JP2002163282A - Retrieving system, filing system and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a retrieving system or the like capable of easily inputting a retrieval keyword or the like corresponding to an image, and taking the image of a desired document by the keyword retrieval. SOLUTION: Characters in the image are recognized by reading an image file (S110), and the recognized characters are written in a cache (S120). Whether a character string agreed with the retrieval keyword exists in the cache or not is retrieved (S130), the image is displayed on a display (S150) when the agreed character string exists, and in a case when the agreed character string does not exist, the processing is transferred to S160 when the retrieval processing in the image file is finished, and transferred to S120 to recognize the next character when the retrieval processing in the image file is not finished. In S160, the processing is finished on the basis of the finish instruction from a user, or the completion of reading all of the image files. On the other hand, when the instruction by the user or the completion of reading all of the image files does not exist, a read object is set in the next image file and the processing is returned to S110. As the retrieving is executed while recognizing the characters in the image file, it is not troublesome.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a search system for searching for a character string included in image information and a filing system provided with the search system.

[0002]

2. Description of the Related Art Conventionally, a document or the like printed on paper or the like is read by a scanner,
There is known a filing system which can store image information (image information) and display or print the stored image information as needed.

[0003] In such a filing system, in order to make it easy to retrieve image information corresponding to a desired document from stored image information, there is a system in which image information can be searched for by using a keyword. In such a system, when an image including a document printed on paper or the like is captured and stored in a computer, a search keyword indicating the content of the read document is input from a keyboard or the like, and the input search keyword is converted into image information. Is stored in association with. When a user searches for image information of a required document, the user inputs a keyword indicating the content of the document to be searched, and the system compares the keyword with the stored search keyword to obtain a keyword. Outputs image information with a search keyword that matches. Therefore, when the search keyword input when storing the image information of the document is not sufficiently input as information indicating the document, the keyword does not match the search keyword, and the desired keyword is not obtained. The image information of the document cannot be extracted. Unless an accurate search keyword indicating the content of the document is input, the search keyword does not match the keyword entered by the user, and the image information is not stored and used. I do. Further, there is a problem that it is very troublesome to input such a search keyword for each image information of each document.

On the other hand, there is known an OCR (optical character reader) which reads a document as image information, converts the image information into text information, and stores the text information. Such an OCR converts all the image information into text information. It is also being converted and saved. With such a method, it is not necessary to register a keyword in advance, and a document can be searched with a free keyword. However, the OCR generally has a recognition rate of about 95% to 99%, and stores only the converted text information. Therefore, in order to retain the contents of the document, the converted text information is stored in the contents of the document. There is a problem that the user has to check and correct the converted text information so that the text information matches. Such an effort becomes enormous as the number of documents to be imported increases.

[0005] Therefore, the present invention does not require time and effort for input,
It is an object of the present invention to provide an image information search system capable of extracting a desired document and a filing system provided with the search system.

[0006]

According to a first aspect of the present invention, there is provided a search system for performing a recognition process at the time of a keyword search and including an input search keyword. Image information or information for specifying the image information is output.
Therefore, it is not necessary to input a search keyword for each document in advance, and it is not necessary to convert the documents into text information by OCR in advance. That is, a keyword included in the stored image information can be directly searched for by a keyword. That is, a desired document can be extracted as image information without having to input a search keyword corresponding to the image information in advance or modifying text converted by OCR.

[0007] Recognition processing for image information being recognized is stopped when it is determined that a search keyword is included. That is, subsequent recognition processing is not performed on the image information being recognized. Therefore, at that time, it is possible to proceed to another process such as, for example, reading another image information and performing a search process. Note that the information for specifying the image information includes, for example, information indicating a location where the image information is stored, a file name, character information up to the time when recognition is completed, and the like.

If there is a part which cannot be converted from the image information into the text information,
That part may be ignored and the recognition process may proceed. In this way, the search can be continued even if there is image information having a part that cannot be recognized. In addition,
Image information having a part that could not be recognized may be output to a display device or the like together with the fact that there was a part that could not be recognized.

[0009] The image information may be composed of, for example, one image file or a plurality of image files. Further, one image file may be, for example, a file obtained by reading one sheet of paper (document) by a scanner, or a file obtained by reading a plurality of sheets of paper as one image file.

It is preferable that a plurality of related image information is stored as a set of image information as described in claim 3, and the set is read out and searched for. That is, for example, when performing a search, a set of image information of the first document group, a set of image information of the second document group, a set of image information of the third document group,. When a set of image information is stored in the image information storage means, the image information is read out and searched for each set of image information of each document group. That is, from the set of image information of the first document group, for example, the image information of the first document, the image information of the second document,... A search for a set of image information of the second document group is performed at the stage where it is found. That is,
It is possible to search whether or not a keyword is included in each set of image information. Therefore, for example, if there is a keyword in the image information of the first document of the first document group, then the second image information of the first document group, the third image information,. It is possible to prevent the search from being duplicated. That is, high-speed search can be performed without searching for unrecognized image information included in the set of image information determined to include the keyword. In this way, for example, when the parallel processing is performed as in claim 4, the image information of each document group can be searched simultaneously, and a plurality of image information in the image information of one document group can be retrieved. There is no waste of searching at the same time.

Claim 4 shows that the processing of different means may be performed in parallel (parallel), or the processing of the same means may be performed in parallel (parallel). For example, the recognition target image reading means reads a plurality of pieces of image information in parallel, and the character recognition means recognizes the plurality of pieces of image information in parallel. And the keyword are determined in parallel to determine whether or not they match each other to obtain a search result. For example, the character recognition unit divides one piece of image information to be recognized into a plurality of areas and performs parallel processing. It is good to perform recognition. By doing so, recognition and search can be performed simultaneously and in parallel, so that search results can be obtained at higher speed.

A first system group including an image information storage unit, a recognition target image reading unit, and a character recognition unit, and a second system group including a search keyword input unit and a search unit.
May be provided, and the first system group and the second system may be connected to each other via a network to perform distributed processing (parallel processing). The first system group may be provided with the function of the second system. In this way, the load can be distributed and the search can be performed at higher speed.

[0013] Further, as described in claim 5,
The recognition result once recognized may be stored, and a search may be performed using the stored recognition result. By doing so, it is not necessary to perform character recognition again on image information that has been subjected to character recognition once, so that the more the search is performed, the faster the search can be performed.

Note that storing in association with image information also includes a case where information including a position at which the recognition is completed is also stored. In this case, the next time a keyword search is performed from the same image information, the search means
First, the stored recognition result is searched up to the position where the recognition is completed, and the portion after that position is recognized by the recognition means, and the recognition result is searched. These processes may be performed in parallel. That is, while the character recognizing unit performs the recognition, the retrieving unit may search in parallel for the character stored in the recognition result storage unit and the character recognized by the character recognizing unit.

Now, in such a system, claim 6
The search may be performed at any time in place of the high-performance character recognition means as shown in FIG. For example, if the character recognition means is constituted by hardware, the hardware can be replaced. If the character recognition means is realized by processing by software, the software can be replaced. Thus, for example, it is possible to change to a character recognizing unit having a high recognition rate according to the image information to be recognized. For example, when searching for a legal document, the character recognition unit is switched to a character recognition unit with a high recognition rate for a legal document. In the case of a handwritten character, the character recognition unit is switched to a character recognition unit with a high recognition ratio for a handwritten character. In addition, the character recognition means may be updated or changed via a network, for example. In particular, since the present system performs character recognition at the time of a search, in this way, a search can be performed using an optimal character recognition means at the time of a search. Since the recognition rate of the character recognition means can be expected to improve year by year, the recognition accuracy is higher than when converting the text information in advance at the time of capturing the image information as in the conventional OCR, and the search accuracy can be improved. .

The above-described search system can also search for image information input from a network or a recording medium, for example. According to the seventh aspect, it is possible to obtain a filing system that captures a document written on paper as image information and displays a result of a search performed on the image information. The search result may be transmitted via a network without being displayed. Alternatively, printing may be performed by a printer or the like. Also, the search keyword input means,
A keyboard provided in such a system may be used,
It may be input via a network.

In addition, as shown in claim 8, claim 1 to claim 1
The function of realizing each means described in 7 by a computer is as follows.
For example, it can be provided as a program to be activated on a computer. In the case of such a program, for example, it is recorded on a computer-readable recording medium such as a floppy (registered trademark) disk, a magneto-optical disk, a CD-ROM, and a hard disk, and is loaded into a computer system as needed and activated. Can be used. In addition, since each unit may constitute a search system or a filing system as a whole, each unit may be realized by a plurality of computers. For example, each means may be realized by a different computer.

[0018]

Embodiments of the present invention will be described below with reference to the drawings. It is needless to say that the embodiments of the present invention are not limited to the following examples, and can take various forms as long as they belong to the technical scope of the present invention.

FIG. 1 shows a filing system 1 according to the present embodiment.
Is shown. Filing system 1 is a personal computer 1
1, a display 12, a keyboard 13, a mouse 14, a scanner 15, and a printer 1 connected to a personal computer 11.
6 is a computer system including a personal computer 11
Is a communication interface connectable to the network 50, a hard disk for recording data,
M, RAM, I / O, etc., display 12, keyboard 13, mouse 14, scanner 15, printer 16
And so on.

The scanner 15 has an ADF (Auto Document Feeder), and can continuously read a set document and output it to the personal computer 11 as image data. When a document to be read is set on the scanner 15 and the scan start button of the scanner 15 is pressed, the scanner 15 transmits to the personal computer 11 a notification that a reading instruction has been input. Then, the personal computer 11 outputs an image reading instruction to the scanner 15. Then, the scanner 15 scans the set documents one after another by the sensor to generate image data of the documents, and transmits the image data to the personal computer 11. The personal computer 11 stores the image data transmitted from the scanner 15 on the hard disk as an image file in a predetermined format (for example, a compression format such as JPEG or PNG). One image file is stored for each document.

The image file of the document including the search keyword can be searched from the image file recorded in this way. This search process is a process of searching the hard disk for an image file including characters of a keyword input via the keyboard 13, the network 50, or the like. The flow of the keyword search process will be described with reference to the flowchart of FIG.

In S110 of FIG. 2, the image file is read from the hard disk, developed as an image, and read into the memory. In S120, the characters in the image on the memory are recognized by a known recognition algorithm, and the characters of the recognition result are written to the cache.

In S130, a search is made to determine whether a character string that matches the search keyword exists in the cache. In S140, it is determined whether or not there is a character string that matches the keyword as a result of the search. If there is a character string that matches the keyword (S140: YES), the process proceeds to S150 and the character string that matches the keyword is determined. If there is no (S140:
NO), and it transfers to S145.

In S145, it is determined whether or not all of the character recognition and search processing in the image file being processed have been completed. If the processing has been completed (S145: YES), S160 is performed.
If the process has not been completed (S145: N
O) The process proceeds to S120 to recognize the next character.

In S150, the image determined to include the character string matching the keyword in S140 is displayed on the display 12. In S160, it is determined whether a user's termination instruction has been input and whether all of the image files to be searched stored in the hard disk have been read in S110. When the reading has been performed for all the data (hereinafter, referred to as a case where the processing is completed) (S160: YES), the search processing is ended. On the other hand, if the end instruction of the user has not been input and the processing of the image file has not been completed, the reading target is set to the next image file, and the process returns to S110 to perform the same search processing.

Character recognition is performed one character at a time from the head of the document (image) (the head is determined by a known method), the character of the recognition result is written to the cache, and the subsequent character is recognized. Writing the character to the cache is repeated to form a character string in the cache. Then, it is determined whether or not there is a character string that matches the keyword with respect to the character string. If the character string matches, the recognition is terminated at that point, and the corresponding image file is read and displayed. If there is an unrecognizable character, that part is ignored and recognition and search are continued. If there is a character string that matches the keyword as described above, the recognition process is stopped. For example, if there is a character string that matches the keyword at a position 10% from the beginning of the image, the remaining 90% Do not perform recognition processing. Therefore, a search can be performed faster than recognizing the entire image.

In this way, a keyword search can be performed while reading an image file and performing character recognition at the time of search. Therefore, it is not necessary to input a search keyword or correct after OCR as in the related art, and an image file of a desired document can be searched for and extracted using an arbitrary character string as a keyword. Therefore, the captured and stored image file is effectively used.

In the embodiment, the keyboard 13 corresponds to a search keyword input unit, and the hard disk of the personal computer 11 corresponds to an image information storage unit. Also,
The image file corresponds to the image information, and S1 in FIG.
Step 10 corresponds to processing as a recognition target image reading unit, step S120 corresponds to processing as a character recognition unit, and step S130 corresponds to processing as a search unit. The scanner 15 corresponds to a reading unit, and the display 12 corresponds to a display unit. [Another embodiment] (1) In the above embodiment, the image file is stored in the scanner 1
5, but may be input via the network 50, or may be generated from a CDROM or DV.
Alternatively, the information may be input from a recording medium such as D. Also,
Although the image of the search result is displayed on the display 12, it may be output to the printer 16. (2) In the above embodiment, the search keyword is set to the keyboard 1
3, but may be input via the network 50. For example, the personal computer 11 is caused to function as a search server, a search keyword is input from a client personal computer connected to the network 50, and the search result is transmitted to the client personal computer. In this way, an image file of a desired document can be searched from a personal computer connected to the network 50. (3) Character recognition processing in the image (S120 in FIG. 2)
The search process for the keyword of the character string in the cache (S130 in FIG. 2) may be performed in parallel (parallel). For example, a recognition processing thread for performing a recognition process and a keyword search thread for performing a keyword search are executed in parallel. If the keyword search processing thread determines that the keyword matches, an end message is sent to the recognition processing thread to perform the recognition. When the processing thread receives the end message, the processing thread ends the recognition processing. (4) In addition to the above (3), the entire process of FIG. 2 may be executed in parallel (for example, by multithreading). That is, a keyword search process is performed on a plurality of image files simultaneously. By doing so, image files that match the keyword are output in order. If these threads are executed by a plurality of different CPUs, the processing speed is increased. Also, as shown in FIG. 3, the plurality of servers 20 read the image file stored in the personal computer 11 via the network (corresponding to S110), execute the recognition processing of S120, and execute the cache processing of the personal computer 11. The search may be performed by sending the character of the recognition result to the PC 11 via the network 50 and executing the processing of S130 to S160 on the personal computer 11. Generally, the recognition processing in S120 takes a long processing time, and thus, by distributing the processing to a plurality of servers 20, a higher-speed search can be realized. (5) In the above embodiment, one file is used for one document. However, a set of related documents (for example, one book, one report, etc.) is collectively stored as one image. Alternatively, a search may be performed. In this way, a search is performed from the beginning for each set of documents. In particular, when searching in parallel as in the above (3) and (4), the search processing is performed in parallel for each set of documents.

On the other hand, one image file may be generated for one document, and a set ID may be assigned to each set of documents and recorded in each image file.
The set ID is information indicating a related document including a plurality of documents such as a book or a report.
For example, when a document set at one time is scanned by a scanner, the same set ID may be automatically recorded in an image file generated by the scan,
The scanned image data may be displayed on the display 12, and the user may select a set of images using the mouse 14 or the like, and record the same set ID as the set of image files. Thus, a plurality of image files in which the set ID is recorded are recorded on the hard disk. When the search processing is performed in parallel, image files having different set IDs are simultaneously searched. If you do this,
Multiple sets of documents can be searched concurrently. (6) In the above embodiment, the recognition process (the process of S120) is performed every time the image file stored in the hard disk is searched for. However, for the image file that has been recognized once, the characters of the recognition result are replaced with characters. It is preferable that the image file is stored in a hard disk as a recognition result storage means in association with the image file, and the character stored in the hard disk is searched for when the next search is performed. That is, as shown in FIG. 4, the process of storing the recognized text in S147 is added to the keyword search process of FIG. 2, and the recognized character (text) is stored in the hard disk. When a search is performed on the same image file as the image file stored in association in this way, it is determined in S101 that the text corresponding to the image file to be searched has been stored (S101:
YES), a keyword search is performed for the stored text in S103. Then, it is determined whether or not the keyword matches the keyword in S105. If the keyword matches (S105: YES),
The process proceeds to S150 to display the corresponding image. If they do not match (S105: NO), the process proceeds to S160. By doing so, it is not necessary to recognize the image file once recognized again, and the keyword search can be performed at high speed.

Further, when a keyword is found during the recognition, that is, in the case of S140: YES in FIG. 5, the text up to the recognized position and the information on the position where the recognition of the image file is completed are stored. You may make it. In this case, the next time the same image file is searched, the search is performed from the stored text up to that position, and the search is performed by performing recognition processing from the subsequent positions. Good. This eliminates the need to re-recognize a part that has been recognized once, making it possible to search at a higher speed. (7) In the above embodiment, the keyword search process may be further stopped when a stop instruction is input from the user. In this way, for example, when the user enters a search keyword by mistake, or when it is sufficient to find some image files including the search keyword, the search process is performed to the end. Can be prevented, and the system becomes easy to use. (8) In the above embodiment, the program for performing the recognition processing in S120 in FIG. 2 may be downloaded from a center (not shown) via the network 50 connected to the Internet. The center always improves the performance of the program that performs this recognition processing. In this way, the search can be performed using the latest recognition processing program at the time of the search.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a configuration of a filing system according to an embodiment.

FIG. 2 is a flowchart illustrating a keyword search process according to the embodiment.

FIG. 3 is a diagram illustrating a configuration of a filing system according to another embodiment.

FIG. 4 is a flowchart illustrating a keyword search process according to another embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Filing system 11 ... Personal computer 12 ... Display 13 ... Keyboard 14 ... Mouse 15 ... Scanner 16 ... Printer 20 ... Server 50 ... Network

Claims (8)

[Claims] A search keyword input unit for inputting a search keyword; an image information storage unit for storing a plurality of image information; and image information to be recognized among the plurality of image information stored in the image information storage unit. A character recognition unit for sequentially recognizing characters included in the image information read by the recognition target image reading unit; and a recognition result input by the search keyword input unit to a recognition result of the character recognition unit. If the search keyword is included, the sequential recognition of the character recognizing unit is stopped, and the image information read by the recognition target image reading unit or a search unit that outputs information for specifying the image information is included. A retrieval system characterized by comprising: 2. The retrieval system according to claim 1, wherein said character recognizing means ignores a part which cannot be converted from said image information into said character and continues the recognition. Search system. 3. The search system according to claim 1, wherein the image information storage unit stores a plurality of related image information as a set, and the recognition target image reading unit includes the recognition target image reading unit. A retrieval system, wherein said image information is read out in sets as target image information. 4. The search system according to claim 1, wherein at least two of the recognition target image reading means, the character recognition means, and the search means perform processing in parallel. Or at least one of the recognition target image reading means, the character recognition means, and the search means executing the processing as the means in parallel. A search system characterized by the following. 5. The search system according to claim 1, further comprising: a recognition result storage unit that stores a recognition result of the character recognition unit in association with image information to be recognized. Is a search system characterized in that a search is performed with priority given to the recognition results stored in said recognition result storage means. 6. A search system according to claim 1, wherein said character recognition means is replaceable. 7. A filing system provided with the retrieval system according to claim 1, wherein a paper surface is read by a sensor to generate image information, and the generated image information is stored in the image information storage means. A filing system, comprising: a reading unit that performs reading; and a display unit that displays the image information output by the searching unit or information for specifying the image information. 8. A computer-readable recording medium in which a program for causing a computer to function as each means in the search system or filing system according to claim 1 is recorded.