JP5942661B2 - Information processing apparatus and information processing program - Google Patents

Description

  The present invention relates to an information processing apparatus and an information processing program.

  Patent Document 1 aims to provide a word reading method that correctly reads a word character string written at an indefinite pitch without causing a significant increase in character recognition processing time. Character pattern rectangle generation that generates a sequence of one or more character pattern rectangles in which the total number of rectangles is within the range of the number of characters of the word to be read by combining these rectangles with a pattern cutout unit that extracts rectangles surrounding the pattern A character recognition means for outputting a candidate character string by comparing the arrangement of character pattern rectangles with a standard character pattern prepared in advance, and outputting a candidate word by comparing the candidate character string with a word dictionary prepared in advance. And a word search means.

  Japanese Patent Laid-Open No. 2004-228561 is intended to read a character or the like recorded on a sheet for the purpose of enabling a detailed specification by using a regular expression for specifying a character type of format control information and improving a recognition rate. For storing the format control information referred to in the format control information section in which the information specifying the character type in the format control information is represented by a regular expression, and the format stored in the format control information section A regular expression analysis unit that analyzes a regular expression in control information, a character type control unit that selects a dictionary to be used in a recognition dictionary based on an analysis result by the regular expression analysis unit, and a dictionary selected by the character type control unit It is disclosed that a collation unit that collates with a pattern of characters or the like recorded on a sheet using the above and obtains a reading result is disclosed.

  In Patent Document 3, it is an object to provide a method for correcting a character recognition result that is easy to expand and maintain the correction rules necessary for correcting the character recognition result and does not cause a correction error. Candidate character strings that are character recognition results are arranged from the first to the nth place to form a candidate character matrix, and this matrix is passed to the regular expression matching unit. The matching unit is adapted to various character string description formats. A modification rule file that stores various modification rules is stored outside the program, a modification rule that can be applied to the input matrix is selected from the file, and a candidate character string that best matches the selected modification rule is matrixed. Then, the character string replacement unit replaces the character string in the candidate character string with a more correct character string according to the selected correction rule. , Then character substitution portion, replacing the individual characters of the string substituted in the candidate character strings to a more correct character is disclosed.

JP-A-01-281586 Japanese Patent Application Laid-Open No. 06-036069 JP 09-138836 A

  In the present invention, when determining whether or not the target character string matches the type of the character string described in the regular expression, compared to the case where the present character string is not included, the present invention is faster. An object of the present invention is to provide an information processing apparatus and an information processing program that perform determination processing.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The invention according to claim 1 is a first accepting means for accepting a target character string, and a second accepting means for accepting a character string type described in a regular expression and a portion that is a set of character strings in the type. A first determination unit that determines whether or not the character string received by the first reception unit matches a character string in the set received by the second reception unit; Second determination means for determining whether or not the character string received by the reception means matches a type described by a regular expression other than the character string in the set received by the second reception means; The character string accepted by the first accepting means is converted into the character string accepted by the second accepting means using the judgment result by the first judging means and the judgment result by the second judging means. Conform to the mold And third determination means for determining dolphin not, a network generation means for generating a network by each of the characters of the plurality of character recognition results as nodes, to construct the links between nodes of adjacent character images, the Limiting means for limiting a link connected to a node in the network generated by the network generating means from either the first direction or the last direction to a link that matches a predetermined character string pattern; and Storage means for storing the determination result by the third determination means in the node, and output means for outputting the character candidate string in the path connected by the link limited by the limiting means as a character recognition result , The limiting unit is configured to limit the link if the determination result in the storage unit does not match. An information processing apparatus characterized by not performed whether processing the character string pattern are consistent.

The invention of claim 2 is received by the first receiving means for receiving the target character string, the second receiving means for receiving the character string type described in the regular expression, and the second receiving means. Extraction means for extracting a portion that is a set of character strings from a character string type, and whether or not the character string received by the first reception means matches the character string extracted by the extraction means A first determination unit that determines whether the character string received by the first reception unit matches a type described by a regular expression other than the character string extracted by the extraction unit. The character string received by the first receiving means is received by the second receiving means using the determination result of the second determining means, the determination result by the first determining means, and the determination result by the second determining means. Third determining means for determining whether or not matching the type of Tagged string, that each of the characters of the plurality of character recognition results as nodes, to construct the links between nodes of adjacent character images Network generation means for generating a network by the above, and a predetermined character string pattern for a link connected to a node in the network generated by the network generation means from either the first direction or the last direction. Character recognition for a character candidate string in a path connected by a link limited by a limiting unit that limits to a matching link, a storage unit that stores a determination result by the third determination unit in the node, and a link limited by the limiting unit comprising output means for outputting as a result, the limitation means, in the case to limit the link, the determination result in said storage means An information processing apparatus characterized by not performed whether processing said are consistent with a predetermined string pattern if matched.

  According to a third aspect of the present invention, the first determining means determines whether or not a portion continuous from the beginning of the character string received by the first receiving means matches the character string extracted by the extracting means. The information processing apparatus according to claim 1, wherein the information processing apparatus is configured to determine whether or not

According to a fourth aspect of the present invention, there is provided a first receiving means for receiving a target character string, and a second receiving portion that is a character string type described in a regular expression and a set of character strings in the type. A first determination unit that determines whether or not the character string received by the first reception unit matches a character string in the set received by the second reception unit; A second determining unit that determines whether the character string received by the first receiving unit matches a type described by a regular expression other than the character string in the set received by the second receiving unit; The character string accepted by the first accepting means is accepted by the second accepting means using the judging means, the judgment result by the first judging means and the judgment result by the second judging means. Sentence Generate a network by building a third determining means for determining whether or not matching the type of column, each of the characters of the plurality of character recognition results as nodes, the links between nodes of adjacent character images And a link that matches a predetermined character string pattern with respect to a link that connects to a node in the network generated by the network generation unit from either the first direction or the last direction. Limiting means for limiting, storage means for storing the determination result by the third determining means in the node, and a character candidate string in the path connected by the link limited by the limiting means is output as a character recognition result to function as an output unit, said limitation means, in the case of limiting the link, the determination result in said storage means in disagreement An information processing program, characterized in that said not performed whether processing is consistent with a predetermined string pattern if Re.

According to a fifth aspect of the present invention, there is provided a computer comprising: a first receiving unit that receives a target character string; a second receiving unit that receives a character string type described in a regular expression; and the second receiving unit. Extraction means for extracting a portion that is a set of character strings from the accepted character string type, and whether the character string accepted by the first acceptance means matches the character string extracted by the extraction means A first determination means for determining whether or not the character string received by the first reception means matches a type described in a regular expression other than the character string extracted by the extraction means. The character string accepted by the first accepting means is converted into the second accepting means using the second judging means for judging, the judgment result by the first judging means and the judgment result by the second judging means. Construction and third determining means for determining whether or not matching the type of the character string received by means of each of the characters of the plurality of character recognition results as nodes, the links between nodes of adjacent character images Network generating means for generating a network by performing a predetermined character string for a link connected to a node in the network generated by the network generating means from either the first direction or the last direction. Limiting means for limiting to links that match the pattern, storage means for storing the determination result by the third determination means in the node, and character candidate strings in the path connected by the links limited by the limiting means to function as an output unit for outputting as a character recognition result, the limitation means, in the case to limit the link, the憶determination result in means is an information processing program characterized by not performing the whether is consistent with a predetermined string pattern processing if disagreement.

According to the information processing apparatus of claim 1, when it is determined whether or not the target character string matches the type of the character string described in the regular expression, and does not have this configuration Compared to the above, the determination process can be performed at high speed. In addition, when a character recognition result is selected and output from a plurality of character recognition result candidates, the character recognition result can be output at a higher speed than when this configuration is not provided.

According to the information processing apparatus of claim 2, when it is determined whether or not the target character string matches the type of the character string described in the regular expression, and does not have this configuration Compared to the above, the determination process can be performed at high speed. In addition, when a character recognition result is selected and output from a plurality of character recognition result candidates, the character recognition result can be output at a higher speed than when this configuration is not provided.

  According to the information processing apparatus of the third aspect, it is also possible to determine whether or not there is a partial match.

According to the information processing program of claim 4 , when determining whether or not the target character string matches the type of the character string described in the regular expression, and does not have this configuration Compared to the above, the determination process can be performed at high speed. In addition, when a character recognition result is selected and output from a plurality of character recognition result candidates, the character recognition result can be output at a higher speed than when this configuration is not provided.

According to the information processing program of claim 5 , when determining whether or not the target character string matches the type of the character string described in the regular expression, and does not have this configuration Compared to the above, the determination process can be performed at high speed. In addition, when a character recognition result is selected and output from a plurality of character recognition result candidates, the character recognition result can be output at a higher speed than when this configuration is not provided.

It is a conceptual module block diagram about the structural example of this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is a conceptual module block diagram about the structural example of this Embodiment. It is explanatory drawing which shows the example of the form made into object. It is explanatory drawing which shows the example of a regular expression description rule. It is explanatory drawing which shows the example of a relationship between a character position and a character candidate. It is explanatory drawing which shows the example of a relationship between a character position and a character candidate. It is a flowchart which shows the process example by this Embodiment. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the process example in case there exist multiple character cutout positions. It is explanatory drawing which shows the example of a symbol. It is explanatory drawing which shows the process example in case there exist multiple character cutout positions. It is explanatory drawing which shows the example of the network which comprises a character string. It is explanatory drawing which shows the example in which the node in the network which comprises a character string is connected. It is explanatory drawing which shows the module structural example in a path | pass limitation processing module. It is a flowchart which shows the process example by a path | pass limitation processing module. It is explanatory drawing which shows the example of a relationship between a character position and a character candidate. It is explanatory drawing which shows the example of the data which a limited character string pattern test | inspection processing module receives and the data to output. It is explanatory drawing which shows the example of the enumeration of a character string. It is explanatory drawing which shows the example which made the character string set the binary tree structure. It is explanatory drawing which shows the example of the data which a limited character string pattern test | inspection processing module receives and the data to output. It is explanatory drawing which shows the example of the data which a limited character string pattern test | inspection processing module receives and the data to output. It is explanatory drawing which shows the example of the data which a limited character string pattern test | inspection processing module receives and the data to output. It is explanatory drawing which shows the example in which the node in the network which comprises a character string is connected. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment. It is explanatory drawing which shows the example of a character string image. It is explanatory drawing which shows the example of a character boundary candidate. It is explanatory drawing which shows the example of a circumscribed rectangle. It is explanatory drawing which shows the example of a character cutout result. It is explanatory drawing which shows the example of the network expression which shows a character cutout position. It is explanatory drawing which shows the example of the pattern in a network expression. It is explanatory drawing which shows the example of a network. It is explanatory drawing which shows the example of a network when there exist a some character candidate.

In this embodiment, a plurality of character strings are targeted, and a character string that matches a character string type described in a regular expression is output from the plurality of character strings. For example, a character recognition result for an image including a character string may be targeted, and a character string that matches a character string type described in a predetermined regular expression is output from the result of character recognition for the image. . More specifically, when character recognition is performed, there are a plurality of character cutout results, and there may also be a plurality of character recognition results for one character image, but a plurality of characters that are combinations of these characters. A correct character string is to be extracted from the sequence as a recognition result.
First, before describing the present embodiment, the premise or an information processing apparatus using the present embodiment will be described. This description is intended to facilitate understanding of the present embodiment.

  For example, a character string image as shown in the example of FIG. 30 is targeted. First, this character string image is divided into character segments. A character segment is a character itself or a character portion that can be a part of a character. Here, a horizontally written character string image as shown in the example of FIG. 30 is taken as an example. In a horizontally written image, the image is divided into character segments by dividing the image with vertical lines (or lines close to vertical). For example, the character string image can be divided by the vertical lines (cut candidate 3110 and cut candidate 3120) shown in FIG. 31 to obtain three character segments “I”, “HI”, and “Study”. The vertical line shown in the example of FIG. 31 is called a break candidate. A break candidate 3110 separates “I” and “HI”, and a break candidate 3120 separates “HI” and “Study”.

Next, as shown in the example of FIG. 32, circumscribed rectangles (circumscribed rectangle 3210, circumscribed rectangle 3220, circumscribed rectangle 3230) are extracted for each character segment.
Hereinafter, the technical content described in Patent Document 2 will be described as an example. Note that the terms used in the following description may be different from the terms used in Patent Document 2. However, the contents are the same as in Patent Document 2.
A character image is determined by integrating the character segments described above. A plurality of character segments may be integrated to form one character image, or one character segment may become one character. Determining the character image is equivalent to determining the character cutout position, and hence may be referred to as the character cutout position determination below.
There are multiple patterns of character segment integration. A final character cutout position is determined by selecting a character image having the highest evaluation from among a plurality of existing patterns.
For the example of FIG. 32, all character cutout patterns are as shown in the example of FIG. That is, in the example of FIG. 33A, three character images (circumscribed rectangle 3210, circumscribed rectangle 3220, circumscribed rectangle 3230) are used as pattern 1, and in the example of FIG. In the example of the rectangles 3210 and 3220 and the circumscribed rectangle 3230) and FIG. 33C, one character image (circumscribed rectangles 3210, 3220, and 3230) is used as the pattern 3, and in the example of FIG. A character image (circumscribed rectangle 3210, circumscribed rectangles 3220 and 3230) is shown.

  A plurality of cutout patterns shown in the example of FIG. 33 can be represented as network expressions (also referred to as graph expressions) indicating character cutout positions. In the example of FIG. 34, the network includes four nodes, a start node 3400, an end node 3490, an intermediate node 3410 (node 1), and an intermediate node 3420 (node 2), and arcs connecting the nodes ( Connection lines between nodes are called arcs). The start point corresponds to the left end of the character string image, and the end point corresponds to the right end of the character string image. Intermediate node 3410 (node 1) and intermediate node 3420 (node 2) respectively indicate character break candidate positions (that is, break candidate 3110 and break candidate 3120 shown in the example of FIG. 31). The intermediate node 3410 (node 1) corresponds to the break candidate 3110. The intermediate node 3420 (node 2) corresponds to the break candidate 3120.

A route from the start point through each node to the end point is hereinafter referred to as a “path”. The path is composed of one or a plurality of arcs. Usually there are multiple paths. The character cutout pattern shown in the example of FIG. 33 corresponds to these multiple paths. For example, the pattern 2 shown in the example of FIG. 33B corresponds to the paths (character cutout pattern 3404 and character cutout pattern 3422) indicated by the thick lines in FIG.
Here, one character image candidate corresponds to any one arc. For example, a character image (character cutout pattern 3404) corresponding to “K” corresponds to an arc connecting the start point node 3400 and the intermediate node 3420 (node 2). For a character corresponding to one arc, an evaluation value of the character can be determined. This is called an “arc evaluation value”.
The arc evaluation value is calculated from character shape information, recognition accuracy in character recognition, and the like. There are various methods for calculating the arc evaluation value. For example, (1) JP-A-9-185681, (2) JP-A-8-161432, (3) JP-A-10-154207, (4) JP-A-61-175878, (5) There are methods shown in the prior art described in JP-A-3-37782, (6) JP-A-11-203406, and the like.

One path is composed of a plurality of arcs. Using a plurality of arc evaluation values, an evaluation value of a path constituted by the arcs can be calculated. This is called a “path evaluation value”.
In order to determine the character cutout position, the path with the highest path evaluation value is selected from the plurality of paths. If the path can be selected, the character cutout position is fixed and the character can be cut out. Then, the result of character recognition of the cut out character (character image) is also confirmed.
For example, assume that a thick line path is selected in the example of FIG. In this case, the character cutout positions are three points: a start point 3400, an intermediate node 3420 (node 2), and an end point 3490. Then, the confirmed character recognition results are “B” (character cutout pattern 3404) and “Study” (character cutout pattern 3422).

パスの数が複数存在すると前述したが、実際の文字列には、多くの文字セグメントが存在しているため、存在するパスの数は膨大となる。
そこで、特開平３−２２５５７９号公報に記載の技術では、図３４の例に示されたようなネットワーク内の複数のパスから最も評価値の高いパスを探索する方法として、ダイナミックプログラミング手法を用いることが述べられている。
ここでは、ダイナミックプログラミング手法の中で、このようなネットワークの最良パスを探索するのに適したビタビ法の説明を行う。 Here, a method for calculating the path evaluation value will be described. Basically, a weighted sum of arc evaluation values is used as the path evaluation value. Assuming that the arc evaluation value of the i-th arc is Vi, the weight for the i-th arc evaluation value is wi, the number of arcs is N, and the path evaluation value is P, P is given by the following equation (1).

As described above, there are a plurality of paths. However, since there are many character segments in an actual character string, the number of existing paths becomes enormous.
Therefore, in the technique described in Japanese Patent Laid-Open No. 3-225579, a dynamic programming method is used as a method for searching for a path having the highest evaluation value from a plurality of paths in the network as shown in the example of FIG. Is stated.
Here, a Viterbi method suitable for searching for the best path of such a network in a dynamic programming method will be described.

In the example shown in FIG. 36, a network from the start node 3600 to the end node 3690 will be described. The links (also referred to as arcs) between the nodes are not limited to those shown in FIG. The connection may not be symmetrical as shown in FIG.
In this network, it is assumed that the end point node is reached from the start point node via a plurality of nodes (intermediate node 3611, intermediate node 3612, intermediate node 3613, etc.) on the way. An intermediate node is called an intermediate node.
A link is established between each node. An evaluation value (link value) unique to the link is assigned to this link. There are a plurality of paths from the start node 3600 to the end node 3690. A path consists of multiple links. The sum of the link values of a plurality of links included in the path becomes the evaluation value of the path.
For example, the link value is a distance between nodes. In this case, the path with the minimum path evaluation value is the path with the minimum distance among the paths from the start node to the end node. Alternatively, it may be a problem of obtaining a path having the maximum path evaluation value.

Here, the Viterbi method reduces non-optimal paths by limiting the number of links input from a certain direction to a certain node. This is a technique for reducing the amount of calculation processing and the required memory amount.
For example, it is assumed that the number of links input from the left to the node x (intermediate node 3621) is already limited to 1. Similarly, the node y (intermediate node 3622) and the node z (intermediate node 3623) are also limited to 1. At this time, the link input from the left to the node X (intermediate node 3631) is limited. The node X (intermediate node 3631) is linked to three nodes: a node x (intermediate node 3621), a node y (intermediate node 3622), and a node z (intermediate node 3623). At this time, there is an optimal possibility that the path passing through the node X (intermediate node 3631) is from the node x (intermediate node 3621), the node y (intermediate node 3622), and the node z (intermediate node 3623) to the node X. One of the links going to (intermediate node 3631). Of these three, only the optimum one is left and the remaining two are deleted. In this way, the path (link) input from the left to the node X (intermediate node 3631) is limited to 1. Similarly, for the node Y (intermediate node 3632) and the node Z (intermediate node 3633), the paths input from the left are limited to 1.
Such a procedure is performed in the right direction in order from the left node A (intermediate node 3611), node B (intermediate node 3612), and node C (intermediate node 3613). Finally, the number of paths is limited to three that enter the node P (intermediate node 3681), the node Q (intermediate node 3682), and the node R (intermediate node 3683). What is necessary is just to select the optimal one among these three paths.
Such an optimal path selection method using the Viterbi method can be similarly applied to the network illustrated in FIG. Let the character cutout position be a node. Moreover, what is necessary is just to let an arc evaluation value be the above-mentioned link value.

The network illustrated in FIG. 34 handled by the prior art has one character candidate for one arc. However, there are actually a plurality of character candidates for one arc. That is, there are a plurality of character recognition results. For example, as shown in FIG. 37, a plurality of character candidates are assigned. FIG. 37 is an explanatory diagram showing a network example when there are a plurality of character candidates. In the example of FIG. 37, when the image “chemical” (character image 3702) is recognized as one character, the recognition result is “top” of the character candidate 3702A, “when” of the character candidate 3702B, and “tilt” of the character candidate 3702C. There are three types. There are three types of recognition results when the image “K” (character image 3704) is recognized as one character, “K” for the character candidate 3704A, “Ratio” for the character candidate 3704B, and “K” for the character candidate 3704C. Similarly, there are a plurality of character candidates as character recognition results for other character images. In the example of FIG. 37, there are three types of character candidates for each character image, but a different number of character candidates may be assigned. For example, when a character having a recognition accuracy equal to or higher than a predetermined value is used as a character candidate, the number of character candidates may be different for each character image.
In the prior art, in such a case, the Viterbi method (or generally the dynamic programming method) is not applied to obtain a character recognition result.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
1 and 3 show conceptual module configuration diagrams of configuration examples of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment is a computer program for causing these modules to function (a program for causing a computer to execute each procedure, a program for causing a computer to function as each means, and a function for each computer. This also serves as an explanation of the program and system and method for realizing the above. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. It is the control to be stored in the device. Modules may correspond to functions one-to-one, but in mounting, one module may be configured by one program, or a plurality of modules may be configured by one program, and conversely, one module May be composed of a plurality of programs. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.). “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. In addition, if it is before the target processing, it is used in accordance with the situation / state at that time or with the intention to be decided according to the situation / state up to that point.
In addition, a system or device is configured by connecting a plurality of computers, hardware, devices, and the like through communication lines (including one-to-one correspondence, one-to-many correspondence, many-to-one correspondence, and many-to-many communication connection). In addition, the case where it is realized by one computer, hardware, device, or the like is also included. “Apparatus” and “system” are used as synonymous terms. Of course, the “system” does not include a social “mechanism” (social system) that is an artificial arrangement.
In addition, when performing a plurality of processes in each module or in each module, the target information is read from the storage device for each process, and the processing result is written to the storage device after performing the processing. is there. Therefore, description of reading from the storage device before processing and writing to the storage device after processing may be omitted. Here, the storage device may include a hard disk, a RAM (Random Access Memory), an external storage medium, a storage device via a communication line, a register in a CPU (Central Processing Unit), and the like.

  The information processing apparatus according to the present embodiment recognizes characters from an image. As shown in the example of FIG. 3, an image reception module 310, a character string extraction module 320, a cutout position extraction module 330, a character A candidate extraction module 340, a path limitation processing module 350, and an output module 360 are included.

  The image reception module 310 is connected to the character string extraction module 320. The image reception module 310 receives an image and passes the image to the character string extraction module 320. Accepting an image means, for example, reading an image with a scanner, a camera, etc., receiving an image from an external device via a communication line by fax, etc., a hard disk (in addition to what is built in a computer, a communication line For example, reading out an image stored in a device etc.). The image may be a binary image or a multi-value image (including a color image). One image may be received or a plurality of images may be received. Moreover, as long as the content of the image contains a character string, it may be a document used for business, a pamphlet for advertisement, or the like.

The character string extraction module 320 is connected to the image reception module 310 and the cutout position extraction module 330. The character string extraction module 320 extracts a character string from the image received by the image reception module 310.
The image targeted by the cut-out position extraction module 330 is a character string image of only one column written horizontally or vertically. Here, the column is a column arranged horizontally in the case of horizontal writing, and a column aligned vertically in the case of vertical writing.
Therefore, if the image received by the image receiving module 310 is a character string image with only one column, the character string extraction module 320 may be used as it is. Some images received by the image receiving module 310 include a plurality of character strings, and various methods have been proposed for separating such a plurality of character strings into a single character string. Therefore, they can be used. Since there are various methods as examples of separation so as to form a single character string, any one of them may be used. For example, if (1) JP-A-4-311283, (2) JP-A-3-233789, (3) JP-A-5-73718, (4) JP-A-2000-90194, etc. are used. Good. Other methods may be used.

  The cutout position extraction module 330 is connected to the character string extraction module 320 and the character candidate extraction module 340. The cutout position extraction module 330 extracts a position at which a character image is cut out from the character string image extracted by the character string extraction module 320. That is, the character string image is divided into a plurality of character segments. Since there are various methods for extracting the character cut-out position, any one of them may be used. For example, (1) Japanese Patent Application Laid-Open No. 5-114047, (2) Japanese Patent Application Laid-Open No. 4-100189, (3) Japanese Patent Application Laid-Open No. 4-92992, (4) Japanese Patent Application Laid-Open No. 4-68481, (5) Special Kaihei 9-54814, (6) Character boundary candidate extraction method described in paragraph 0021 of JP-A-9-185681, (7) Character cut-out position determination described in paragraph 0005 of JP-A-5-128308 A method or the like may be used. Other methods may be used. The character image here is a so-called character candidate image, and the character image is not necessarily an image representing one character.

  Further, the cutout position extraction module 330 may extract a plurality of cutout positions. By extracting a plurality of cutout positions, there are a plurality of character cutout position groups for one character string image. The character cutout position group means that there are one or more character cutout positions for one character string image. For example, if there are two character cutout positions, they are divided into three character images. Also, “a plurality of character cut-out position groups” means that there are a plurality of character image strings divided by character cut-out positions for one character string image. For example, a character image string composed of three character images at two character cutout positions and a character image string composed of four character images at three character cutout positions. To explain with a specific example, a character image string consisting of “I”, “HI”, and “Study” and a character image string consisting of “K” and “Study” are generated for the character string “Chemical”.

  The character candidate extraction module 340 is connected to the cutout position extraction module 330 and the path limitation processing module 350. The character candidate extraction module 340 extracts a plurality of character candidates that are the result of character recognition performed on the character images divided by the positions extracted by the cutout position extraction module 330. In order to perform this extraction process, a character recognition process may be performed. Therefore, a character recognition module may be included in the character candidate extraction module 340. As described above, the recognition result obtained by the character recognition process corresponds to a plurality of character candidates for one character image. In other words, the character image is recognized, and a plurality of character candidates such as a character candidate having the first recognition accuracy and a character candidate having the second recognition accuracy are recognized. As a result. And as a character recognition result, you may have the recognition accuracy of the character candidate other than a character candidate. In addition, for extraction, a predetermined number of character candidates may be extracted from one character image, or character candidates having a recognition accuracy equal to or higher than a predetermined value are extracted. Also good. The recognition accuracy may be a value representing the reliability as a recognition result in the character recognition process, or a value representing the character likeness determined by the size of the circumscribed rectangle of the character image, the aspect ratio, etc. Also good.

The path limitation processing module 350 is connected to the character candidate extraction module 340 and the output module 360. The path restriction processing module 350 uses each of the plurality of character candidates extracted by the character candidate extraction module 340 as a node, and generates a network by constructing a link between nodes of adjacent character images. Between nodes of adjacent character images means that there is an adjacent character image and the node corresponds to the character image.
When the cutout position extraction module 330 has extracted a plurality of cutout positions, the path limitation processing module 350 performs character processing on character images divided by the cutout positions extracted by the cutout position extraction module 330. Each of a plurality of character candidates as a result of recognition may be a node, and a network may be generated by building a link between nodes of adjacent character images.
Then, the path limitation processing module 350 limits the links connecting to the generated nodes in the network from either the first direction or the last direction to links that match a predetermined character string pattern. .
Further, the path limitation processing module 350 may generate a link value based on a value representing the character string likelihood based on the relationship between the character candidates of the nodes connected by the limited link. Furthermore, the link value may be generated based on a value representing character likeness with respect to the nodes constituting the link.
Then, the path limitation processing module 350 may select a path in the network based on the generated link value.

Further, when the character string pattern does not match from the first link, the path limitation processing module 350 may limit the link following the non-matching link to a link that matches the character string pattern. .
In addition, when there is no link that matches the character string pattern, the path limitation processing module 350 may limit the link to a part of the character string pattern that matches the character string pattern.

  The output module 360 is connected to the path limitation processing module 350. The output module 360 outputs a character candidate string in the path connected by the link limited by the path limitation processing module 350 as a character recognition result. The output module 360 may output a character candidate string in the path selected by the path restriction processing module 350 as a character recognition result. Outputting the character recognition result includes, for example, printing on a printing device such as a printer, displaying on a display device such as a display, storing in a storage medium such as a memory card, passing to another information processing device, etc. Is included.

The embodiment shown in the example of FIG. 3 can also be grasped as follows.
(1) A plurality of cut position extraction means for extracting a position to cut out a character image from an image, and a plurality of character recognition results obtained by performing character recognition on the character image divided by the position extracted by the cut out position extraction means. Character candidate extraction means for extracting character candidates, and network generation for generating a network by constructing a link between nodes of adjacent character images with each of the plurality of character candidates extracted by the character candidate extraction means as nodes. And a link that connects to a node in the network generated by the network generation unit from either the first direction or the last direction, and is limited to a link that matches a predetermined character string pattern A character candidate string in a path connected by means and a link limited by the limiting means An information processing apparatus characterized by comprising output means for outputting a result.
According to this information processing apparatus, when a character is recognized from an image, a character recognition result with higher accuracy can be output as compared with a case where the present configuration is not provided.

(2) a link value generating means for generating a link value based on a value representing a character string likelihood based on a relationship between character candidates of nodes connected by a link limited by the limiting means; and the link value generating means Path selection means for selecting a path in the network generated by the network generation means based on the generated link value, and the output means includes character candidate strings in the path selected by the path selection means Is output as a character recognition result, The information processing apparatus according to (1).
According to this information processing apparatus, it is possible to prevent a recognized character string from being determined based on only one character recognition result of each character image.

(3) The information processing apparatus according to (2), wherein the link value generation unit generates the link value based on a value representing character likeness with respect to the nodes constituting the link. .
According to this information processing apparatus, it is possible to generate a link value using a value representing character stringiness and a value representing characteriness.

(4) The cutout position extraction unit extracts a plurality of cutout positions, and the network generation unit recognizes characters for character images divided by the plurality of cutout positions extracted by the cutout position extraction unit. The information according to (2) or (3), wherein each of a plurality of character candidates as a result of performing the step is used as a node, and a network is generated by constructing a link between adjacent character image nodes. It is a processing device.
According to this information processing apparatus, it is possible to output character recognition results for a plurality of cutout positions.

(5) In the case where the character string pattern does not match from the first link, the limiting means limits the link following the non-matching link to a link that matches the character string pattern. The information processing apparatus according to any one of (1) to (4).
According to this information processing apparatus, even if there is an erroneous character recognition result at first, a character recognition result that matches the character string pattern can be output.

(6) In the case where there is no link that matches the character string pattern, the limiting means limits the link to a link that matches a part of the character string pattern in the character string pattern. The information processing apparatus according to any one of the above.
According to this information processing apparatus, it is possible to output a character recognition result that matches a partial character string pattern in the character string pattern.

(7) As a result of the computer performing character recognition on the character image divided by the position extracted by the cut-out position extracting unit and the position extracted by the cut-out position extracting unit. A character candidate extracting means for extracting a plurality of character candidates and a network by constructing a link between adjacent character image nodes with each of the plurality of character candidates extracted by the character candidate extracting means as a node And a link that matches a predetermined character string pattern with respect to a link that connects to a node in the network generated by the network generation unit from either the first direction or the last direction. Limiting means for limiting and characters in a path connected by a link limited by the limiting means An information processing program for functioning as an output means for outputting the auxiliary column as a character recognition result.
According to this information processing program, it is possible to output a character recognition result with higher accuracy when recognizing characters from an image than when not having this configuration.

FIG. 4 is an explanatory diagram showing an example of a target form 400. In the form 400, a name frame 410, an address frame (in front of the city) 420, and an address frame (after the city) 430 are set. A reporter on the form 400 enters a name in the name frame 410. Addresses are written in the address frame (in front of the city) 420 and the address frame (after the city) 430. As a result, it can be assumed that only the name is entered in the name box 410. Alternatively, it can be assumed that only the address is written in the address frame (in front of the city) 420 and the address frame (after the city) 430.
In this way, when the characters or words that are supposed to be described in the frame are limited, the recognition rate can be increased as compared with the case where the description can be freely made. For example, in the case of an address or the like, consider a case where the name of a city is designated to be written in the address frame (in front of the city) 420 as in the example of FIG. The name of the city is limited, so if you limit it, the accuracy will be higher. Here, for example, it is assumed that the city names that may be described in the address frame (in front of the city) 420 are limited to the following three.
(1) Yokohama (2) Kawasaki (3) Yokosuka Here, it can be said that the character string described in the address frame (city front) 420 is limited to these three patterns.

There is a regular expression as an example of a method for designating the limitation of the character string pattern (a method for designating the limited character string pattern 108). There are various notation methods for regular expressions. As an example, a notation method for regular expressions is illustrated in FIG. FIG. 5 is an explanatory diagram showing an example of a regular expression notation rule 500. In the regular expression notation rule 500, the notation in the rule column 510 is explained in the meaning column 520.
For example, as described above, when targeting only “Yokohama”, “Kawasaki”, or “Yokosuka”, as a regular expression,
"Yokohama | Kawasaki | Yokosuka"
May be described.

In the technique described in Patent Document 2, an example is described in which the character type is limited for each character position to increase accuracy.
In the city example above,
・ The first character is “horizontal” and “river” only ・ The second character is only “Hama”, “Saki”, and “su” ・ The third character is only “ga”. Use this condition. For example, since there can only be “horizontal” and “river” for the first character, it is set to output only that. By doing so, it is possible to increase the accuracy of the recognition rate. For example, “horizontal” is similar in character to “yellow” and the correct answer is “horizontal”, but there is a possibility that it may be misrecognized as “yellow”. By limiting to “”, output of “yellow” is prohibited.

Furthermore, as shown in Patent Document 3, there is a method of viewing a plurality of character candidates from the first character.
When recognizing one character, a plurality of recognition candidates can be obtained. The plurality of character candidates are ranked from the first candidate to the nth candidate. The first candidate is the candidate with the highest accuracy, and the accuracy of recognition decreases as the numerical value increases. In the technique described in Patent Document 3, a search is made for items matching the regular expression in order from the first candidate of the first character. Here, it is assumed that the first character is determined. If the first candidate of the first character matches the regular expression, the candidate is selected. If the first candidate does not match the regular expression, the second candidate is checked. Thereafter, the candidates are searched in order of the second and third until the regular expression is matched. If no candidate matches the regular expression, the process ends. If there is a candidate that matches the regular expression, select that candidate. After selecting a candidate, the second character is selected. Here, since the first character has already been selected, it is necessary to select a character whose two character strings match the regular expression together with the first character. Here, similarly to the first character, search is performed in order from the first candidate of the second character. When a regular expression is matched, the candidate is selected.
With this method, even if there are a plurality of character candidates, a character string that finally matches the regular expression can be selected.

For example, assume that each character and its recognized character candidate are as shown in the example of FIG. That is, there are three character recognition candidates for each of the three characters. In this case, the correct answer is “Yokosuka”. Also, the regular expression as the output character pattern is
"Yokohama | Kawasaki | Yokosuka"
Suppose that
In this example, the correct output can be obtained by selecting the second candidate for the first character, the second candidate for the second character, and the first candidate for the third character.
In the technique described in Patent Document 2, character candidates to be output are determined in advance according to the character position. The output candidate in the technique described in Patent Document 2 has the highest ranking among the outputs excluding the hatched portion shown in the example of FIG. 7 (if the first candidate has a higher rank than the second candidate) Will be output. Eventually, with the technique described in Patent Document 2, “Yokohamaga” is output.

  In the technique described in Patent Document 3, since “horizontal” matches the regular expression at the first character, “horizontal” is selected. In the second character, “Hama” is output because “Hama” has the highest ranking and matches the regular expression. In the third character, no character matches the regular expression. This is because the word “Yokohamaga” is not in the output character pattern “Yokohama | Kawasaki | Yokosuka”. Therefore, in the technique described in Patent Document 3, there is no output or “Yokohama” having the longest match in “Yokohamaga” is output.

In the techniques described in Patent Document 2 and Patent Document 3, a regular expression (or a character string pattern instruction method such as a regular expression in order from the first character of the character string and the first candidate. ) Is selected.
In the present embodiment, a pattern that matches a regular expression is searched for from character strings that can be character recognition candidates. For this purpose, the Viterbi method may be used.

FIG. 8 is a flowchart showing an example of processing according to this embodiment.
In step S802, the image reception module 310 receives a target image.
In step S804, the character string extraction module 320 extracts a character string image from the image.
In step S806, the cutout position extraction module 330 extracts the cutout position for the character string image.
In step S808, the character candidate extraction module 340 recognizes characters in the cut character image.
In step S810, the character candidate extraction module 340 extracts a plurality of character recognition results as character candidates for the character image.
In step S812, the path limitation processing module 350 generates a network and limits the paths therein.
In step S814, the output module 360 outputs a character recognition result.

Next, processing performed by the path limitation processing module 350 will be described with reference to FIGS.
In the present embodiment, the character cutout position is confirmed or the character is recognized by outputting a path having a high path evaluation value. A dynamic programming method may be used for path search.
In the network of the present embodiment, there are a start node, an end node, and a plurality of intermediate nodes. A link value is given to the link between each node. A path from the start node to one end node through one or a plurality of intermediate nodes passes through a link depending on the intervening node. The path evaluation value of the path from the start point node to the end point node can be expressed as a weighted sum of the link values of the links through which the path passes.
The path limitation processing module 350 according to the present embodiment generates the above-described node, link, and path configuration (network structure) when a plurality of character recognition results exist for one character image. It is. Given a network structure, the path limitation processing module 350 can search for an optimal path using a method such as the Viterbi method.

<A1. When the character cutout position is fixed>
First, the case where the character cutout position extracted by the cutout position extraction module 330 is fixed (one type) will be described.
FIG. 9 is an explanatory diagram showing a symbol example. As types of symbols, there are a rectangle 910, connecting lines 920, 922, 924, 927, 928 which are horizontal bars, an arc 930, and character candidates 942, 944, 946 which are circles.
In the example of FIG. 9, rectangles 910A, 910B, 910C, and 910D (rectangle 910 illustrated in FIG. 10) each represent a character segment.
Connection lines 920, 922, 924, 926, and 928 which are horizontal bars indicate character cutout positions (connection lines 920 and 922 illustrated in FIG. 11). A character segment is connected to an adjacent character segment via a character cutout position.
Furthermore, character candidates 942A, 944A, and the like represented by circles indicate a plurality of character candidates when one character segment is recognized as one character. Arcs 930A, 930B, 930C, and 930D indicate that character recognition is performed only on the lower one character segment.

In the example of FIG. 12, the character candidates 942, 944, and 946 indicate a plurality of character candidates when the character segment of one character indicated by the rectangle 910 below the character candidates is recognized. An arc 930 indicates that character recognition is performed on only the rectangle 9101 below the arc 930.
In the present embodiment, a plurality of character candidates in a character segment are regarded as nodes. Further, a link is connected to a character candidate of an adjacent character segment. In the example of FIG. 13, links are indicated by bold lines.
Here, as the link value generated by the link value generation process, a link value indicating the interaction between the left and right nodes of the link may be used. Specifically, the probability (bigram) that the left character candidate of the link and the right character candidate of the link appear in Japanese sentences in succession is used.
By configuring nodes and links in this way, all network structures can be defined. If the network structure can be defined, the optimum path can be selected by the Viterbi method or the like.

<A2. When using in-node information>
In the above description, only the link value indicating the interaction between nodes (probability of appearing in the text) is used, but an evaluation value of the node alone may be used. Here, it is assumed that the optimum path is searched using the Viterbi method. In order from the left, only one link for each node is entered from the left of the node.
Assume that it is a stage where the links of the character candidates 942B, 944B, and 946B are limited in the example of FIG.
Here, link values between the character candidates 942B, 944B, and 946B and the character candidates 942A, 944A, and 946A on the left side are generated. As a link value, both a value such as a bigram representing an interaction between nodes and a value inside each node are used. The value inside the node includes, for example, the recognition accuracy of the character candidate 942B.

Here, since the link is between the character candidates 942B, 944B, 946B and the character candidates 942A, 944A, 946A, the link values are the evaluation values between the character candidates 942B, 944B, 946B and the character candidates 942A, 944A, 946A. Is easy to calculate. However, the value inside the node is not between the character candidates 942B, 944B, 946B and the character candidates 942A, 944A, 946A, but in this case, exists in the character candidates 942B, 944B, 946B.
That is, the inter-node information exists inside the link, and the intra-node information exists at the end point of the link. Such occurrence positions or values with different concepts are handled at a time.

Conventionally, arc evaluation values between nodes are calculated using the start point node 3400, the intermediate node 3410 (node 1), the intermediate node 3420 (node 2), the end node 3490, etc. (that is, the character extraction position) shown in FIG. doing. As in the present embodiment, a link value between nodes is not calculated using a plurality of character codes as nodes. Therefore, the prior art cannot be used as it is.
In the present embodiment, as the link evaluation value, a value (for example, bigram value) existing inside the link and a value (for example, character recognition accuracy of the character candidate 942B) existing only at one end point of the link are used. Use. The value existing at the other end point (for example, the character recognition accuracy of the character candidate 942A) is not used. By doing in this way, evaluation using both the value inside the link and the value of the end point of the link becomes possible.
Eventually, the evaluation values of all the links are added by the expression (1) as the evaluation value (path evaluation value) of the character string. Therefore, if the link evaluation value includes the evaluation value inside the link and the evaluation value at one end of the link, the evaluation values inside all the links and the link end points are included in the path evaluation value. One evaluation value is included.

In the link value generation process, a link value may be calculated using a plurality of values (bigram and recognition accuracy) as feature quantities, such as the above-described link internal value and link end point value. As described above, methods for calculating one link value from a plurality of values include (1) Japanese Patent Laid-Open No. 9-185681, (2) Japanese Patent Laid-Open No. 61-175878, and (3) Japanese Patent Laid-Open No. 3-37782. No. 4, (4) Japanese Patent Laid-Open No. 11-203406, etc. may be used. Other methods may be used.
Note that a plurality of values can be grasped as a feature vector, and the link value can be realized by a function that outputs a link evaluation value (scalar value) for the feature vector.

<A3. When using two or more nodes as link information>
In the above, a bigram is used as mutual information between the left and right nodes of the link. In this case, the relationship information between the two nodes is used as the link information.
When the Viterbi method is used, for example, the number of links on the left side of the character candidates 942A, 944A, and 946A that are nodes is already limited to one. In this case, link information can be constructed using information of two or more nodes.
For example, it is possible to use a trigram which is the occurrence probability of three consecutive characters instead of the bigram which is the occurrence probability of two consecutive characters.
Now, in the link value generation process, an attempt is made to generate link values on the left side of the character candidates 942B, 944B, and 946B that are nodes.
For example, the link value between the character candidate 942A and the character candidate 942B is calculated. If it is a bigram, what is necessary is just to obtain | require the occurrence probability that the character candidate 942A and the character candidate 942B continue. Here, a case where a trigram is obtained will be described. Since the left link of the character candidate 942A is limited to one, the character on the left of the character candidate 942A is actually confirmed. Let G be the node that holds this character. As the trigram, the occurrence probabilities relating to the three characters of node G-node (character candidate 942A) -node (character candidate 942B) may be obtained.
The trigram obtained as described above may be generated as a link value between the node (character candidate 942A) and the node (character candidate 942B). Similarly, even Ngram can be obtained.

<A4. When the character cutout position is not fixed>
When the character cutout position is not fixed (that is, when the cutout position extraction module 330 has extracted a plurality of character cutout positions, specifically, “I” and “H”, such as “B”. Alternatively, when it is not known which of the two is “change”, the selection of the character candidate and the selection of the character cutout position may be performed. When the character cutout position is not fixed, the character candidate selection is the character cutout position selection.
FIG. 14 is an explanatory diagram illustrating a processing example when there are a plurality of character cutout positions. Here, the meaning of the symbol of the arc is added. When the arc indicates a plurality of character segments (rectangles) below, the arc indicates that an image obtained by integrating the plurality of character segments is recognized as one character. The arc 1410A has character candidates 1422A, 1424A, and 1426A as character recognition results by regarding the image obtained by integrating the rectangle 910A and the rectangle 910B as one character. In addition, the arc 1410C has character candidates 1422C, 1424C, and 1426C as character recognition results by regarding an image obtained by integrating the rectangles 910A, 910B, 910C, and 910D as one character.
As shown in the example of FIG. 15, when there are two character segments (rectangle 910A, rectangle 910B) “I” and “HI” below the arcs 930A and 930B, the arc 1410 including the two character segments Character candidates (character candidates 1422, 1424, and 1426) correspond to a plurality of character candidates when one character segment “formation” in which “I” and “HI” are integrated is recognized.

The link connection when the character cutout position is not fixed is as shown in the example of FIG. FIG. 16 is an explanatory diagram illustrating a processing example when there are a plurality of character cutout positions.
Here, attention is focused on the character cutout position. Now, the node link related to the character cutout position indicated by the arrow in FIG. 16 is targeted. The nodes linked at this character cut-out position include
(1) Left node: a node on the right side of the arc at the character cutout position of the arrow (a hatched node, character candidate 1642A, character candidate 1644A, character candidate 1662A, character candidate 1664A, character candidate 1672A, character candidate 1673A, etc. )When,
(2) Right node: a node in which the left side of the arc is present at the character cut-out position of the arrow (inner white node, character candidate 1642B, character candidate 1644B, character candidate 1662B, character candidate 1664B, character candidate 1672B, character candidate 1673B, etc. )
There are two types. At this time, a graph structure can be constructed by forming a link between the left node and the right node.
For example, a link may be formed so that all left nodes can be directly connected to all right nodes. Furthermore, as described above, a link between the left node and the right node is formed at all character cutout positions, and if the left side is the end point of the character string, it is connected to the start point node, and the right side is the character string In the case of an end point, all graph structures can be constructed by connecting to the end node.

Also in this case, the link value may be one indicating the interaction between the left and right nodes of the link, or an evaluation value inside the node may be used.
In particular, in this case, since the character cutout position is not fixed, the character shape information can be used as the evaluation value inside the node. As an example of the character shape information, the aspect ratio of the character, the amount of white space on the left and right of the character, and the like can be used.

  In this way, all paths from the left end of the character string to the right end of the character string can be written out. Each path corresponds to a recognized output character string. That is, in the network constituting the character string, the character string can be determined by determining the path from the left end node to the right end node.

  Summarizing the above, the network constituting the character string is, for example, as shown in FIG. In the example of FIG. 17, ◯ indicates a node. A solid line connecting ○ and ○ is an arc or a link indicating a connection between nodes. Node A indicates the left end of the character string, and node B indicates the right end of the character string. In this network, a character string can be determined by determining a path from the left end node A to the right end node B.

Of these paths, only those that match the regular expression need be output. However, since the number of paths is enormous, it is not practical to check whether all paths match the regular expression.
Therefore, the speed is increased by using the Viterbi method.
As described above, the number of links connected to a certain node from the left is limited to one. Of course, the number of links connected to a certain node from the right may be limited to one, but in the following example, a link connected from the left will be described.
Here, if a link connected to a certain node from the left is determined, an output character string reaching that node can be determined. What is necessary is just to check whether this output character string partially matches the regular expression.

First, it is assumed that there are N links connected to a certain node from the left. Of the N links, only those that partially match the regular expression are extracted, and those that do not partially match are discarded.
This will be described with reference to the example of FIG. FIG. 18 is an explanatory diagram showing an example in which nodes in a network constituting a character string are connected.
For example, it is assumed that three links from the left are connected to the node D (character candidate “meeting”). The links are connected from node A (character string candidate “Higaku”), node B (character string candidate “Chemistry”), and node C (character string candidate “Gaku”). Here, it is assumed that the regular expression is “chemical meeting”.
Nodes A, B, and C are further connected from the left, but that portion is omitted in the description. Regarding nodes A, B, and C, the number of nodes on the left side is already limited to one, and the paths to those nodes are already determined. Therefore, the character strings that reach those nodes are also determined. The character string candidate of node A is “Higaku”, the character string candidate of node B is “chemistry”, and the character string candidate of node C is “gaku”.
Here, the link connected to the node D from the left is determined. If it is a path from node A, the character string is “Higaku society”, if it is a path from node B, the character string is “Chemical Society”, and if it is a path from node C, the character string is It becomes "Togaku Gakkai". Among them, the one that partially matches the character string pattern that is a regular expression is selected.

Here, the partial matching of the character string with the character string pattern means that the character string only needs to match a portion continuous from the top of the regular expression “Chemical Conference”. For example, “Chemical Society” matches the first to third characters of the regular expression “Chemical Conference”, so it is assumed that they partially match. Others such as “Higaku Gakkai” and “Gaku Gakkai” do not match.
Therefore, partial match means that when a character string is X, it is assumed that an arbitrary character follows X, and whether or not the character string followed by an arbitrary character matches the regular expression from the beginning. You may do that.

Here, when there are a plurality of partial matches, the one with the highest evaluation value may be selected by a method different from the method using the regular expression. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.
Furthermore, if there is no partial match, the candidate with the highest evaluation value may be selected from all candidates using a method different from the regular expression. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.
As described above, the link on the left side is narrowed down to one at each node. Finally, since a plurality of paths from the left end to the right end remain, it is sufficient to obtain a path to be output from among them.

<Example 1 of the path limitation processing module 350>
FIG. 19 is an explanatory diagram showing a module configuration example in the path limitation processing module 350. The path limitation processing module 350 includes a network construction processing module 1910, a node number limitation processing module 1920, a control module 1930, and an output determination processing module 1940.
FIG. 20 is a flowchart illustrating an example of processing performed by the path limitation processing module 350.
In step S2002, the network construction processing module 1910 constructs a network.
In step S2004, the node number limitation processing module 1920 limits the nodes in the network under the control of the control module 1930.
In step S2006, the output determination processing module 1940 determines a path to be output.

The network construction processing module 1910 is connected to the node limit processing module 1920. The network construction processing module 1910 uses each of the plurality of character candidates extracted by the character candidate extraction module 340 as a node, and creates a network by constructing a link between adjacent character image nodes. That is, as described above, a network is constructed from one end (for example, the left end) of the character string to the other end (for example, the right end).
The node limit processing module 1920 is connected to the network construction processing module 1910, the control module 1930, and the output determination processing module 1940. The node limit processing module 1920 matches a predetermined character string pattern with respect to a link connected to a node in the network generated by the network construction processing module 1910 from either the first direction or the last direction. Limited to links. That is, as described above, for each node, for example, processing for limiting the number of nodes connected from the left is performed. For example, the number of nodes to be limited is one.

The control module 1930 is connected to the node number limitation processing module 1920. The control module 1930 controls the node positions that limit the number of nodes in order from the left.
In the present embodiment, the control module 1930 does not perform processing for limiting the number of nodes in the rightmost end node to one. That is, if the number of links (number of arcs) entering the rightmost end node is M, M paths will eventually remain. The M paths correspond to M character strings.

The output determination processing module 1940 is connected to the node number limitation processing module 1920. The output determination processing module 1940 outputs a character candidate string in the path connected by the link limited by the node number limitation processing module 1920 as a character recognition result. That is, the character string to be output is selected from the M character strings described above. For example, in the example of FIG. 17, when three links are connected to the rightmost end node B, three character string candidates remain. A character string to be output is selected from these three candidates.
This is because the number of characters that do not match the back side of the character string cannot be evaluated by partial matching in the middle. In order to select the character string having the smallest number of mismatches by combining the number of mismatches between the front side and the back side of the character string, the M character strings are evaluated.
Further, in the control module 1930, the number of input nodes at the rightmost end node may be selected until one. The output determination processing module 1940 selects a character string having the longest portion matching the regular expression from the single character string.

There are various evaluation scales for selecting “character string to be output”, and any one of the following may be selected.
(1) Evaluation scale 1
Choose the longest match for a regular expression.
If there are multiple longest matches, the character string with the highest path evaluation value is selected. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.
As a modified example, when the number of characters of the longest match is less than a predetermined number of characters, it is rejected.
(1.1) Modification (Part 1)
If the left end or right end of the character string does not match the regular expression, the portion excluding the left end or right end that does not match is extracted, and only that portion is output as the regular expression. For example, if the regular expression is “Chemical Conference” and the character string is “AB Chemical Conference C”, “Chemical Conference” is output by removing “AB” and “C”. At this time, the number of characters at the left end “AB” and the right end “C” removed is a total of three characters. The character string with the smallest number of removed characters is selected.
(1.2) Modification (Part 2)
In the above-described example, the character string in the image that is “chemical meeting” (for example, the number of pixels of the image or the number of centimeters on the paper before scanning) may be selected. That is, the smallest noise in the image is selected.

(2) Evaluation scale 2
The length of the character string that matches the regular expression is not specified, and the character string having the highest path evaluation value is selected from those that match the regular expression. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.
There should be a part that matches the regular expression in the output string. For example, if the regular expression is “Chemical Conference” and the character string is “Previous Chemical Conference A”, the first and sixth characters are omitted, and only the part “Chemical Conference” is output. Become.
Further, it may be adopted only when it completely matches the regular expression.

(3) Evaluation scale 3
If all character strings from the left end to the right end match the regular expression, that character string is output. If multiple paths match, select the character string with the highest path evaluation value. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used. However, if none of the character strings from the left end to the right end match the regular expression, there is no output (reject).

<Example 2 of the path limitation processing module 350>
In Example 1 of the path limitation processing module 350 described above, a partially matching node is selected from the left end of the character string.
However, in partial matching, it is necessary to match the regular expression from the beginning of the character string.
Noise often occurs at the beginning of the character string. When noise occurs, there may be no character string that partially matches from the beginning of the character string. For example, when there is vertical bar noise at the beginning of a character string, the character “1” may be included in the first character of many output character strings.
In such a case, all the paths constructed by the network construction process will not partially match, and regular expression matching becomes impossible. This is because partial matching means matching from the beginning of the character string.
Therefore, instability when noise is mixed at the beginning of the character string is eliminated.

Therefore, as a process for limiting the number of nodes, the following process is performed for each link.
(1) I = 1.
(2) It is checked whether or not a partial match is made from the I character in the character string.
(3) End if partial match.
(4) If I is the end of the character string, the process ends.
(5) If there is no partial match, set I = I + 1 and return to (2).
Then, by using the value of the variable I, it is measured how many characters have been partially matched for each link. Using the measured I, the number of input nodes is limited by the following method in the processing in the node limit processing module 1920.
-Select the input node with the smallest value of I among the partially matched paths.
When there are a plurality of smallest I values (particularly the same I value) among the partially matched paths, the node with the largest path evaluation value is selected.
If there is no partially matching path, select the node with the largest path evaluation value.
By doing so, instability when noise is mixed at the beginning of the character string is eliminated.

<Example 3 of the path limitation processing module 350>
Further, the path limitation processing module 350 may output a partially matched character string when there is no character string that completely matches the regular expression.
In Examples 1 and 2 of the path limitation processing module 350 described above, a path (character string) that matches a given character string pattern (regular expression) is output. However, since it may be a part, it may be desired to output a match. For example, it is assumed that the recognition result as in the example of FIG. The correct answer is “Yokohama”.

In this case, since there is no path of “Yokohama”, a character string that matches the regular expression cannot be output.
After character recognition, a human may correct the recognition result. If it is not output (if it is rejected), the human must input “Yokohama” and two characters. However, the character “horizontal” exists as a character recognition result. If only “horizontal” can be output, a human needs to input only one character of “beach”.
The path limitation processing module 350 performs the following processing.
(1) When verifying a partial match, record the case where the character length of the partially matched character string is the longest. You can record the string itself or the location of the path.
(2) In the processing in the output determination processing module 1940, if there is a character string that matches the regular expression, it is output.
(3) In the processing in the output determination processing module 1940, if there is no character string that matches the regular expression, the character string having the longest partial match character length is output.
Then, the operator who confirms and corrects the character recognition result is presented with a determination as to whether or not partial matching is also output. You may make it perform.

As described above, the limited character string pattern inspection process as shown in FIG. 22 is performed. That is, the limited character string pattern inspection processing module 2200 corresponding to the above-described path limitation processing module 350 receives the limited character string pattern 108 and the target character string 118 and outputs the inspection result 162.
The limited character string pattern 108 is information for limiting the character string pattern, and typically corresponds to the regular expression described above.
The limited character string pattern inspection processing module 2200 receives the limited character string pattern 108 and the target character string 118. If the target character string 118 matches the limited character string pattern 108, “match” is output as the inspection result 162. If the target character string 118 does not match the limited character string pattern 108, “non-match” is output as the inspection result 162.
There are the following two types of inspections. Do one of the tests.
(Inspection 1) Complete inspection in which “match” is set only when the character string completely matches, and “non-match” is set otherwise.
(Inspection 2) Partial match inspection in which a character string and a limited character string pattern (regular expression) are also “matched” when the partial match described in the prior art is “matched” and the rest is “nonmatched”.

For example, a regular expression is adopted as the limited character string pattern 108, and the content is
Yokohama | Kawasaki | Yokosuka.
In the case of a complete inspection, “when the target character string 118 is“ Yokohama ”,“ match ”is output as the inspection result” or “when the target character string 118 is“ Kohama ”or the target character When the column 118 is “horizontal”, an operation such as “output“ non-match ”” as the inspection result 162 is performed.
In the case of partial match inspection, “when the target character string 118 is“ Yokohama ”or the target character string 118 is“ horizontal ”,“ match ”is output as the inspection result 162”, or “target character string 118 Is “Kamahama”, the operation result such as “output“ non-match ”” as the inspection result 162 is performed.
“When the target character string 118 is“ horizontal ”,“ match ”is output as the test result 162”, or “when the target character string 118 is“ Kohama ”, the test result 162 is“ non- Operations such as “output match” are performed.
In order to realize the above-described processing, such limited character string pattern inspection processing is performed.
Here, the limited character string pattern 108 may be long. For example, when a prefecture name is received as the limited character string pattern 108, it is necessary to enter about 50 prefecture names with a symbol “|” indicating a logical sum. If it is a city name, it is necessary to enter the city name of the order number of about 1000 with the symbol “|” indicating the logical sum.
It is necessary to process such a long regular expression. In particular, when performing the process of selecting the optimum path from a plurality of paths as shown in the example of FIG. 36, the number of times of the limited character string pattern inspection process increases, so that the overall processing amount and processing time are also increased. Will increase.

Here, a case will be described in which the limited character string pattern 108 is used as a regular expression to check whether the target character string 118 matches the regular expression. Since the regular expression is a general-purpose pattern description method, the matching / non-matching inspection process becomes slow depending on the pattern description method.
Therefore, in the present embodiment, the description of the limited character string pattern 108 is decomposed.
The case where the limited character string pattern 108 is given as a simple enumeration of character strings is targeted. For example, as shown in the example of FIG. 23, a character string (character string (Yokohama) 2310, character string (Kawasaki) 2320, character string (Yokosuka) 2330) to be limited is simply arranged (that is, as a logical sum) (When a character string is connected).
Hereinafter, such a list of character strings is referred to as a character string set.
The character string set may be a text code that can be separated by any symbol as described above, an array of character strings, or any other data format that can express the set. That's fine.
There are various algorithms for determining whether the data set A exists and the input data x matches the data in the set A. Using such an algorithm, a match with the character string set as described above can be determined.
For example, methods such as binary tree search, red / black tree search, trie tree search, and hash method can be used.

Here is an example. The strings can be ordered in dictionary order (ie, can be sorted). The character string set is sorted into a binary tree structure.
The example of FIG. 24 is a diagram illustrating an example in which a character string set is a binary tree structure. In FIG. 24, ◯ indicates a node. Each node has a maximum of two child nodes. For example, in FIG. 24, node 8 has node 4 and node 12 as children.
In the binary tree search, for example, a tree structure is created such that left child <parent <right child.
In this way, by referring to the magnitude relationship with the target character string from the top parent node, in the case of N sets, data exists in the set with log ₂ N times. It is possible to inspect whether or not (in the case of FIG. 24).
As described above, the character strings that can be ordered can be inspected at a higher speed than a simple search (needs N determinations).

Since regular expressions require versatility, such a high-speed algorithm is introduced.
For example,
In the case of the regular expression of Yokohama | Kawasaki | Yokosuka, the algorithm for the character string set described above can be applied as it is. But for example,
Yokohama | (another regular expression) | As in Suga, there may be a case where a complex expression using another regular expression is inserted between OR symbols. In that case, the complicated expressions cannot be arranged in a dictionary order as a character string set. At least, it becomes a regular expression nested structure, so it is slower. For this reason, it is impossible to apply the above-described high-speed algorithm for searching a character string as a character string set for all character strings between logical sum symbols.
Therefore, in the present embodiment, a character string set portion in the limited character string pattern 108 is extracted. That is, only the character string set portion is extracted, and the binary tree search is performed on the portion, for example.
Also, a fast search algorithm can be used for partial match inspection.
for that purpose,
It may be determined whether the target character string + arbitrary character string exists in the character string set.
Assuming that the strings are arranged in dictionary order,
The target character string + optional character string is
It will line up after the target character string.
Therefore, it is only necessary to find a character string having a value greater than or equal to the target character string in the character string set in the character string set and determine the complete match for the number of characters of the target character string from the beginning of the character string.

  FIG. 1 is a conceptual module configuration diagram of a configuration example of the present embodiment (specifically, the path limitation processing module 350 illustrated in FIG. 3). The information processing apparatus according to the present embodiment outputs a character string that matches a character string type described in a predetermined regular expression from among a plurality of character strings. As shown in the example 1, the limited character string pattern reception module 110, the target character string reception module 120, the character string set extraction processing module 130, the character string set inspection processing module 140, the regular expression inspection processing module 150, the inspection result integration processing A module 160 is included.

The limited character string pattern receiving module 110 is connected to the character string set extraction processing module 130, and receives the limited character string pattern 108 which is a character string type described in a regular expression. The limited character string pattern 108 corresponds to the character string pattern described above with reference to FIGS. The limited character string pattern 108 is a predetermined regular expression that indicates that the character string pattern is composed of a three-digit number, “−”, and a four-digit number if it is a zip code, for example. If it is an address, a set of character strings that can be used as an address is applicable.
The target character string reception module 120 is connected to the character string set inspection processing module 140 and the regular expression inspection processing module 150, and receives the target character string 118, which is a target character string. The target character string 118 is, for example, a character string of a character recognition result, but is not limited to this, and may be a character string or the like typed by the operator using a keyboard or the like.

The character string set extraction processing module 130 is connected to the limited character string pattern reception module 110, the character string set check processing module 140, the regular expression check processing module 150, and the check result integration processing module 160. The character string set extraction processing module 130 extracts a portion (character string set area 132) that is a set of character strings from the limited character string pattern 108 received by the limited character string pattern receiving module 110. Then, the character string set area 132 is transferred to the character string set check processing module 140, the regular expression area 134 is transferred to the regular expression check processing module 150, and the logical relationship 136 is transferred to the check result integration processing module 160. The regular expression area 134 is the remaining part of the limited character string pattern 108 excluding the character string collection area 132, and the logical relationship 136 includes the character string collection area 132 and the regular expression area 134 in the limited character string pattern 108. It is a logical relationship.
For example, a special symbol indicating a region of a set of character strings is prepared as a regular expression of the limited character string pattern 108. Here, examples of “<<” and “>>” are shown as special symbols. For example, as the limited character string pattern 108,
<< Yokohama | Kawasaki | Yokosuka >>>> (Other regular expressions)
In this case, a portion surrounded by “<<” and “>>” is extracted as a character string collection region 132. That is, “Yokohama | Kawasaki | Yokosuka” is extracted as the character string collection area 132. This indicates one of “Yokohama”, “Kawasaki”, and “Yokosuka”. Although an example in which a region surrounded by a special symbol indicating a region of a set of character strings is extracted has been described, a region in which character strings are enumerated by “|” may be extracted.
In the above example, the “(other regular expression)” portion corresponds to the regular expression area 134. The “|” between the character string collection area 132 and the regular expression area 134 corresponds to the logical relationship 136.

The character string set inspection processing module 140 is connected to the target character string reception module 120, the character string set extraction processing module 130, and the inspection result integration processing module 160. The character string set inspection processing module 140 determines whether or not the target character string 118 received by the target character string receiving module 120 matches the character string set area 132 extracted by the character string set extraction processing module 130. . For example, processing such as binary tree search is performed on the character string collection region 132.
In addition, the character string set inspection processing module 140 matches the character string set area 132 in which a portion continuous from the beginning of the target character string 118 received by the target character string receiving module 120 is extracted by the character string set extraction processing module 130. You may make it determine whether it has done. This is processing corresponding to partial matching.

  The regular expression inspection processing module 150 is connected to the target character string reception module 120, the character string set extraction processing module 130, and the inspection result integration processing module 160. Whether the target character string 118 received by the target character string receiving module 120 matches the type described in the regular expression other than the character string extracted by the character string set extraction processing module 130. Determine whether or not. In the above-described example, the portion described in “(Other regular expression)” that is the regular expression area 134 is used, and a normal regular expression as to whether or not the target character string 118 matches the regular expression area 134 is used. Perform the inspection process.

The inspection result integration processing module 160 is connected to the character string set extraction processing module 130, the character string set inspection processing module 140, and the regular expression inspection processing module 150, and outputs the inspection result 162. The inspection result integration processing module 160 uses the determination result by the character string set inspection processing module 140 and the determination result by the regular expression inspection processing module 150 to convert the target character string 118 received by the target character string reception module 120 into a limited character string. It is determined whether or not the limited character string pattern 108 received by the pattern reception module 110 matches. Specifically, the final inspection result 162 is output using the logical relationship 136 between the character string collection area 132 and the regular expression area 134 which is another regular expression area. In the above example,
<< Yokohama | Kawasaki | Yokosuka >>>> (Other regular expressions)
Then, the logical relationship 136 is “|” (OR (logical sum)).

Hereinafter, the operation of the inspection result 162 integrated processing module 160 according to the logical relationship 136 will be described in detail.
(1) The logical relationship 136 for the results of the regular expression check (process by the regular expression check processing module 150) and the character string set check (character string set check processing module 140) is AND (logical product), and the regular expression check When it is performed before column set check: Determines whether the target character string matches the regular expression.
(A) If it matches a regular expression,
(A-1) If the character string set is matched, the inspection result 162 is output as a match.
(A-2) When the character string set does not match, the inspection result 162 is output as non-matching.
(A) If the regular expression does not match, the inspection result 162 is output as non-matching.

(2) When the logical relationship 136 for the result of the regular expression check and the character set check is OR, and the regular expression check is performed before the character set check Determines whether the target character string matches the regular expression To do.
(A) If the regular expression matches, the inspection result 162 is output as a match.
(B) If the regular expression does not match,
(A-1) If the character string set is matched, the inspection result 162 is output as a match.
(A-2) If the character string set does not match, the inspection result 162 is output as non-matching.

(3) When the logical relation 136 for the result of the regular expression check and the character set check is AND, and the regular expression check is performed after the character set check Determines whether the target character string matches the character set To do.
(A) If it matches the string set,
(A-1) If it matches the regular expression, the test result 162 is output as a match.
(A-2) If the regular expression does not match, the inspection result 162 is output as non-matching.
(A) When the character string set does not match, the inspection result 162 is output as non-matching.

(4) When the logical relationship 136 for the results of the regular expression check and the character set check is OR, and the regular expression check is performed after the character set check Determines whether the target character string matches the character set To do.
(A) If the character string set matches, the inspection result 162 is output as a match.
(B) If the string set does not match,
(A-1) If the regular expression matches, the inspection result 162 is output as a match.
(A-2) If the regular expression does not match, the inspection result 162 is output as non-matching.

FIG. 2 is a flowchart showing an example of processing according to this embodiment.
In step S202, the limited character string pattern receiving module 110 receives the limited character string pattern 108.
In step S <b> 204, the target character string receiving module 120 receives the target character string 118.
In step S206, the character string set extraction processing module 130 extracts the character string set region 132 from the limited character string pattern 108.
In step S <b> 208, the character string set extraction processing module 130 extracts the regular expression area 134 that is the remaining part of extracting the character string set area 132 from the limited character string pattern 108.
In step S210, the character string set extraction processing module 130 extracts the logical relationship 136 between the character string set area 132 and the regular expression area 134.
In step S212, the character string set inspection processing module 140 checks whether the target character string 118 matches the character string set area 132.
In step S214, the regular expression inspection processing module 150 checks whether the target character string 118 matches the regular expression area 134.
In step S216, the inspection result integration processing module 160 integrates the inspection result of the character string set inspection processing module 140 and the inspection result of the regular expression inspection processing module 150 according to the logical relationship 136, and outputs the inspection result 162.

In the above-described example, the character string collection area 132 is extracted from the text in the limited character string pattern 108. However, the present invention is not limited to this. Any method can be used as long as the character string collection area 132 and the regular expression area 134 can be separated.
For example, the character string collection area 132 and the regular expression area 134 may be separated with a time interval for acceptance. A regular expression input function and a character string set input function may be separately provided and separated.
More specific examples will be described with reference to FIGS. 25, 26, and 27. FIG. The limited character string pattern inspection processing module 2500 in the example of FIG. 25 includes a regular expression 2508 (a character string type described in a regular expression), a character string set 2518 (a portion that is a set of character strings in the regular expression 2508), The target character string 118 is received and the inspection result 162 is output.
It is determined whether or not the target character string 118 matches a character string in the character string set 2518. Then, it is determined whether or not the target character string 118 matches a regular expression 2508 other than the character string set 2518. Using these two determination results, it is determined whether or not the target character string 118 matches the regular expression 2508. In the above-described example, a part that is a set of character strings is extracted from the regular expression. However, in this example, the regular expression 2508 and the character string set 2518 are separated in advance, and processing using them.
Here, the limited character string pattern inspection processing performed by the limited character string pattern inspection processing module 2500 is used in place of the process of checking whether or not the regular expression matches in the above-described technique. By performing such a limited character string pattern inspection process, the character recognition result can be limited to a result that matches the limited character string pattern.
Hereinafter, “match” and “non-match” indicate either a complete inspection or a partial match inspection.
In the case of the present embodiment, the logical relationship between the regular expression check and the character string set check and the inspection order of the regular expression check and the character string set check are fixed.

The limited character string pattern inspection processing performed by the limited character string pattern inspection processing module 2500 is as follows.
(25-1) A case where the regular expression check is performed before the character string set check will be described with the logical relationship between the regular expression check and the character set check being the AND.
It is determined whether or not the target character string 118 matches the regular expression 2508.
(A) If it matches the regular expression 2508,
(A-1) When the character string set 2518 is matched, the inspection result 162 is output as a match.
(A-2) If the character string set 2518 is not matched, the inspection result 162 is output as a non-match.
(A) If the regular expression 2508 does not match, the inspection result 162 is output as non-matching.

(25-2) The case where the regular expression check is performed before the character string set check will be described using the logical relationship between the regular expression check and the character set check as the OR.
It is determined whether or not the target character string 118 matches the regular expression 2508.
(A) If the regular expression 2508 matches, the inspection result 162 is output as a match.
(A) If the regular expression 2508 does not match,
(A-1) When the character string set 2518 is matched, the inspection result 162 is output as a match.
(A-2) If the character string set 2518 is not matched, the inspection result 162 is output as a non-match.

(25-3) A case will be described in which the logical relationship between the regular expression check and the character string set check is AND, and the regular expression check is performed after the character string set check.
It is determined whether or not the target character string 118 matches the character string set 2518.
(A) If it matches the character string set 2518,
(A-1) If it matches the regular expression 2508, the inspection result 162 is output as a match.
(A-2) If the regular expression 2508 does not match, the inspection result 162 is output as non-matching.
(A) If the character string set 2518 does not match, the inspection result 162 is output as non-matching.

(25-4) A case will be described in which the logical relationship between the regular expression check and the character string set check is OR, and the regular expression check is performed after the character string set check.
It is determined whether or not the target character string 118 matches the character string set 2518.
(A) If the character string set 2518 is matched, the inspection result 162 is output as a match.
(A) If the character string set 2518 does not match,
(A-1) If the regular expression 2508 is matched, the inspection result 162 is output as a match.
(A-2) If the regular expression 2508 does not match, the inspection result 162 is output as non-matching.

The limited character string pattern inspection processing module 2600 in the example of FIG. 26 receives the logical relationship 2608, the regular expression 2508, the character string set 2518, and the target character string 118, and outputs the inspection result 162. That is, compared to the example of FIG. 25, a logical relationship 2608 between the regular expression check and the character string set check is added.
Here, the limited character string pattern inspection processing performed by the limited character string pattern inspection processing module 2600 is used in place of the process of checking whether or not a regular expression is matched in the above-described technique. By performing such a limited character string pattern inspection process, the character recognition result can be limited to a result that matches the limited character string pattern.
Hereinafter, “match” and “non-match” indicate either a complete inspection or a partial match inspection.
In the case of this embodiment, the regular expression check is fixed in the character string set check order.
As the logical relationship 2608, “AND” or “OR” is accepted.
The inspection order of regular expression inspection and character string set inspection is fixed.
For example, when the regular expression inspection is performed first, the internal operation of the limited character string pattern inspection processing is changed according to the logical relationship 2608. If it is AND, the above-described operation (25-1) is performed. If it is OR, the operation (25-2) described above is performed.
In addition, for example, when the regular expression check is performed later, the internal operation of the limited character string pattern check process is changed according to the logical relationship 2608. If it is AND, the above-described operation (25-3) is performed. If it is OR, the operation (25-4) described above is performed.

The limited character string pattern inspection processing module 2700 in the example of FIG. 27 receives the inspection order 2708, the logical relationship 2608, the regular expression 2508, the character string set 2518, and the target character string 118, and outputs the inspection result 162. That is, compared with the example of FIG. 26, the inspection order 2708 of the regular expression inspection and the character string set inspection is added.
Here, the limited character string pattern inspection processing performed by the limited character string pattern inspection processing module 2700 is used in place of the process of checking whether or not a regular expression is matched in the above-described technique. By performing such a limited character string pattern inspection process, the character recognition result can be limited to a result that matches the limited character string pattern.
Hereinafter, “match” and “non-match” indicate either a complete inspection or a partial match inspection.
As the logical relationship 2608, “AND” or “OR” is accepted.
As the inspection order 2708, “regular expression inspection is first” or “regular expression inspection is later” is accepted.
When the logical relationship 2608 is AND and the check order 2708 performs the regular expression check first, the above-described operation (25-1) is performed.
When the logical relationship 2608 is OR and the check order 2708 performs the regular expression check first, the above-described operation (25-2) is performed.
When the logical relationship 2608 is AND and the check order 2708 performs the regular expression check later, the above-described operation (25-3) is performed.
When the logical relationship 2608 is OR and the inspection order 2708 performs the regular expression inspection later, the operation (25-4) described above is performed.

Furthermore, the present invention may be applied when the Viterbi algorithm is used.
Assume that there are paths from node A, node B, and node C to node D as shown in the example of FIG.
Here, it is assumed that the limited character string pattern is “chemical meeting”. The case where the path is limited so as to be this character string pattern will be described. FIG. 28 shows an example of the intermediate stage.
As described above, in the Viterbi algorithm, the optimum path selection process is performed by limiting the number of nodes connected to the left from each node.
In the path from node A to node D, the number of paths from node A to the left is already limited to one. Therefore, when the path from node A to node D is selected, the path from the head to node D is determined, so the input character string can be determined. In this case, it is determined whether or not the input character string is “Higaku Gakkai” and this partially matches “Chemical Conference”.
In the path from node B to node D, as described above, the target character string is “Chemical Society”, and it is determined whether or not it partially matches “Chemical Conference”.
In the path from the node C to the node D, as described above, the target character string is “Japanese society”, and it is determined whether or not the character string partially matches the “chemical meeting”.
However, at the stage where the path to the left of the node A is determined, it is clear that the character string leading to the node A is “Higaku” and does not match the “chemical meeting”. For this reason, the process of comparing “Hyo Gakkai” with “Chemical Conference” is unnecessary.

Therefore, in the present embodiment, the following processing may be performed.
1. Each node of the Viterbi algorithm stores 1-bit information (match information) indicating whether the limited character string pattern is matched or not matched.
(A) When they match: The match information is turned ON.
(A) When they do not match: The match information is turned OFF.
2. Evaluate the path from the target node to the left node. This evaluation process is performed by the path limitation processing module 350 illustrated in FIG. 3 (such as the information processing apparatus illustrated in FIG. 1). At this time,
(A) If the match information of the left node is OFF, the limited character string pattern inspection process is not performed.
(A-1) Further, if the match information of all the left nodes is OFF, the match information of the target node is turned OFF.
(A) The limited character string pattern inspection process is performed only when the match information of the left node is ON.
(A-1) When the result of the limited character string pattern inspection process matches, the match information of the target node is turned ON.
(A-2) If the result of the limited character string pattern inspection process does not match, the match information of the target node is turned OFF.
(C) When the matching information of the target node is only one path, select that path. When there are two or more paths for which the match information of the target node is ON, as described above, the one having the highest evaluation value may be selected by a method different from the regular expression. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.
(D) Even when the match information of the target node is OFF, as described above, the one with the highest evaluation value may be selected by a method different from the regular expression. As the evaluation value here, for example, a method disclosed in JP 2012-118650 A may be used.

  With reference to FIG. 29, a hardware configuration example of the information processing apparatus according to the present embodiment will be described. The configuration shown in FIG. 29 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 2917 such as a scanner and a data output unit 2918 such as a printer.

  A CPU (Central Processing Unit) 2901 includes various modules described in the above embodiment, that is, a limited character string pattern reception module 110, a target character string reception module 120, a character string set extraction processing module 130, a character string set check. Processing module 140, regular expression inspection processing module 150, inspection result integration processing module 160, character string extraction module 320, cutout position extraction module 330, character candidate extraction module 340, path limitation processing module 350, network construction processing module 1910, node Number limit processing module 1920, control module 1930, output determination processing module 1940, limited character string pattern inspection processing module 2200, limited character string pattern inspection processing module A control unit that executes processing according to a computer program describing an execution sequence of each module such as the network rule 2500, the limited character string pattern inspection processing module 2600, and the limited character string pattern inspection processing module 2700.

  A ROM (Read Only Memory) 2902 stores programs used by the CPU 2901, operation parameters, and the like. A RAM (Random Access Memory) 2903 stores programs used in the execution of the CPU 2901, parameters that change as appropriate in the execution, and the like. These are connected to each other by a host bus 2904 including a CPU bus.

  The host bus 2904 is connected to an external bus 2906 such as a peripheral component interconnect / interface (PCI) bus via a bridge 2905.

  A keyboard 2908 and a pointing device 2909 such as a mouse are input devices operated by an operator. The display 2910 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 2911 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 2901 and information. The hard disk stores received images, character recognition results, character string patterns, network structures, target character strings, limited character string patterns, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 2912 reads data or a program recorded in a removable recording medium 2913 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and reads the data or program into an interface 2907 and an external bus 2906. , A bridge 2905, and a RAM 2903 connected via the host bus 2904. The removable recording medium 2913 can also be used as a data recording area similar to the hard disk.

  The connection port 2914 is a port for connecting an external connection device 2915 and has a connection unit such as USB or IEEE1394. The connection port 2914 is connected to the CPU 2901 and the like via the interface 2907, the external bus 2906, the bridge 2905, the host bus 2904, and the like. A communication unit 2916 is connected to a communication line and executes data communication processing with the outside. The data reading unit 2917 is a scanner, for example, and executes document reading processing. The data output unit 2918 is, for example, a printer, and executes document data output processing.

  Note that the hardware configuration of the information processing apparatus illustrated in FIG. 29 illustrates one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 29, and the modules described in the present embodiment are executed. Any configuration is possible. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line Alternatively, a plurality of systems shown in FIG. 29 may be connected to each other via a communication line so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

In the above-described embodiment, Japanese characters are shown as an object, but characters such as Chinese and English may be an object.
In the above-described embodiment, description has been made such that the left is the start point and the right is the end point, assuming a horizontally written character string. However, the above description also holds true for vertical writing and character strings written from right to left. For example, in the case of vertical writing, conversion may be performed in which “left” is “upper” and “right” is “lower”. In the case of a character string written from right to left, conversion may be performed with “left” as “right” and “right” as “left”.
In addition, although demonstrated using a numerical formula, the thing equivalent to the numerical formula is contained in a numerical formula. The equivalent includes not only the mathematical formula itself, but also transformation of the mathematical formula to the extent that the final result is not affected, or solving the mathematical formula by an algorithmic solution.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray Disc (registered trademark), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM (registered trademark)) )), Flash memory, Random access memory (RAM) SD (Secure Digital) memory card and the like.
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

DESCRIPTION OF SYMBOLS 108 ... Limited character string pattern 110 ... Limited character string pattern reception module 118 ... Target character string 120 ... Target character string reception module 130 ... Character string set extraction processing module 132 ... Character string set area 134 ... Regular expression area 136 ... Logical relationship 140 ... Character string set inspection processing module 150 ... Regular expression inspection processing module 160 ... Inspection result integration processing module 162 ... Inspection result 310 ... Image reception module 320 ... Character string extraction module 330 ... Cutout position extraction module 340 ... Character candidate extraction module 350 ... path limited processing module 360 ... output module 2200 ... limited character string pattern inspection processing module 2500 ... limited character string pattern inspection processing module 2508 ... regular expression 2518 ... character string set 2600 ... limited character string pattern Inspection processing module 2608 ... logical relationship 2700 ... limited character string pattern inspection processing module 2708 ... inspection order

Claims (5)

First receiving means for receiving a target character string;
Second receiving means for receiving a character string type described in a regular expression and a portion that is a set of character strings in the type;
First determination means for determining whether or not the character string received by the first reception means matches a character string in the set received by the second reception means;
A second determining unit that determines whether the character string received by the first receiving unit matches a type described by a regular expression other than the character string in the set received by the second receiving unit; A determination means;
The character string accepted by the first accepting means is the type of the character string accepted by the second accepting means using the judgment result by the first judging means and the judgment result by the second judging means. and third determination means for determining whether meets the,
Network generation means for generating a network by setting each character of a plurality of character recognition results as a node and building a link between nodes of adjacent character images;
Limiting means for limiting a link that connects to a node in the network generated by the network generating means from either the first direction or the last direction to a link that matches a predetermined character string pattern;
Storage means for storing a determination result by the third determination means in the node;
An output means for outputting a character candidate string in a path connected by a link limited by the limiting means as a character recognition result ;
The limiting means does not perform processing of whether or not the predetermined character string pattern is matched if the determination result in the storage means does not match when the link is limited. Information processing device. First receiving means for receiving a target character string;
A second accepting means for accepting a character string type described in a regular expression;
Extraction means for extracting a portion that is a set of character strings from the character string type received by the second reception means;
First determination means for determining whether or not the character string received by the first reception means matches the character string extracted by the extraction means;
Second determination means for determining whether or not the character string received by the first reception means matches a type described in a regular expression other than the character string extracted by the extraction means;
The character string accepted by the first accepting means is the type of the character string accepted by the second accepting means using the judgment result by the first judging means and the judgment result by the second judging means. and third determination means for determining whether meets the,
Network generation means for generating a network by setting each character of a plurality of character recognition results as a node and building a link between nodes of adjacent character images;
Limiting means for limiting a link that connects to a node in the network generated by the network generating means from either the first direction or the last direction to a link that matches a predetermined character string pattern;
Storage means for storing a determination result by the third determination means in the node;
An output means for outputting a character candidate string in a path connected by a link limited by the limiting means as a character recognition result ;
The limiting means does not perform processing of whether or not the predetermined character string pattern is matched if the determination result in the storage means does not match when the link is limited. Information processing device. The first determination means determines whether or not a portion continuous from the beginning of the character string received by the first reception means matches the character string extracted by the extraction means. The information processing apparatus according to claim 1 or 2. Computer
First receiving means for receiving a target character string;
Second receiving means for receiving a character string type described in a regular expression and a portion that is a set of character strings in the type;
First determination means for determining whether or not the character string received by the first reception means matches a character string in the set received by the second reception means;
A second determining unit that determines whether the character string received by the first receiving unit matches a type described by a regular expression other than the character string in the set received by the second receiving unit; A determination means;
The character string accepted by the first accepting means is the type of the character string accepted by the second accepting means using the judgment result by the first judging means and the judgment result by the second judging means. and third determination means for determining whether meets the,
Network generation means for generating a network by setting each character of a plurality of character recognition results as a node and building a link between nodes of adjacent character images;
Limiting means for limiting a link that connects to a node in the network generated by the network generating means from either the first direction or the last direction to a link that matches a predetermined character string pattern;
Storage means for storing a determination result by the third determination means in the node;
Function as output means for outputting the character candidate string in the path connected by the link limited by the limiting means as a character recognition result ,
In the case of limiting the link, the limiting unit does not perform processing of whether or not it matches the predetermined character string pattern if the determination result in the storage unit does not match
An information processing program characterized by that . Computer
First receiving means for receiving a target character string;
A second accepting means for accepting a character string type described in a regular expression;
Extraction means for extracting a portion that is a set of character strings from the character string type received by the second reception means;
First determination means for determining whether or not the character string received by the first reception means matches the character string extracted by the extraction means;
Second determination means for determining whether or not the character string received by the first reception means matches a type described in a regular expression other than the character string extracted by the extraction means;
The character string accepted by the first accepting means is the type of the character string accepted by the second accepting means using the judgment result by the first judging means and the judgment result by the second judging means. and third determination means for determining whether meets the,
Network generation means for generating a network by setting each character of a plurality of character recognition results as a node and building a link between nodes of adjacent character images;
Limiting means for limiting a link that connects to a node in the network generated by the network generating means from either the first direction or the last direction to a link that matches a predetermined character string pattern;
Storage means for storing a determination result by the third determination means in the node;
Function as output means for outputting the character candidate string in the path connected by the link limited by the limiting means as a character recognition result ,
In the case of limiting the link, the limiting unit does not perform processing of whether or not it matches the predetermined character string pattern if the determination result in the storage unit does not match
An information processing program characterized by that .

Images