JPH11272804A - Method and device for recognizing character - Google Patents

Abstract

PROBLEM TO BE SOLVED: To extract a reliable word string candidate with high accuracy by using a part character string constituting one part of a word as a word candidate and performing collation on a character level. SOLUTION: An destination of a mail, etc., undergoes image input 101 and character line extracting processing 102 extracts an address character line. Next, pattern segmentation processing 103 segments a character pattern candidate from the address character line and character identification processing 104 obtains an identification candidate character by using a character identification dictionary 105. Character segmentation processing 106 obtains a word string candidate of a character unit from the pattern candidate and the identification candidate character. Word collation processing 107 collates with the candidate character by a town area address dictionary 108 and makes it a word candidate. Next, part work collation processing 110 collates a part character string produced from the dictionary 108 with the word string candidate and adds it to a word candidate. Hierarchy processing 109 produces a hierarchy for the dictionary 108 among word candidates and a word string from connection relations. Read result selection processing 111 selects what is appropriate among word strings and outputs an address read result 113 together with a town section number.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to the recognition of a word string having a hierarchical structure, and more particularly to a method and apparatus for character recognition which is preferable for reading the address of a mail.

[0002]

2. Description of the Related Art In order to read a printed or written address, the following three functions are required.

(1) Cut out a character pattern. (Character extraction) (2) The character type of each character pattern is identified. (Character identification) (3) The result of character identification is interpreted as a character string. (Character string collation) Among these, factors such as incomplete description and noise are (1)
In most cases, (2) cannot be used. For more accurate character recognition, the complementing function in (3) character string collation is important.

A typical example of a word string having a hierarchical structure is a town area portion of an address character string. This matching method uses "prefecture"
A method of obtaining address structure candidates based on key characters such as “city” and “town” and obtaining an address character string by applying a hierarchical relationship (Transactions of the 41st Annual Convention of IPSJ 90 4L-5 "Examination of post-processing method for character recognition result of address"), a method of extracting an address character string by extracting place names constituting an address by word matching and tracing the hierarchical relationship of the address from top (prefecture) to top down ( 1979 IEICE National Convention D-465 "Knowledge Processing for Freely-written Address Strings")
And so on. In the method described in IPSJ Transactions No. 35, No. 6, "Error Correction Algorithm for Handwritten Kanji Address Recognition", a place name word at an arbitrary position is extracted by an automaton-type word collation even if the candidate character is incomplete. At the same time, by performing a bottom-up process of determining the positional relationship between place names while tracing the hierarchical relationship from the lower hierarchy to the upper hierarchy based on the candidate place name of each hierarchy, flexibility in address notation, complementing ability and processing It solves the problem of quantity and realizes a practical method.

[0005] However, in these methods, when a character candidate is incomplete, completion is performed on a word-by-word basis, and a penalty is added to evaluate the incompleteness of the word. As a result, a plurality of penalized word candidates appear, which increases the possibility of selecting an erroneous candidate as a street address character string that is a word string candidate.

[0006]

In the above prior art,
Word matching is performed for noise that is mixed in the word string to be read, blurred characters, incorrect patterns caused by handwritten character deformation, or difficult to identify and incomplete identification candidate characters. In that case, the candidate responded by issuing a complemented word candidate and imposing a penalty appropriate to that. In order to perform matching using words as the minimum unit,
When a word is incomplete, a word penalty is imposed on the candidate word, and a word string must be selected from word candidates with low certainty, which has a problem in reliability.

[0007] The problem to be solved by the present invention is to provide a word string having high accuracy and reliability by performing collation at the level of the characters constituting the word even if the word described is incomplete due to missing characters or the like. Getting candidates.

[0008]

In order to solve the above-mentioned problems, according to the present invention, not only words originally existing in the dictionary but also partial character strings constituting a part of the words are used as word candidates, and the character level is used. Is matched. In the following, a character string forming a part of such a word will be referred to as a partial word, and word matching based on the partial words will be referred to as partial word matching.

This partial word collation is performed when a part of the word is obtained with high reliability from among the candidate characters, and a candidate word string can be selected by using the partial word. In addition, by performing hierarchical processing, word string candidates can be obtained with a high degree of certainty.

Although there is a possibility that the same word candidate may appear even by complementing the conventional method, in this case, the penalty is imposed excessively for the low degree of matching of the character with the word. The partial word uses only a part with a high degree of coincidence, so that the word penalty is low, a higher degree of certainty can be obtained when connected as a word string, and the reliability as a word string candidate is high.

[0011] As described above, the above-mentioned problem is solved. For this purpose, according to the present invention, there is provided image input means for digitizing and inputting image information described on a document which is an object of the present invention, In a character recognition method having means for reading a word string described from the inside, a character line extraction process is performed to extract a character line in which a target word string is described from an image, and a plurality of character pattern candidates are cut out. Perform pattern extraction processing, character-identify the extracted pattern, perform character identification processing to obtain a plurality of recognition candidate characters, narrow down character pattern candidates according to the character identification result and the validity of the character pattern, and perform one or more Perform character extraction processing to determine the extraction for each character, and compare it with the word information in the prepared word string dictionary to A word matching process is performed to generate a number of word candidates, a partial word consisting of a part of the word generated from the word string dictionary is word matched, and a partial word matching process of adding the result to the word candidate is performed. By performing a hierarchical process of generating a word string candidate from a word candidate by referring to a hierarchical relationship and a connection relationship of words, and performing a reading result selecting process of selecting an appropriate reading result from the word string candidates, A word string consisting of a plurality of words having a hierarchical structure is read.

According to the second aspect of the present invention, in the hierarchical processing, when a connectable upper-level word is not found, or when a word penalty is large even if it is found (that is, no effective connection candidate is obtained when creating a word string candidate). Time),
Partial word matching is performed on the upper word.

According to a third aspect of the present invention, a partial word effective for reading a word string is created in advance from the words in the word string dictionary, stored as a partial word dictionary, and the partial word dictionary is referred to. The result of word matching is added to candidate words.

[0014]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a flowchart showing an example of an embodiment of a character recognition method according to the present invention. This example is an address recognition process in which an entire image obtained by photoelectrically converting a surface on which an address is described is input and an address character string as a read result is output.

Here, the present character recognition method is applied to reading of a word string in a town area from a prefecture to a town name in an address of an address, and an example in which the candidate character lattice is incomplete is shown in FIG. It is assumed that a postmark has been applied to a town area.

An addressing surface such as a postal matter is taken in as an image input 101 by an image pickup means (scanner section).
A character line extraction process 102 extracts an address character line from the entire image.

Next, a pattern extraction process 103 extracts a pattern candidate that can be a character from the address character line.

The character identification process 104 performs character identification for each of the extracted pattern candidates using the character identification dictionary 105, and outputs a plurality of candidate characters and the degree of similarity between the candidate characters.

The character extracting process 106 selects a pattern based on the character identification similarity of each pattern candidate, the positional relationship between the patterns, and the like, generates one or a plurality of pattern strings, and outputs them as character extracting candidates. .

The word matching process 107 searches for a word in the town area address dictionary 108 from a candidate character lattice obtained by combining the character segmentation result and the identification candidate character of each pattern. The corresponding parts of the character lattice are compared, a penalty corresponding to the degree of matching of each character is calculated, and the result is output as a word candidate. A word candidate lattice is created from the thus obtained word candidates and the positional information of each word candidate.

The town area address dictionary 108 stores words of each layer and information on connection relationships between the layers, and is referred to for generating a town area word string of addresses.

The hierarchy processing 109 searches word candidates in the upper hierarchy in order from the lowest hierarchy of the town area address dictionary 108 on the word candidate lattice based on the connection relation, and generates a word string. The validity of the positional relationship between the connected words is defined as a connection penalty, and the degree of certainty as a word string is calculated in combination with the word penalty, thereby defining a candidate word string for a town area.

In the hierarchical processing 109, if a valid word is not found as a higher word to be connected even though the word penalty is sufficiently low, the partial word matching processing 110
I do. The partial word matching process 110 searches for a connectable high-order word from the town address dictionary 108 and, for those partial character strings that can identify the town address character string, performs word matching again on the candidate character lattice. Is what the line is about. As a result, the partial word comes up as a candidate, and if the word penalty and the connection relationship are appropriate, this is used as a candidate word string in the town area.

The reading result selection processing 111 selects the one having the highest certainty as the recognition result of the town area part from the candidate word strings of the street address based on the certainty.

After the candidate for the town area is selected, a block number representing a street or an address is read 112 from the position following the end of each candidate for the town character of the candidate character lattice, and is output as a final address reading result 113. .

Next, the details of each process in FIG. 1 will be described.

The character line extraction process 102 is a process for extracting an address character line from the image 201 of the mail address surface. The address character line represents a rectangular area 202 including the name of the prefecture, the name of the city, the name of the city, and the address. If the address extends over a plurality of lines, a rectangular area corresponding to the number of lines is output. As a method of extracting an address character line, for example, Japanese Patent Application Laid-Open No. 9-1610
A method as described in FIG.

The pattern cutting process 103 will be described with reference to FIG. The pattern cutout processing is performed on the address character line 2
A candidate for a character boundary is extracted based on a cluster of black pixels on 02 (connected component), and a plurality of combinations of patterns that can become a character are selected as character pattern candidates. At this time, cutting processing of the contacted character pattern is also performed. Numeral 301 is a diagram expressing a pattern cut out of the address character line 202 in a graph. Hereinafter, this is called a cut-out graph.

The character identification processing 104 is realized by using a known method such as pattern matching or structure analysis. By character identification, it is assumed that a plurality of candidate characters and the similarity to the standard pattern in the character identification dictionary 105 are obtained for each of the extracted pattern candidates as shown in FIG.

The character extraction processing 106 is the character identification processing 1
Pattern selection is performed based on the similarity of the identification candidate characters of each pattern candidate obtained in step 04, the positional relationship between the patterns, and the like, and one or more pattern strings are generated as shown in FIG. Output as The selection of patterns can be regarded as an optimal path search problem on a cut-out graph having an arc weighted by a similarity or a positional relationship between patterns.

The structure of the street address dictionary 108 will be described with reference to FIG.

The town area address dictionary 108 is used for the word matching process 10.
7, a hierarchy process 109, and a dictionary referred to in the partial word collation process 110. As shown in FIG. 6, the dictionary is composed of four layers of place name word dictionaries 601 to 604. The place name word of each hierarchy has connection information to the place name word of the upper hierarchy, and the town area word string of the address connects words according to the connection information from the core word of the third or fourth hierarchy from the bottom up. It is obtained by going. In the word matching processing 107, the place name words in each layer are referred to to create word candidates. In the hierarchical processing 109, the word is connected by referring to the core place name word and sequentially going to the place name word dictionary of the upper hierarchy based on the connection information of the word, thereby obtaining a town area word string candidate. Further, in the partial word matching process 110, the reference to the core word, the search for the higher-order connected word, and the acquisition of the word information for creating the partial word are performed using the town address dictionary 108.

The word collation processing 107, the hierarchy processing 109, and the reading result selection processing 111 are realized according to the method described in IPSJ Transactions No. 35, No. 6, "Error Correction Algorithm for Handwritten Kanji Address Recognition". .

In the word matching process 107, as shown in FIG.
A dictionary word is searched from each candidate character in the candidate character lattice 701 composed of the character cutout candidate 501 (and 502) and the identification candidate character of each pattern, and a dictionary word having the first or second character matching is determined as a candidate word. I'll give it. At this time, a penalty is calculated for each candidate word in consideration of the degree of matching with each corresponding character on the candidate character lattice 701. This word penalty is 0 when all the character candidates of the word are first. A word candidate lattice 702 is created from the thus obtained word candidates and position information on the description position of each word candidate. In the example of 702, for example, for “Honmachi” 703, the word penalty is 0 because all character candidates are in the first place, and in “Honda” 704, “hon” is the first place and “many” is not a candidate. A large penalty is imposed on “many”. Further, for “Fuchu City” 705, “Middle” is the second candidate and no candidate characters corresponding to “Fu” and “Town” are found, so the word penalty is further increased.

The hierarchical processing 109 is performed in the word candidate lattice 70
Based on the connection relation of the town area address dictionary 108, words of the upper layer are searched in order from the word candidate lattice 702 with the word of the lowest hierarchy at the core as the core, and a town area word string of the address is generated. . The validity of the positional relationship with respect to the description position of the connected word is defined as a connection penalty, and the degree of certainty as a word string is calculated together with the word penalty, thereby defining a candidate word string for a town area. FIG. 8 illustrates a state of the hierarchical processing in the word candidate lattice 702. In this case, the core word is the third hierarchy, and the only upper hierarchy word that can be connected is “Fuchu City” in the second hierarchy. The word strings that can be formed based on the connection relationship are “Fuchu City Kotobukicho”, “Fuchu City Fuchucho”, “Fuchu City Honmachi”, and “Fuchu City Honjukucho”. When only one character is allowed, the locations that are appropriate as the positional relationship are “Fuchu-shi Honmachi” and “Fuchu-shi Honjuku-cho”. However, in these cases, the word penalty of “Fuchu” is large, and the connection penalty is added to the extent that the second-layer word and the third-layer word overlap, so that the certainty factor as a word string is reduced.

The partial word processing 110 will be described with reference to FIGS.

In the partial word processing 110, in the hierarchy processing 109, if a valid word cannot be found as a higher word to be connected even though the word penalty is small,
The connectable words are searched from the town address dictionary 108, and the partial character strings of these words that can identify the town address character string are subjected to word matching again on the candidate character lattice 701. In the hierarchical processing 109, when the penalty of the core word is small on the word candidate lattice 702 and the upper word is not found, the town area word string 902 including the core word is selected from the town address dictionary 108 first. In order to select a town area word string, a core word is found from the town area address dictionary as shown in FIG. 9 and upper words are connected according to the connection information of the word. Next, of the town area word strings obtained in this manner, the following processing is performed on only the word that is uniquely determined by the core word and its upper words. The target town area word string can be identified by the core word and its upper words. Therefore, of the words included in the target town area word string, word matching using partial words is performed for each of the upper words of the core word. In this example, “Honmachi” 901 is a word having a small penalty and no valid upper word to be connected. For “Honmachi” 901, “Kokubunji city” 1001 “Fuchu city” 1002 “Tanashi city” 1003 as shown in FIG. In this case, partial words such as one character, two characters... From the end of the word, such as 1004, are dynamically created in consideration of the incompleteness of the head of the word. In order to maintain the uniqueness of the town area word string determination based on the partial words, word matching is performed again on the candidate character lattice 701 as a partial word candidate, excluding a duplicated word from all the created partial words. . As a result, four valid partial words like 1005 are dynamically generated. As for the generation of the partial words, a partial word effective for reading the word string may be created in advance from the words in the word string dictionary, and this may be stored as the partial word dictionary. When word matching is performed on these partial words, a word candidate lattice like 1006 is obtained. If a partial word comes up as a candidate, the hierarchical processing is continued in addition to the word candidate. At this time, the connection relation of the partial words is inherited from that of the original word, but a connection to a higher order is not required. In this example, as shown in FIG.
There may be connections such as "Nakaichi Honjuku-cho", "(Kokubu) Bunji-shi Honda", "(Kokubu) Teraichi Honda", etc., but the core word "Honjuku-cho"
These are not adopted because the word penalty for "Honda" is large. In this way, if the partial word is raised as a candidate and the connection relation with the word penalty is appropriate, this is set as a candidate word string in the town area. In this example, "(Fu) Nakaichi Honmachi"
"(Kokubu) Honcho, Kunibu" and "Honmachi (Kokubu) Teraichi" are added as candidate word strings.

The reading result selection processing 111 selects the one having the highest certainty as the recognition result of the town area portion based on the certainty degree from the word string candidates of the town area. In this example, “(Kokubun) Teraichi Honmachi” is finally obtained as a town area word string from the word penalty and the connection penalty.

After the candidate for the town area word string is selected, block numbers indicating the streets and addresses are read 112 from the position following the end of each town area candidate in the candidate character lattice, and the final address read result 113 Output as

[0040]

According to the method and apparatus of the present invention described above,
When recognizing a word string having a hierarchical structure such as a town area where a postal address is located, even if the word is incomplete, a word string with high accuracy and reliability can be obtained by performing matching at the level of the characters that make up the word. Candidates can be obtained.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing an example of an embodiment of a real name invention.

FIG. 2 is a conceptual diagram showing an example of a mail address surface image and an address character line.

FIG. 3 is a diagram showing a relationship between a pattern cutout process and a cutout graph.

FIG. 4 is a diagram showing each pattern and the result of its character identification processing.

FIG. 5 is a diagram showing an example of a character cutout candidate.

FIG. 6 is a conceptual diagram showing a configuration of a town area address dictionary.

FIG. 7 is a diagram showing a relationship between a candidate character lattice and a candidate word lattice.

FIG. 8 is a diagram showing an example of a procedure of a hierarchical process.

FIG. 9 is a conceptual diagram showing a procedure for selecting a target for creating a partial word.

FIG. 10 is a diagram showing a procedure for creating a partial word and a partial word matching process.

FIG. 11 is a diagram showing a procedure of hierarchical processing using partial word candidates.

[Explanation of symbols]

101: input image, 102: character line extraction processing, 103:
Pattern cutout processing, 104 ... Character identification processing, 105 ...
Character identification dictionary, 106: character extraction processing, 107: word collation processing, 108: town area address dictionary, 109: hierarchical processing, 110: partial word collation processing, 111: reading result selection processing, 112: block reading, 113: address Reading result, 201: mail address side image, 202: address character line, 301: cut-out graph, 401: character identification result,
501: character extraction candidate 1, 502: character extraction candidate 2, 601: first-level place name word dictionary, 602: second-level place name word dictionary, 603: third-level place name word dictionary, 60
4. Fourth hierarchical place name word dictionary, 701: Candidate character lattice, 702: Candidate word lattice, 703: Candidate word example "Honmachi", 704: Candidate word example "Honda", 705 ... Candidate word example "Fuchu" 901: a core word for activating the partial word matching process; 902: a town area word string identified by the partial word; 1001: an example of a word to be subjected to the partial word creation: "Kokubunji City"; 1001 ... Examples of words for which partial words are to be created, “Fuchu City”, 1001. Examples of words for which partial words are to be created, “Tanashi City”, 1004, partial words, 1005, valid partial words.

────────────────────────────────────────────────── ───

[Procedure amendment]

[Submission date] July 19, 1999

[Procedure amendment 1]

[Document name to be amended] Statement

[Correction target item name] Claims

[Correction method] Change

[Correction contents]

[Claims]

[Procedure amendment 2]

[Document name to be amended] Statement

[Correction target item name] 0011

[Correction method] Change

[Correction contents]

[0011] In order to solve the above-mentioned problem, an image input means for digitizing and inputting image information described in a text which is an object of the present invention is provided. In a character recognition method having means for reading a word string described from the inside, a character line extraction process is performed to extract a character line in which a target word string is described from an image, and a plurality of character pattern candidates are cut out. Perform pattern extraction processing, character-identify the extracted pattern, perform character identification processing to obtain a plurality of recognition candidate characters, narrow down character pattern candidates according to the character identification result and the validity of the character pattern, and perform one or more performs character cutout process of determining the cut-out character units, double from the recognition candidate characters by collation with the word information in the word dictionary prepared in advance Deeds word collation processing for generating a word candidates, a partial word comprised of a portion of a word generated from the word dictionary and word collating performs partial word collating process of adding the result to the word candidate, the word in the dictionary By performing a hierarchical process of generating word string candidates from word candidates by referring to a hierarchical relationship and a connection relationship, and performing a reading result selecting process of selecting an appropriate reading result from the word string candidates, a hierarchical structure is obtained. A word string consisting of multiple words with is read.

[Procedure amendment 3]

[Document name to be amended] Statement

[Correction target item name] 0013

[Correction method] Change

[Correction contents]

[0013] word by the claims 3, which leave create a valid partial word from word of advance word dictionary to read the word string, and stores it as a partial word dictionary refers to the partial word dictionary The matching result is added to the candidate word.

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Masafumi Koga 1-280 Higashi Koigakubo, Kokubunji-shi, Tokyo Inside Central Research Laboratory, Hitachi, Ltd.

Claims (5)

[Claims] 1. A character recognition method and apparatus comprising: image input means for converting image information written on a document into an electric signal and inputting the signal; and means for reading a word string described in the image. A character line extraction process for extracting a character line in which a target word string is described, a pattern cutout process for cutting out a plurality of character pattern candidates, and a character that obtains a plurality of identification candidate characters by character-identifying the cutout pattern Identification processing, character extraction processing for narrowing down character pattern candidates according to the character identification result and the validity of the character pattern, and determining one or more types of character string extraction of word string candidates. A word matching process that generates multiple word candidates from identification candidate characters by comparing with word information of Word matching of partial character strings to be added and the same result to word candidates, and a hierarchy for generating word string candidates from word candidates by referring to the hierarchical relationships and connection relationships of words in the dictionary A character recognition method and apparatus for sequentially executing a process and a reading result selecting process for selecting an appropriate reading result from word string candidates. 2. In the partial word matching process according to claim 1, a partial character string of a connection candidate word is generated and partial word matching is performed only when a valid connection candidate word is not found for a word candidate having a high degree of certainty. A character recognition method and apparatus. 3. The partial word matching process according to claim 1, further comprising means for storing a partial character string generated in advance from a word dictionary, and performing the same process using the stored partial character string. Character recognition method and apparatus. 4. A character recognition device having image input means for converting image information written on a document into an electric signal and inputting the same, and means for reading a word string described in the image. Word matching processing means for generating a plurality of word candidates by matching a word string with word information in a word dictionary prepared in advance, and word matching of a partial character string consisting of a part of a word generated from the word dictionary, Partial word matching processing means for adding the result to word candidates; hierarchical processing means for generating word string candidates from word candidates by referring to the hierarchical relation and connection relation of words in the dictionary; And a reading result selecting means for selecting an appropriate reading result from the data. 5. An image input process for converting image information described in a document into an electric signal and inputting the converted signal, a process for reading a word sequence described in the image, a process for preparing a read word sequence and A word matching process that generates a plurality of word candidates by matching with word information in a word dictionary, and a word matching of a partial character string that is a part of a word generated from the word dictionary, and adds the same result to the word candidates Partial word matching processing, hierarchical processing of generating word string candidates from word candidates by referring to the hierarchical relation and connection relation of words in the same dictionary, and selecting appropriate reading results from word string candidates And performing a reading result selecting process.