hypothesis, one character, 4 and 5 are combined in order 1, 2, and 3, respectively. The second hypothesis shows an example in which the characters 1 and 2 are combined into one character, the character 3 alone is combined with one character, and the strings 4 and 5 are combined into one character. The above is the processing of the pattern cutout unit 900.
Step 704 is processing of the pattern recognition unit 200.
In step 704, the component list 713, the component attribute list 714, and the character list 715 described above are input, the components shown in the character list 715 are collected and pattern matching is performed, and the result is written in the result list 716.

The result code representing the matching result is the above-mentioned result code.
(SP.a), (SC.a, b), (SS.a, b), (CC.a,
b), (AC.a), (RJ.a), etc. The meanings of these are, as described above, “sub-pattern of category a”, “sub-pattern of category a and sub-pattern of category b”, and “sub-pattern of sub-categories a and b contact each other”, respectively. , “Category a and category b are in contact with each other”, “category a pattern”, and “candidate a is rejected”. Step 705 is processing of the recognition result final determination unit 400. Here, with respect to the above-mentioned result list 716, all rules in the rewriting rule dictionary 300 are referred to, they are sequentially applied until there are no applicable rules, and processing according to the finally obtained result is performed.

In step 706, it is determined whether or not the processing has been completed for all the lines on the form 75. If not completed, the procedure returns to step 701 and the above-described processing is repeated until the processing is completed. According to the above-described embodiment, for example, the input 1 unit image pattern is 1 in the recognition unit.
If it is determined that the pattern is a part of a pattern that represents a category, multiple partial patterns are combined into one character,
It is possible to perform character recognition on the combined characters, and it is possible to obtain the effect of improving the reading accuracy of characters written under natural writing conditions in the character reading device. It is needless to say that the above embodiment shows one example of the present invention, and the present invention should not be limited to this.

[0024]

As described above in detail, according to the present invention, a character written under natural writing conditions, such as a large protrusion from a character frame or a contact with an adjacent character,
In particular, when it is determined that the input 1-unit video pattern is a part of the pattern representing one category, it is possible to combine a plurality of partial patterns into one character and perform character recognition on the combined character. It has a remarkable effect that a pattern cutting and recognition method and its system can be realized.

[Brief description of drawings]

FIG. 1 is a diagram showing an example of a character frame and a handwritten character of a conventional OCR form.

FIG. 2 is a diagram showing an example of a character frame and a handwritten character of a conventional OCR form when a writing condition is relaxed.

FIG. 3 is a diagram illustrating various states of adjacent character patterns.

FIG. 4 is a diagram (No. 1) for explaining the principle of the present invention.

FIG. 5 is a diagram (part 2) explaining the principle of the present invention.

FIG. 6 is a diagram (part 3) explaining the principle of the present invention.

FIG. 7 is a diagram (part 4) explaining the principle of the present invention.

FIG. 8 is a block diagram of a character reading device according to an embodiment of the present invention.

FIG. 9 is a diagram exemplifying a flowchart of cutout processing and recognition processing and a content of data corresponding to the processing in the character reading device according to the embodiment.

[Explanation of symbols]

 75 Documents to be read 100 Pattern dictionary 101 to 103 Partial dictionary 104 Normal pattern dictionary 200 Pattern recognition unit 300 Recognition result rewriting rule dictionary 400 Recognition result final determination unit 800 Pattern observation unit 900 Pattern cutout unit 950 Form format dictionary

Front page continuation (72) Inventor Shozo Kadota 2880, Kozu, Odawara-shi, Kanagawa Hitachi Ltd., Odawara Plant (72) Inventor, Kiyomichi Kurino 2880, Kozu, Odawara, Kanagawa Ltd.

Claims (6)

[Claims] 1. A form that does not have a character frame for each character is input, and one or more patterns including characters are cut out from a two-dimensional video pattern converted into an electrical signal by a cutout unit, and the pattern is recognized. A pattern cutting and recognizing method, which is configured so that the pattern is recognized by comparing the pattern with each pattern in a pattern dictionary in the recognizing unit, and the recognizing unit includes a character line portion of the two-dimensional video pattern. The region corresponding to is processed, the region of consecutive black pixels is extracted as a pattern component, the pattern components are ordered in the horizontal direction, and then a character component list having the pattern component as an element is created. Furthermore, the attribute of each part of the character component list is calculated to create a component attribute list, and the component attribute list is referred to for the unit of each character or A hypothesis of a combination of a plurality of pattern components is established, the hypothesis of the combination is stored as a character list, the recognition unit inputs the character list, and a combination of pattern components to be recognized from the character list is configured. A pattern cutout and recognition method, wherein recognition processing is performed by matching each pattern in the pattern dictionary, and a final determination unit makes a comprehensive determination of the recognition result for one character line. 2. In the cutout by the cutout unit, if there is ambiguity about a combination of pattern components forming a character, a plurality of hypotheses are created and the plurality of hypotheses are stored in the character list. Claim 1 characterized by
Described pattern cutting and recognition method. 3. The pattern cutout and recognition method according to claim 2, wherein the recognition unit reads the plurality of hypotheses from a character list and performs recognition processing of a combination of pattern components corresponding to the respective hypotheses. . 4. The pattern cutout according to claim 3, wherein the final judgment unit inputs recognition results corresponding to the plurality of hypotheses, performs a comprehensive judgment, and selects a single hypothesis. And recognition method. 5. A form that does not have a character frame for each character is input, and a cutout unit cuts out a one-unit video pattern containing characters from a two-dimensional video pattern converted into an electrical signal, and the pattern recognition unit recognizes the pattern. A pattern cutout and recognition system configured to recognize the pattern by comparing it with each pattern in a pattern dictionary in a recognition section, wherein the cutout section performs processing on the two-dimensional video pattern. , A region of consecutive black pixels is extracted as a pattern component, the pattern components are ordered in the horizontal direction, and then a character component list having the pattern component as an element is created, and the attribute of each part of the character component list is created. To create a component attribute list and refer to the component attribute list to combine one unit or a plurality of pattern components forming each character One or more hypotheses are stored, the hypotheses of the combination are stored as a character list, and the recognition unit inputs the character component list and the character list to form a combination of pattern components to be recognized from the character list, Recognition processing is performed by matching each pattern in the pattern dictionary, and a final determination unit makes a comprehensive determination of the recognition result of one character line and selects a single hypothesis. Recognition system. 6. The pattern dictionary stores a complete pattern forming one character pattern, a partial pattern forming a part of the character pattern, and a contact pattern in which one character pattern is in contact with another character pattern. The pattern cutting and recognizing system according to claim 5.