Character candidate suggestion device, handwritten character identification system, handwritten character identification method and program

Abstract

To provide a character candidate proposal device, a handwritten character identification system, a handwritten character identification method, and a program for proposing similar character string candidates more appropriately.SOLUTION: In a handwritten character identification system 1, a character candidate proposal device 100 comprises: a similar character storage unit 115 in which similarity relationships of the appearance of characters are stored; an existing-character storage unit 112 in which existing character strings are stored; a proxy processing unit 121 that receives one or more characters, and proxy-processes offering character candidates having similar appearance to the characters; a collation processing unit 123 that specifies candidates for characters having similar appearance to the received character by checking against the similar character storage unit, and checks against existing character strings stored in the existing character storage unit 112, among combinations of the candidates for characters having similar appearance; and a candidate character transmission processing unit 125 that outputs, as candidate characters, combinations of candidates for characters having similar appearance obtained as a result of the collation of the collation processing unit 123.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a character candidate suggestion device, a handwritten character recognition system, a handwritten character recognition method, and a program. [Background technology]

[0002] Patent document 1 describes that "the information processing device includes a character extraction unit 224 that extracts character strings from image data, a list creation unit 244 that creates a conversion candidate list including one or more conversion candidate characters corresponding to input characters, an identification unit 248 that identifies a conversion destination character based on a comparison between the one or more conversion candidate characters included in the conversion candidate list and the character string extracted by the character extraction unit, and a display control unit 252 that generates a display screen including the conversion destination character identified by the identification unit." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-163413 A Summary of the Invention [Problem to be solved by the invention]

[0004] Although the above technology can present character candidates, if the characters are misrecognized, it is difficult to obtain appropriate results.

[0005] An object of the present invention is to provide a technique for more appropriately proposing similar character string candidates. [Means for solving the problem]

[0006] The present application includes a plurality of means for solving at least part of the above-mentioned problems, examples of which are as follows: An information processing device according to one aspect of the present invention includes a similar character storage unit that stores a similarity relationship in the appearance of characters, an existing character storage unit that stores existing character strings, a request processing unit that receives one or more characters and accepts a request to devise character candidates having a similar appearance to the received characters, a matching processing unit that specifies character candidates having a similar appearance to the received characters by matching them with the similar character storage unit and matches combinations of the candidate characters having a similar appearance with the existing character strings stored in the existing character storage unit, and a candidate character transmission processing unit that outputs the combination of the candidate characters having a similar appearance that is found as a result of the matching by the matching processing unit as a candidate character.

[0007] For example, the above-mentioned character candidate suggestion device may also include a similar character registration processing unit that, after outputting the candidate characters, receives a character similar to any of the characters received by the entrusted processing unit, stores the character in the similar character storage unit if the similarity relationship is not stored in the similar character storage unit.

[0008] For example, in the above-mentioned character candidate suggestion device, the existing character storage unit may store character strings of existing personal names, the request processing unit may accept a request to propose a personal name as the character candidate to be proposed, and the candidate character transmission processing unit may output a combination of candidate characters having similar appearances as candidate characters for the personal name.

[0009] In addition, for example, the above-mentioned character candidate suggestion device may be configured such that the character string of the existing person's name is divided into a surname and a given name, and the device is equipped with a name discrimination processing unit that divides the received characters into a surname and a given name and causes the matching processing unit to match them.

[0010] Also, for example, the above-mentioned character candidate suggestion device may be characterized in that the name discrimination processing unit identifies combinations of surnames and given names by changing the position separating the surname and given name for the received characters, and when a hit is obtained as a result of matching by the matching processing unit for both the surname and given name of each combination, the combination is designated as a candidate character.

[0011] In addition, for example, in the above character candidate suggestion device, the candidate character transmission processing unit may output the candidate characters in an order according to appearance frequency.

[0012] In addition, for example, in the above-described character candidate suggestion device, the characters received by the entrustment processing unit may be characters that have been read and recognized as handwritten characters.

[0013] Further, a handwritten character identification system according to another aspect of the present invention is a handwritten character identification system including a character candidate suggestion device, a business terminal communicatively connected to the character candidate suggestion device via a network, and a reading device that reads handwritten characters in response to instructions from the business terminal, wherein the business terminal includes a character recognition unit that acquires the handwritten characters from the reading device and performs character recognition, a commissioning processing unit that transmits characters recognized by the character recognition unit to the character candidate suggestion device and commissions the suggestion of character candidates, and a visual confirmation processing unit that displays character candidates output from the character candidate suggestion device, and the character candidate suggestion device: The system is characterized by comprising a similar character storage unit that stores similar relationships in character appearance, an existing character storage unit that stores existing character strings, a request processing unit that receives one or more characters and requests the creation of character candidates having a similar appearance to the received character, a matching processing unit that identifies character candidates having a similar appearance to the received character by matching them with the similar character storage unit and matches combinations of the candidate characters having a similar appearance with the existing character strings stored in the existing character storage unit, and a candidate character transmission processing unit that outputs the combinations of candidate characters having a similar appearance that are found as a result of the matching by the matching processing unit as candidate characters.

[0014] A handwritten character identification method according to another aspect of the present invention is a handwritten character identification method using a handwritten character identification system including a character candidate suggestion device, a business terminal communicatively connected to the character candidate suggestion device via a network, and a reading device that reads handwritten characters in response to instructions from the business terminal, wherein the business terminal executes a character recognition step of acquiring the handwritten characters from the reading device and performing character recognition, a commissioning processing step of transmitting characters recognized in the character recognition step to the character candidate suggestion device and commissioning the suggestion of character candidates, and a visual confirmation processing step of displaying character candidates output from the character candidate suggestion device, The apparatus includes a similar character storage unit that stores similar relationships in character appearance, and an existing character storage unit that stores existing character strings, and executes an order processing step of receiving one or more characters and accepting the creation of character candidates having a similar appearance to the received character, a matching processing step of identifying character candidates having a similar appearance to the received character by matching them with the similar character storage unit, and matching combinations of the candidate characters having a similar appearance with the existing character strings stored in the existing character storage unit, and a candidate character sending processing step of outputting the combination of candidate characters having a similar appearance that is found as a result of the matching in the matching processing step as candidate characters.

[0015] Moreover, a program according to another aspect of the present invention is a program for causing a computer to perform a process for assisting in the identification of handwritten characters, the computer comprising a similar character memory unit that stores similar relationships in character appearance, an existing character memory unit that stores existing character strings, and a processing unit, and is characterized in that the processing unit executes an order processing step of receiving one or more characters and accepting the creation of character candidates having a similar appearance to the received character, a matching processing step of identifying character candidates having a similar appearance to the received character by matching them with the similar character memory unit and matching combinations of the candidate characters having a similar appearance with the existing character strings stored in the existing character memory unit, and a candidate character sending processing step of outputting the combinations of candidate characters having a similar appearance that are found as a result of the matching in the matching processing step as candidate characters. Effect of the Invention

[0016] According to the present invention, a technique for appropriately evaluating the content of a text can be provided.

[0017] Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0018] [Figure 1] 1 is a block diagram illustrating an overview of a handwriting identification system according to an embodiment. [Diagram 2] FIG. 1 is a diagram illustrating an example of the configuration of a handwriting recognition system. [Diagram 3] FIG. 13 illustrates an example of a data structure of a receipt data storage unit; [Figure 4] FIG. 13 is a diagram illustrating an example of a data structure of a surname storage unit. [Diagram 5] FIG. 4 illustrates an example of a data structure of a name storage unit; [Figure 6] 13 is a diagram illustrating an example of a data structure of a similar character storage unit; [Figure 7] 13 is a diagram illustrating an example of a data structure of a candidate character storage unit; [Figure 8] FIG. 4 illustrates an example of a data structure of a character storage unit; [Figure 9] FIG. 4 illustrates an example of a data structure of an image storage unit. [Figure 10] FIG. 2 is a diagram illustrating an example of a hardware configuration of a character candidate suggestion device. [Figure 11] FIG. 2 is a diagram illustrating an example of an overall processing flow of handwriting recognition. [Figure 12] FIG. 13 is a diagram illustrating an example of a flow of a first name category matching process. [Figure 13] FIG. 13 is a diagram illustrating an example of the flow of a candidate character receiving process. [Figure 14] FIG. 11 is a diagram illustrating an example of a flow of a similar character registration process. [Figure 15] FIG. 13 is a diagram showing an example of a candidate presentation screen. [Figure 16] FIG. 13 is a diagram showing an example of surname candidate presentation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] A handwriting recognition system 1 to which an embodiment according to one aspect of the present invention is applied will be described below with reference to the drawings. In the following embodiment, when necessary for convenience, the description will be divided into a number of sections or embodiments. However, unless otherwise specified, they are not unrelated to each other, and one is a partial or complete modification, detail, supplementary explanation, etc. of the other.

[0020] In addition, in the following embodiments, when referring to the number of elements (including the number, numerical values, quantities, ranges, etc.), unless specifically stated or clearly limited to a specific number in principle, the number is not limited to that specific number and may be more than or less than a specific number.

[0021] Furthermore, in the following embodiments, the components (including element steps, etc.) are not necessarily essential unless specifically stated otherwise or considered to be clearly essential in principle.

[0022] Similarly, in the following embodiments, when referring to the shapes, positional relationships, etc. of components, etc., unless otherwise specified or considered to be obviously different in principle, it includes those that are substantially similar or similar to the shapes, etc. The same applies to the above numerical values ​​and ranges.

[0023] In addition, in all the drawings for explaining the embodiments, the same members are generally given the same reference numerals, and repeated explanations thereof will be omitted.

[0024] 1 is a block diagram illustrating an example of an overview of a handwriting identification system according to the present embodiment. A user uses a business terminal 200 to connect to a character candidate suggestion device 100 via a browser or the like to use the handwriting identification system 1, but this is not limited thereto, and each function of the character candidate suggestion device 100 may be installed in the business terminal 200 as application software.

[0025] When connecting from business terminal 200 to character candidate suggestion device 100, the connection is made via network 50, which is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, a mobile phone network, or a combination of these. The network may be a VPN (Virtual Private Network) on a wireless communication network such as a mobile phone communication network.

[0026] Examples of applications of the handwriting identification system 1 include business systems that involve handling specified documents (e.g., insurance applications, bank account opening applications, etc., where names are entered by hand according to a specified format).

[0027] In such cases, users are expected to handwrite their name in the designated field on the designated document; however, in order to process large volumes of documents, it is more efficient to process large volumes of information through computer processing, so handwritten notations such as names are generally digitized using OCR (Optical Character Recognition).

[0028] Here, although the technology for digitizing character data of paper documents has improved, misreading and non-reading occur at a certain rate, and there is no technology that can completely recognize all handwritten characters. Therefore, ultimately, visual confirmation of character matching by humans is performed, but this visual work is one of the factors that hinders the reduction of the cost of digitizing document character data. Specifically, when a name is read, a mechanism is incorporated to improve the character recognition rate by comparing it with a database related to the name such as surname and given name. However, there are also characters that are difficult to read and confusing characters, and the cost of visually confirming whether misreading has occurred still remains.

[0029] That is, when the read characters include misreading, for example, if the correct surname "Kawamoto" is misread as "Kogi" by a character recognition engine such as OCR, in order to perform collation with each database for the incorrect "Kogi", the ranking of the candidate for the correct "Kawamoto" may be inferior or there may be a candidate leakage.

[0030] Also, when using a format in which the surname and given name are entered as a full name without clearly separating the entry fields for the surname part and the given name part, if the correct surname is not identified, there may be cases where the occurrence of misreading is not even noticed. For example, if the "田" in the full name "Oyamadashin" (おやまだしん) is misread as "由", the surname may be recognized as "小山" (こやま), and names starting with "由" such as "由伸" (よしのぶ) may be candidates.

[0031] In view of these, the present application, on the premise that the characters read by a character recognition engine such as OCR are incorrect, in addition to collating with a DB related to the surname and given name, collates with similar characters that record information on characters that were frequently misread by a character recognition engine such as OCR in the past. As a result, the range of candidates for the read characters including characters prone to misreading is appropriately widened, characters that may be inferior or have candidate leakage are also included as candidates, and after performing the discrimination process between the surname and the given name, the candidate characters are selected. Also, it is assumed that this similar character can always accumulate new similar character information through the visual confirmation work of the character, aiming to improve the accuracy of character recognition.

[0032] The business terminal 200 according to this embodiment is a terminal used for the business of digitizing such a prescribed document. The reading device 300 is a scanner, an imaging device, or the like, and reads the prescribed document as an image or the like in response to an instruction from the business terminal 200, and transfers the read handwritten image to the business terminal 200.

[0033] In this business, when business terminal 200 receives a handwritten character image, it digitizes it by OCR and converts it into character string information, transmits the converted character string to character candidate suggestion device 100, and receives candidate characters proposed by character candidate suggestion device 100. Then, business terminal 200 selectively displays candidate characters, and uses the candidate characters selected by the user as digitized information.

[0034] In addition, the reading device 300 is not limited to a scanner, but may be a device capable of reading images as data, such as a mobile phone terminal with a camera or a tablet terminal with a camera, and may be configured to be communicatively connected to the business terminal 200 via the network 50.

[0035] In addition, reading device 300 is not a required device, and character candidate suggestion device 100 or business terminal 200 may receive image data that has already been read or data that has undergone character recognition from other devices via network 50 and suggest character candidates.

[0036] 2 is a diagram showing an example of the configuration of a handwritten character identification system. In character candidate suggestion device 100, storage unit 110, processing unit 120, and communication unit 130 are communicatively connected to one another via a bus or the like.

[0037] The storage unit 110 includes a received data storage unit 111, an existing character storage unit 112, a similar character storage unit 115, and a candidate character storage unit 116. The existing character storage unit 112 stores character strings such as existing personal names and proper nouns. For example, the existing character storage unit 112 includes a surname storage unit 113 and a given name storage unit 114. For example, it is said that there are more than 300,000 different Japanese surnames, and surnames whose existence has been confirmed are stored in the surname storage unit 113.

[0038] FIG. 3 is a diagram showing an example of a data structure of the received data storage unit. The received data storage unit 111 includes an acceptance date 111A, a requesting company ID 111B, a document number 111C, a character identification number 111D, and a recognized character code 111E. The acceptance date 111A is information for identifying the date on which a request for character candidate proposal was accepted from the business terminal 200. The requesting company ID 111B is information for identifying the company that requested the character candidate proposal. The document number 111C is information for identifying the document (image data of the document) for which the request for character candidate proposal was made. The character identification number 111D is information for identifying each character included in the document to be recognized. The recognized character code 111E is a character code of a character obtained as a result of recognizing each character from its appearance.

[0039] 4 is a diagram showing an example of a data structure of the surname storage unit. The surname storage unit 113 includes a surname identifier 113A, a surname 113B, a character count 113C, and an occurrence frequency 113D. The surname identifier 113A is information for distinguishing a surname from other surnames. The surname 113B is written information of the surname. The character count 113C is the number of characters in the written form of the surname. The occurrence frequency 113D is the occurrence frequency within the entire surname.

[0040] 5 is a diagram showing an example of the data structure of the name storage unit. The name storage unit 114 includes a name identifier 114A, a name 114B, a character count 114C, and an occurrence frequency 114D. The name identifier 114A is information for distinguishing a name from other names. The name 114B is information on the writing of the name. The character count 114C is the number of characters in the writing of the name. The occurrence frequency 114D is the frequency of occurrence within the entire name.

[0041] 6 is a diagram showing an example of a data structure of the similar character storage unit. The similar character storage unit 115 includes a character code 115A, a similar character code 115B, an occurrence frequency 115C, and a storage date 115D. The character code 115A is a code of a reference character among characters that are similar to each other. The similar character code 115B is a code of a character that is similar in appearance to the character identified by the character code 115A. The occurrence frequency 115C is a frequency at which the character appears as a similar character in use. The storage date 115D is information that identifies the date on which the character was stored as a similar character.

[0042] 7 is a diagram showing an example of a data structure of the candidate character storage unit. Candidate character storage unit 116 includes character identification number 116A and candidate character code 116B. Character identification number 116A is information for identifying individual characters included in a document to be recognized. Candidate character code 116B is a character candidate different from a character recognized by OCR, and is a code for a similar and actually existing character.

[0043] The processing unit 120 includes an acceptance processing unit 121 , a name discrimination processing unit 122 , a matching processing unit 123 , a similar character registration processing unit 124 , and a candidate character transmission processing unit 125 .

[0044] The acceptance processing unit 121 accepts a request for proposal of character candidates from the business terminal 200. When the name discrimination processing unit 122 receives a proposal of character candidates of a plurality of character strings, it specifies a combination of a family name and a given name, which is divided by changing the division position of the family name one character at a time, and judges whether it is valid as a family name. The matching processing unit 123 checks against the existing character storage unit 112 to judge whether it is an existing character candidate. The similar character registration processing unit 124 registers the characters reported from the business terminal 200 as unregistered similar relations in the similar character storage unit 115. The candidate character transmission processing unit 125 outputs the combination of candidates of characters that are similar in appearance, which is hit as a result of the matching by the matching processing unit 123, as candidate characters. Specifically, the candidate character transmission processing unit 125 realizes the idea by outputting (transmitting) the candidates stored in the candidate character storage unit 116 to the business terminal 200. The communication unit 130 communicates with other devices via the network 50.

[0045] The business terminal 200 includes a storage unit 210, a processing unit 220, and a communication unit 230, which are communicatively connected to one another via a bus or the like.

[0046] The storage unit 210 includes a character storage unit 211 , a candidate character storage unit 212 , and an image storage unit 213 .

[0047] 8 is a diagram showing an example of the data structure of the character storage unit 211. The character storage unit 211 includes an image data number 211A, a read date 211B, a character identification number 211C, and an image 211D.

[0048] Image data number 211A is information that identifies an image of a character string read by reading device 300. Reading date 211B is information that identifies the date when reading device 300 read a document. Character identification number 211C is information that identifies individual characters included in the document to be recognized. Image 211D is information that identifies image data of a single character identified by character identification number 211C (part of an image read by reading device 300).

[0049] 9 is a diagram showing an example of the data structure of the image storage unit 213. The image storage unit 213 includes an image data number 213A, a document number 213B, a read date 213C, and an image 213D.

[0050] Image data number 213A is information that identifies an image of a character string read by reading device 300. Document number 213B is information that identifies a document (document image data) for which a request for character candidate proposal was made. Reading date 213C is information that identifies the date on which reading device 300 read a document. Image 213D is information that identifies an image read by reading device 300.

[0051] The processing unit 220 includes a character recognition unit 221, a commission processing unit 222, a visual confirmation processing unit 223, and a similar character report processing unit 224. The character recognition unit 221 is a so-called OCR engine, and analyzes a handwritten character image acquired from the reading device 300 to recognize characters.

[0052] In order to eliminate rework or procedural errors caused by misreading by the character recognition unit 221, the commission processing unit 222 commissions the character candidate suggestion device 100 to propose candidate characters with high accuracy.

[0053] Visual confirmation processing unit 223 selectively displays each of the character candidates output from character candidate proposing device 100 so that the candidate can be visually confirmed, and accepts a selection of any of the candidates from the user.

[0054] Similar character report processor 224 accepts input of characters that the user recognizes as similar characters, and reports to character candidate suggesting device 100 to register the characters as similar characters.

[0055] The communication unit 230 communicates with other devices via the network 50 .

[0056] In addition, the business terminal 200 includes an input unit (not shown) that accepts input from a user, and an output unit that outputs various output information such as a screen, a form, etc. For example, the input unit accepts various inputs such as various contact inputs such as typing, touching, and flick input, or voice input, or gaze input.

[0057] 10 is a diagram showing an example of a hardware configuration of character candidate suggestion device 100. Character candidate suggestion device 100 has a hardware configuration realized by the housing of a so-called server device, a workstation, a personal computer, a smartphone, or a tablet terminal. Character candidate suggestion device 100 has a calculation device 101, a main memory device 102, an auxiliary memory device 103, a communication device 104, and a bus 107 connecting each device. The same is true for business terminal 200. In addition, business terminal 200 has input / output devices such as a touch panel, a keyboard, a microphone, and a display.

[0058] The arithmetic device 101 is, for example, a arithmetic device such as a CPU (Central Processing Unit).

[0059] The main storage device 102 is a memory device such as a RAM (Random Access Memory).

[0060] The auxiliary storage device 103 is a non-volatile storage device capable of storing digital information, such as a so-called hard disk drive, a solid state drive (SSD), or a flash memory.

[0061] The communication device 104 may be a wired communication device such as a network card, or a wireless communication device.

[0062] The above-mentioned entrustment processing unit 121, name discrimination processing unit 122, matching processing unit 123, similar character registration processing unit 124, and candidate character transmission processing unit 125 of character candidate suggestion device 100 are realized by a program that causes arithmetic device 101 to perform processing. This program is stored in main memory device 102, auxiliary memory device 103, or a ROM device (not shown), and is loaded onto main memory device 102 for execution and executed by arithmetic device 101.

[0063] Moreover, storage unit 110 of character candidate proposing device 100 is realized by main storage device 102 and auxiliary storage device 103. Moreover, communication unit 130 is realized by communication device 104. An example of the hardware configuration of character candidate proposing device 100 has been described above.

[0064] The configuration of character candidate proposing device 100 can be further divided into more components according to the processing content, or can be divided so that one component executes more processes.

[0065] In addition, each processing unit (the acceptance processing unit 121, the name discrimination processing unit 122, the matching processing unit 123, the similar character registration processing unit 124, and the candidate character transmission processing unit 125) may be constructed with dedicated hardware (ASIC, GPU, etc.) that realizes each function. In addition, the processing of each processing unit may be executed by one piece of hardware or by multiple pieces of hardware.

[0066] Next, the operation of the handwriting recognition system 1 in this embodiment will be described.

[0067] 11 is a diagram showing an example of the overall process flow of handwriting recognition. The handwriting recognition process is started when a user issues an instruction to start the process from the business terminal 200.

[0068] First, the business terminal 200 requests the reading device 300 to read image data of a document (step S10). Specifically, the character recognition unit 221 instructs the reading device 300 to start scanning or photographing.

[0069] Upon receiving a request from the business terminal 200, the reading device 300 reads the image of the document, creates image data, and sends the image data to the business terminal 200 (step S11).

[0070] The character recognition unit 221 of the business terminal 200 receives the image data from the reading device 300, stores it in the image storage unit 213, and executes character recognition processing with the OCR engine (step S12). Then, the recognized character data is stored in the character storage unit 211 (step S13). Note that this OCR engine may be implemented in a PC terminal, a server terminal, or the like, that is placed on a network to which the business terminal 200 can be connected, and may be configured to execute character recognition processing in response to an instruction from the business terminal 200.

[0071] Then, in business terminal 200, commission processing unit 222 transmits the recognized characters to character candidate proposing device 100, and commissions the process of proposing character candidates (step S14).

[0072] Then, request processing unit 121 of character candidate proposing device 100 receives the recognized characters from business terminal 200 and stores them in received data storage unit 111 (step S15).

[0073] Then, the matching processor 123 matches the received character data with the existing character storage unit 112 and the similar character storage unit 115 (step S16).

[0074] Then, matching processor 123 selects candidate characters and stores them in candidate character storage unit 116 (step S17).

[0075] Then, candidate character transmission processor 125 transmits the candidate characters to business terminal 200 (step S18).

[0076] Entrustment processing unit 222 of business terminal 200 receives the candidate characters and stores them in candidate character storage unit 212 (step S19).

[0077] Then, the visual confirmation processing unit 223 outputs a screen for comparing the candidate characters with the image in the image storage unit (step S20). More specifically, for example, the screen displays the handwritten character image read by the reading device 300 and a plurality of candidate characters for selection and input.

[0078] When an instruction to register a similar character is accepted from a user, similar character report processor 224 accepts an input if there is a single similar character other than the candidate character, and responds to character candidate suggesting device 100 (step S21).

[0079] Similar character registration processing unit 124 of character candidate proposing device 100 receives the similar characters, and stores them in similar character storage unit 115 if they have not been stored therein yet (step S22).

[0080] The above is an example of the overall process flow of handwriting recognition. According to the overall process of handwriting recognition, it is possible to more appropriately suggest similar character string candidates.

[0081] 12 is a diagram showing an example of the flow of the first name segment matching process. The first name segment matching process is an example of a process in which the processes of steps S16 to S18 in the overall process flow of handwriting recognition are performed as a series.

[0082] First, the name discrimination processing unit 122 identifies the total number of characters n (step S1601). For example, when the name "Koyamada Shin" is the target string for candidate presentation, the name discrimination processing unit 122 identifies the total number of characters n as "4" with each Chinese character of "Koyamaada Shin" being counted as one character.

[0083] Then, the name discrimination processing unit 122 decomposes the first d (d is 1 or more and less than n, initial value 1) characters as the surname and the remaining characters as the given name (step S1602).

[0084] The matching processing unit 123 decomposes the characters constituting the surname one by one and matches them with the similar character storage unit 115, and then matches the combinations of similar characters with the existing surname storage unit 113 to select existing surname candidates (step S1603).

[0085] Then, the name discrimination processing unit 122 determines whether there is no surname candidate corresponding to the similar character storage unit 115 (step S1604). If there is no surname candidate (in the case of "Yes" in step S1604), the name discrimination processing unit 122 proceeds to step S1611 described later for control.

[0086] If there is a surname candidate (in the case of "No" in step S1604), the name discrimination processing unit 122 determines whether there is at least one corresponding name in the existing surname storage unit 113 for the surname candidate (step S1605). If there is no corresponding name in the existing surname storage unit 113 (in the case of "No" in step S1605), the name discrimination processing unit 122 proceeds to step S1611 described later for control.

[0087] If there is a surname in the existing surname storage unit 113 corresponding to the surname candidate (in the case of "Yes" in step S1605), the name discrimination processing unit 122 temporarily stores all the selected surname candidates (step S1606).

[0088] Then, the matching processing unit 123 breaks down the characters constituting the name character by character and matches them with the similar character storage unit 115, and matches combinations of similar characters with the name storage unit 114 to select existing name candidates (step S1607).

[0089] Then, the name discrimination processing unit 122 determines whether there is no matching name candidate in the similar character storage unit 115 (step S1608). If there is no matching name candidate ("Yes" in step S1608), the name discrimination processing unit 122 advances control to step S1611, which will be described later.

[0090] If there is a name candidate (step S1608: No), the name discrimination processing unit 122 determines whether or not there is at least one corresponding name candidate in the name storage unit 114 (step S1609). If there is no corresponding name candidate in the name storage unit 114 (step S1609: No), the name discrimination processing unit 122 advances control to step S1611 described below.

[0091] If there is a corresponding name in the name candidates in the name storage unit 114 ("Yes" in step S1609), the name discrimination processing unit 122 temporarily stores all the selected name candidates (step S1610).

[0092] Then, the name discrimination processing unit 122 increments (+1) the number of characters d of the family name (step S1611).

[0093] Then, the name discrimination processing unit 122 determines whether the number of characters d of the family name matches the total number of characters n (step S1612). If they do not match ("No" in step S1612), the name discrimination processing unit 122 returns control to step S1602.

[0094] When the number of characters d in the surname matches the total number of characters n (i.e., "Yes" in step S1612), the surname discrimination processing unit 122 determines whether there is a set of temporarily stored surname candidates and given name candidates (where the sum of the surname length and the given name length matches the total number of characters n), that is, whether there is a hit combination of surnames and given names as a result (step S1613).

[0095] If there is no set of temporarily stored surname candidates and given name candidates (where the sum of the surname length and the given name length matches the total number of characters n) (i.e., "No" in step S1613), the candidate character transmission processing unit 125 notifies the business terminal 200 that discrimination is impossible (step S1614).

[0096] If there is a set of temporarily stored surname candidates and given name candidates (where the sum of the surname length and the given name length matches the total number of characters n) (i.e., "Yes" in step S1613), the candidate character transmission processing unit 125 transmits the character candidates to the business terminal 200 (step S1801). At this time, the candidate character transmission processing unit 125 sorts and transmits each set of temporarily stored surname candidates and given name candidates according to the order of the appearance frequencies. That is, the candidate character transmission processing unit 125 transmits the surname candidates and given name candidates composed of characters with higher appearance frequencies first.

[0097] The above is an example of the flow of the surname and given name discrimination and matching process. According to the surname and given name discrimination and matching process, for a surname consisting of one or more characters, the discrimination position of the surname and given name can be changed, and each similar character can be fitted to identify the existing candidates. For example, in the case of the surname "Koyamada Shin" above, "田" and "由" are similar characters, and candidate characters including the candidate of taking the two-character surname "小山" and the remaining given name "由伸", and the candidate of taking the three-character surname "小山田" and the remaining given name "伸", can be identified.

[0098] FIG. 13 is a diagram showing an example of the flow of the candidate character reception process. The candidate character reception process is an example of a process that performs the processes of steps S19 to S21 in the overall process flow of handwritten character recognition as a series.

[0099] First, the entrustment processing unit 222 stores the received candidate characters in the candidate character storage unit 212 (step S191).

[0100] Then, the visual confirmation processing unit 223 displays the candidate characters and the handwritten character image for confirmation (step S201). An example of the screen for this confirmation display will be described later.

[0101] Then, the visual confirmation processor 223 accepts the selection input of the candidate characters (step S202), thereby finalizing the digitization of the handwritten characters.

[0102] In addition, the similar character report processor 224 determines whether or not a new similar character has been input (step S211). If no new similar character has been input (step S211: No), the similar character report processor 224 ends the candidate character receiving process.

[0103] If a new similar character is input ("Yes" in step S211), similar character report processor 224 transmits information on the new similar character to character candidate proposing device 100 (step S212).

[0104] The above is an example of the flow of the candidate character receiving process. According to the candidate character receiving process, it is possible to receive candidate characters from the character candidate suggesting device 100 and select and input the candidate while comparing it with the handwritten character. Also, when a similar character is noticed, it is possible to report it to the character candidate suggesting device 100 and request that it be newly registered as a similar character.

[0105] 14 is a diagram showing an example of a flow of similar character registration processing. The similar character registration processing is started by character candidate suggesting device 100 when information that becomes a similar character in the candidate character receiving processing is transmitted from business terminal 200 to character candidate suggesting device 100.

[0106] First, the similar character registration processing unit 124 determines whether the received similar character information has already been stored in the similar character storage unit 115 (step S2201).

[0107] If the received similar character information is not already stored in the similar character storage unit 115 ("No" in step S2201), the similar character registration processing unit 124 identifies one-to-one combinations of similar characters (breaks down characters that have a similar relationship into one-to-one combinations) (step S2202).

[0108] Then, similar character registration processing unit 124 stores both of the mutually similar characters as being similar to each other in similar character storage unit 115 (step S2203).

[0109] If the received similar character information has already been stored in similar character storage unit 115 (step S2201: Yes), similar character registration processing unit 124 notifies business terminal 200 that the information has been registered (step S2204).

[0110] Then, the similar character registration processing unit 124 increases the appearance frequency of each of the mutually similar characters by a predetermined amount (step S2205).

[0111] The above is an example of the flow of the similar character registration process. According to the similar character registration process, if the similar characters requested to be registered from the business terminal 200 are new, they are registered as similar, and if they have already been registered, their frequency of appearance can be increased.

[0112] FIG. 15 is a diagram showing an example of a candidate presentation screen. Candidate presentation screen 400 is a screen output in step S20 of the handwriting recognition overall processing flow and in step S201 of the candidate character reception processing. Original data to be visually confirmed (handwritten character image read by reading device 300) is displayed in original data display area 401, and candidate characters to be visually confirmed are displayed in surname candidate display area 402 and given name candidate display area 403. Candidate characters proposed by character candidate suggestion device 100 as candidates with the highest occurrence rate are displayed in surname candidate display area 402 and given name candidate display area 403. Last name candidate decision button 404, upon receiving an input, confirms the last name displayed in surname candidate display area 402. First name candidate decision button 405, upon receiving an input, confirms the first name displayed in first name candidate display area 403.

[0113] Candidate characters from the next candidate onwards are arranged in order of appearance frequency and displayed in a selectable list in a surname next candidate display area 406 and a given name next candidate display area 407. The surname next candidate display area 406 and the given name next candidate display area 407 accept the selection of listed characters. When input is accepted, the surname next candidate confirm button 408 confirms the surname selected in the surname next candidate display area 406. When input is accepted, the given name next candidate confirm button 409 confirms the name selected in the given name next candidate display area 407.

[0114] Similar character registration area 410 and similar character registration area 411 each accept character input. When registration button 412 accepts input, it accepts the characters input in similar character registration area 410 and similar character registration area 411 as characters having a similar relationship, and starts a registration process in character candidate suggesting device 100. That is, when a character is found as a result of visual confirmation that the visual operator (user) feels the need to register as a new similar character, the character can be registered by inputting the character in similar character registration area 410 and similar character registration area 411 and selecting registration button 412. Furthermore, when input to back button 413 or next screen button 414 is accepted as necessary, a transition to the previous or next business screen is made.

[0115] Fig. 16 is a diagram showing an example of surname candidate presentation. In the handwriting identification system 1 to which this embodiment is applied, even if the reading device 300 and the character recognition unit 221 misread, the presented candidates are highly likely to include the correct character, and this is specifically shown.

[0116] If a character recognition engine such as OCR misreads the correct surname "Kawamoto" (a) as "Ogi" (b), when comparing the misread "Ogi" (b) with existing surnames, the correct character candidate "Kawamoto" (a) may be ranked lower or a candidate may be missed.

[0117] The misreading "Oki" (b) is broken down into "O" (c) and "Ki" (d), which are then compared with the similar character storage unit 115 to identify similar characters in order of frequency of occurrence (e, f). Next, a family name formed by combining characters with high frequency of occurrence is compared with the family name storage unit 113 to select and sort candidate characters (g). As a result, even if a misreading occurs, by performing comparison with the similar character storage unit 115, it is possible to avoid the subordination of the correct answer "Kawamoto" (a) or the omission of candidates, and to expect an improvement in the character recognition rate.

[0118] The above is an example of a handwriting recognition system according to an embodiment. According to the example of the handwriting recognition system according to the embodiment, similar character string candidates can be more appropriately proposed for an image in which handwriting has been read, so that a user can smoothly perform a handwriting reading task by simply selecting from the presented candidates.

[0119] In addition, in the above embodiment, a name was used as an example of the subject of handwritten characters, but this is not limited to this, and by replacing the real character storage unit 112 to be compared, it is possible to apply this to any other character data, such as an address.

[0120] Furthermore, the technical elements of the above-described embodiments may be applied independently, or may be divided into a plurality of parts, such as program parts and hardware parts, and then applied.

[0121] The present invention has been described above mainly with reference to the embodiment. [Explanation of symbols]

[0122] 1 Handwritten character identification system, 50 Network, 100 Character candidate suggestion device, 110 Memory unit, 111 Received data memory unit, 112 Existing character memory unit, 113 Family name memory unit, 114 First name memory unit, 115 Similar character memory unit, 116 Candidate character memory unit, 120 Processing unit, 121 Accepted processing unit, 122 Family name discrimination processing unit, 123 Matching processing unit, 12 4···Similar character registration processing unit, 125···Candidate character transmission processing unit, 130···Communication unit, 200···Business terminal, 210···Memory unit, 211···Character memory unit, 212···Candidate character memory unit, 213···Image memory unit, 220···Processing unit, 221···Character recognition unit, 222···Commission processing unit, 223···Visual confirmation processing unit, 224···Similar character report processing unit, 230···Communication unit, 300···Reading device.

Claims

1. A method for identifying a person who exists in a computer system, comprising: a processing unit; and an existing character storage unit for storing a character string of an existing person's name; The processing unit includes: a character recognition step of acquiring handwritten characters and performing character recognition; an output step of identifying character candidates having a similar appearance to the characters recognized by the character recognition step, and outputting the combinations of the character candidates having the similar appearance, which are hit as a result of matching with the existing character string stored in the existing character storage unit, as candidate characters for a person's name, in order of frequency of occurrence for each of the candidates; A character identification system comprising:

2. 2. The character identification system of claim 1, The character string of the name of an existing person is divided into a surname and a given name, The processing unit performs the matching by classifying the characters recognized in the character recognition step into a surname and a given name. A character recognition system comprising:

3. 2. The character identification system of claim 1, The processing unit specifies a combination of a surname and a given name by changing a position separating the surname and the given name for the characters recognized by the character recognition step, and when a hit is obtained as a result of the matching for both the surname and the given name for each combination, the combination is set as the candidate character. A character recognition system comprising:

4. A character recognition method using a computer, comprising: The computer includes: a processing unit and an existing character storage unit for storing character strings of existing person names, The processing unit includes: a character recognition step of acquiring handwritten characters and performing character recognition; an output step of identifying character candidates having a similar appearance to the characters recognized by the character recognition step, and outputting the combinations of the character candidates having the similar appearance, which are hit as a result of matching with the existing character string stored in the existing character storage unit, as candidate characters for a person's name, in order of frequency of occurrence for each of the candidates; A character identification method comprising:

5. A program for causing a computer to perform a process for assisting in the identification of handwritten characters, comprising: The computer includes: The system includes an existing character storage unit that stores character strings of existing personal names, and a processing unit, The processing unit includes: a character recognition step of acquiring handwritten characters and performing character recognition; an output step of identifying character candidates having a similar appearance to the characters recognized by the character recognition step, and outputting the combinations of the character candidates having the similar appearance, which are hit as a result of matching with the existing character string stored in the existing character storage unit, as candidate characters for a person's name, in order of frequency of occurrence for each of the candidates; A program for causing the user to carry out the above steps.

Images