KR102516990B1 - Device and method for processing text indexing through multi-image segmentation - Google Patents

Abstract

The present invention relates to a multi-image text processing apparatus, and more particularly, to a text index processing apparatus and method through multi-image segmentation capable of extracting and processing text from multi-images obtained by merging a plurality of scanned documents into a single file, and processing the same. It is about.
As described above, according to the present invention, page information for a single image divided from multi-images is generated, and the location and information of the text extracted by adding the generated page information to an index value is processed by page indexing for each single image, thereby obtaining information from the multi-images. It is possible to provide accurate search results to the user by providing the location and information of the extracted text in units of pages.

Description

Apparatus and method for processing text indexing through multi-image segmentation

The present invention relates to a multi-image text processing apparatus, and more particularly, to a text index processing apparatus and method through multi-image segmentation capable of extracting and processing text from multi-images obtained by merging a plurality of scanned documents into a single file, and processing the same. It is about.

BACKGROUND OF THE INVENTION [0002] In general, various services using the Internet have been provided due to the development and spread of the Internet, among which a representative example is a search service.

Such a search service is a service in which, when a user inputs a word or a combination of words to be searched for as a query, a search engine provides the user with search results corresponding to the inputted query.

In this way, in order to properly show the content that users want to search for, search service providers collect various electronic documents, extract document text from the collected electronic documents, index them based on them, and store them separately, Although it can be implemented to quickly provide users with search results for queries, it was not possible to extract and search images of documents in the same way as electronic documents.

To solve this inconvenience, it is possible to extract and index the text in the image through the OCR function. to provide a search function.

However, in the case of extracting text from multiple images created as a single file by scanning multiple documents and merging them, all images do not have page divisions, and text location information may be provided when indexing after text is extracted. Therefore, since the search efficiency is lowered, there is a problem in that a search function for multi-images cannot be provided.

For example, when indexing after extracting text from 1000 multi-images, it is difficult to estimate the position of the text on the image, resulting in a decrease in efficiency of the search engine.

Therefore, in the future, there is a demand for the development of a multi-image text processing apparatus capable of providing accurate search results to users by providing information and locations of texts extracted from multi-images in units of pages.

Republic of Korea Patent Publication No. 10-2019-0123790 (2019. 11. 01)

One object of the present invention to solve the above problems is to generate page information for a single image divided from multiple images, add the generated page information to an index value, and extract the location and information of text for each single image. It is to provide a multi-image text processing apparatus and method capable of providing accurate search results to users by providing the location and information of text extracted from multi-images in units of pages by performing page indexing.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

An apparatus for processing text indexing through multi-image segmentation according to an embodiment of the present invention for solving the above problems includes a conversion unit for converting multiple images into single images; an extraction unit extracting text from each single image; a storage unit for storing the extracted text; and generating page information for each single image, adding the generated page information to an index value, performing page indexing of the location and information of the extracted text for each single image, and adding the generated page information to an index value. and a control unit for storing location and information in the storage unit, wherein the control unit, when an acquired image is the multi-image obtained by merging a plurality of scanned documents and rescanning them into a single file, converts the image through the conversion unit. When converting a multi-image into each of the single images and processing a page index for each of the single images, when the location and information of the extracted text are equally present in a plurality of single images among the single images, the extraction It is characterized by indexing the location and information of the edited text as duplicate pages.

In this case, the conversion unit may set a division area from the multi-image, divide the multi-image according to the set division area, and convert each division area of the multi-image into each single image.

Also, when setting the division area from the multi-image, the conversion unit may set the division area according to a preset setting value. Also, when setting the division area from the multi-image, the conversion unit may set the division area according to a user input value.

In addition, the extraction unit includes an optical recognition module that performs an OCR (Optical Character Recognition) function, and when extracting text from each converted single image, at least one of letters, symbols, and numbers included in each single image. one can be extracted. In this case, the control unit may generate page information for each single image when the text of each single image is extracted. The control unit may control the extraction unit to generate page information for each single image when the extraction unit extracts the text of each single image.

In addition, when processing a page index for each single image, the control unit identifies a plurality of single images having the same position and information of the extracted text among the single images, based on preset priorities. In this way, it is possible to select any one of the plurality of identified single images, and to perform page index processing on the position and information of the extracted text as page information on the selected single image.

Meanwhile, a text index processing method through multi-image segmentation according to an embodiment of the present invention includes converting multiple images into single images; extracting text from each single image; generating page information for each single image; indexing the location and information of the extracted text for each single image by adding the generated page information to an index value; and storing the location and information of the page-indexed text, wherein the page-indexing step is the multi-image obtained by merging multiple scanned documents and rescanning them into a single file. In this case, when the multi-image is converted into each of the single images and the page index is processed for each of the single images, the location and information of the extracted text are equally present in a plurality of single images among the single images. , characterized in that the location and information of the extracted text are indexed as duplicate pages.

In addition, a computer program that provides a text index processing method through multi-image segmentation according to an embodiment of the present invention for solving the above problems is combined with a computer that is hardware to perform any one of the above methods. stored on a computer-readable recording medium for

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium recording a computer program for executing the method may be further provided.

As described above, according to the present invention, page information for a single image divided from multi-images is generated, and the location and information of the text extracted by adding the generated page information to an index value is processed by page indexing for each single image, thereby obtaining information from the multi-images. It is possible to provide accurate search results to the user by providing the location and information of the extracted text in units of pages.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a block diagram illustrating a multi-image text processing apparatus according to an embodiment of the present invention.
2 is a diagram for explaining multi-images.
3 is a diagram for explaining a single image.
4 is a flowchart illustrating a multi-image text processing method of a multi-image text processing apparatus according to an embodiment of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Prior to the description, the meaning of the terms used in this specification will be briefly described. However, it should be noted that the description of terms is intended to help the understanding of the present specification, and is not used in the sense of limiting the technical spirit of the present invention unless explicitly described as limiting the present invention.

1 is a block diagram for explaining a multi-image text processing apparatus according to an embodiment of the present invention, FIG. 2 is a diagram for explaining multi-images, and FIG. 3 is a diagram for explaining a single image. am.

As shown in FIG. 1, the multi-image text processing apparatus of the present invention includes an image acquisition unit 110 that acquires multi-images, an image conversion unit 120 that converts the acquired multi-images into a plurality of single images, and conversion Controls the text extraction unit 130 that extracts text from the single image, the text storage unit 140 that stores the extracted text, and the image conversion unit 120, the text extraction unit 130, and the text storage unit 140. It may include a control unit 150 to.

Here, the control unit 150 generates page information for each single image, adds the generated page information to an index value, processes the location and information of the extracted text for each single image, and processes the page indexed text. The text storage unit 140 may be controlled to store location and information.

In the present invention, as shown in FIG. 2 , a multi-image may refer to an image file obtained by scanning multiple documents and merging the scanned documents into a single file.

For example, multi-images, jpg, tif. It can contain multiple image files including png, etc.

Also, as shown in FIG. 3, a single image may include one image file divided from multiple images.

Also, the image conversion unit 120 may set division areas from the multi-images, divide the multi-images according to the set division areas, and convert each division area of the multi-images into one single image.

For example, the image conversion unit 120 may set the divided area according to a preset setting value when setting the divided area from the multi-image.

Here, the preset setting value may include the size and number of divided regions, which is only an example, but is not limited thereto.

As another example, the image converting unit 120 may set the split area according to a user input value when setting a split area from multiple images.

Here, the user input value may include the size and number of divided regions, which is only an example, but is not limited thereto.

Next, the text extractor 130 may include an optical recognition module that performs an OCR (Optical Character Recognition) function, which is only one embodiment, but is not limited thereto.

Also, when extracting text from the converted single image, the text extractor 130 may extract at least one of letters, symbols, and numbers included in the single image.

Next, the control unit 150 generates page information for each single image, adds the generated page information to an index value, processes the location and information of the extracted text for each single image, and processes the page indexed text. The text storage unit 140 may be controlled to store location and information.

Here, the controller 150 may control the image conversion unit 120 to convert the acquired multi-images into a plurality of single images when the image acquisition unit 110 acquires the multi-images.

In some cases, the controller 150, when the image acquisition unit 110 acquires the image, determines whether the acquired image is a multi-image, and if the acquired image is a multi-image, converts the multi-image into a plurality of single images. The conversion unit 120 may be controlled, and the text extraction unit 130 may be controlled to extract text from the image if the obtained image is not a multi-image.

In addition, the control unit 150 may control the text extraction unit 130 to extract text from the converted single image when the multi-image is converted into a plurality of single images by the image conversion unit 110 .

Further, the controller 150 may generate page information for the single image when the text of the single image is extracted.

Here, the controller 150 may generate page information for each single image when texts of all single images are extracted.

In some cases, the controller 150 may generate page information for a corresponding single image whenever the text of each single image is extracted.

As another case, the controller 150 may control the text extractor 130 to generate page information for the single image when the text extractor 130 extracts the text of the single image.

As such, according to the present invention, the control unit 150 may control generation of page information for each single image according to text extraction by the text extraction unit 130, while the text extraction unit 130 directly extracts text. It is also possible to create page information for each single image.

Accordingly, in the present invention, various design modifications are possible in generating page information for each single image.

Next, when page indexing is performed for each single image, the controller 150 may index the location and information of the extracted text as a duplicate page if the location and information of the extracted text overlap with a plurality of single images.

As another embodiment, when page indexing is performed for each single image, the controller 150 selects one of the plurality of overlapping single images when the location and information of the extracted text are duplicated in the plurality of single images, and selects the selected single image. The location and information of the text extracted as the page information for the image may be page indexed.

Here, the controller 150 may select any one of the plurality of overlapping single images according to a preset priority when selecting one of the plurality of overlapping single images.

As such, in the present invention, when the position and information of the extracted text are duplicated in a plurality of single images, various methods can be used for quick and fast indexing.

In addition, according to the present invention, by selecting any one of a plurality of overlapping single images according to priority and indexing the location and information of text extracted as page information for the selected single image, prompt search results are provided to the user. You may.

Next, when storing the location and information of the text indexed by the page, the control unit 150 may group and store the location and information of the text extracted from the single image for each multi-image as a group, which is only an example. It is not limited to this.

In this way, the present invention generates page information for a single image divided from multiple images, adds the generated page information to an index value, and processes the location and information of the extracted text by page indexing for each single image. It is possible to provide accurate search results to users by providing text location and information in units of pages.

4 is a flowchart illustrating a multi-image text processing method of a multi-image text processing apparatus according to an embodiment of the present invention.

As shown in FIG. 4 , the apparatus for processing multi-image text according to the present invention first acquires multi-images and converts the obtained multi-images into a plurality of single images (S10).

Here, the present invention, when converting a multi-image into a plurality of single images, sets a division area from the multi-image, divides the multi-image according to the set division region, and converts each division region of the multi-image into one single image. can be converted to

In this case, in the present invention, when setting a division region from multi-images, the division region may be set according to a preset setting value, or in some cases, the division region may be set according to a user input value.

And, in the present invention, text can be extracted from the converted single image (S20).

Next, the present invention may generate page information for each single image (S30).

Here, in the present invention, when the text of all single images is extracted, page information for each single image may be generated. Depending on the case, the present invention may generate page information for each single image whenever the text of each single image is extracted. You can also create page information about.

Subsequently, the present invention may add the generated page information to the index value and perform page index processing on the location and information of the extracted text for each single image (S40).

Here, in the present invention, when page indexing is performed for each single image, if the location and information of the extracted text overlap with a plurality of single images, the location and information of the extracted text can be indexed as a duplicate page.

In some cases, in the present invention, when page indexing is performed for each single image, if the position and information of the extracted text is duplicated in a plurality of single images, one of the plurality of overlapping single images is selected, and information about the selected single image is selected. The location and information of text extracted as page information may be page indexed.

Here, in the present invention, when selecting one of a plurality of overlapping single images, one of the plurality of overlapping single images may be selected according to a preset priority.

In addition, the present invention may store the location and information of the page indexed text (S50).

Here, in the present invention, when storing the location and information of the text indexed on a page, the location and information of the text extracted from a single image for each multi-image can be grouped and stored as a group, which is only one embodiment and is limited thereto. It doesn't work.

In this way, the present invention generates page information for a single image divided from multiple images, adds the generated page information to an index value, and processes the location and information of the extracted text by page indexing for each single image. It is possible to provide accurate search results to users by providing text location and information in units of pages.

The method according to an embodiment of the present invention described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The aforementioned program is C, C++, JAVA, machine language, etc. It may include a code coded in a computer language of. These codes may include functional codes related to functions defining necessary functions for executing the methods, and include control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. can do. In addition, these codes may further include memory reference related codes for which location (address address) of the computer's internal or external memory should be referenced for additional information or media required for the computer's processor to execute the functions. there is. In addition, when the processor of the computer needs to communicate with any other remote computer or server in order to execute the functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes for whether to communicate, what kind of information or media to transmit/receive during communication, and the like.

The storage medium is not a medium that stores data for a short moment, such as a register, cache, or memory, but a medium that stores data semi-permanently and is readable by a device. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers accessible by the computer or various recording media on the user's computer. In addition, the medium may be distributed to computer systems connected through a network, and computer readable codes may be stored in a distributed manner.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (10)

a conversion unit that converts multiple images into single images;
an extraction unit extracting text from each single image;
a storage unit for storing the extracted text; and
Page information for each single image is generated, and the location and information of the extracted text is page-indexed for each single image by adding the generated page information to an index value, and the location of the page-indexed text And a control unit for storing information in the storage unit;
The control unit,
When the acquired image is the multi-image obtained by merging a plurality of scanned documents and rescanning into a single file, converting the multi-image into each single image through the conversion unit;
When the page index is processed for each single image, if the location and information of the extracted text are equally present in a plurality of single images among the single images, the location and information of the extracted text are indexed as duplicate pages. Text indexing processing apparatus through multi-image segmentation, characterized in that for processing. According to claim 1,
The conversion unit,
Setting a division area from the multi-image, dividing the multi-image according to the set division area, and converting each division area of the multi-image into each single image. processing unit. According to claim 2,
The conversion unit,
Text indexing processing apparatus through multi-image division, characterized in that when setting the division region from the multi-image, the division region is set according to a preset setting value. According to claim 2,
The conversion unit,
Text indexing processing apparatus through multi-image division, characterized in that when setting the division region from the multi-image, the division region is set according to a user input value. According to claim 1,
The extraction part,
Includes an optical recognition module that performs an OCR (Optical Character Recognition) function,
When text is extracted from each converted single image, at least one of letters, symbols, and numbers included in each single image is extracted. According to claim 5,
The control unit,
When the text of each single image is extracted, the text index processing apparatus through multi-image segmentation, characterized in that for generating page information for each single image. According to claim 5,
The control unit,
When the extraction unit extracts the text of each single image, the apparatus for processing text indexing through multi-image segmentation, characterized in that for controlling the extraction unit to generate page information for each single image. According to claim 1,
The control unit,
When processing the page index for each single image, a plurality of single images having the same position and information of the extracted text among the single images are identified;
Selecting one of the identified multiple single images based on a preset priority,
Text indexing processing apparatus through multi-image segmentation, characterized in that for page indexing the position and information of the extracted text with page information for the selected single image. In the method performed by the text index processing apparatus through multi-image segmentation,
converting multiple images into single images;
extracting text from each single image;
generating page information for each single image;
indexing the location and information of the extracted text for each single image by adding the generated page information to an index value; and
Storing the position and information of the page indexed text;
The page index processing step,
When the obtained image is the multi-image in which a plurality of scanned documents are merged and rescanned as a single file, the multi-image is converted into each single image;
When the page index is processed for each single image, if the location and information of the extracted text are equally present in a plurality of single images among the single images, the location and information of the extracted text are indexed as duplicate pages. Text index processing method through multi-image segmentation, characterized in that the processing. delete

Images