JP2014154028A - Image processing device, image processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve efficiency of processing for improving accuracy of character recognition.SOLUTION: An image processing device comprises: a first extraction unit that executes character recognition processing on an image to extract a character; a determination unit that determines an area to be subjected to correction processing in the image on the basis of the extraction result of the extraction unit; a correction unit that executes the correction processing on the area determined by the determination unit; and a second extraction unit that executes character recognition processing on the image on which the correction processing is executed to extract a character.

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program.

  When performing character recognition processing on an image, character recognition accuracy can be improved by performing correction processing on the image in advance.

  However, since the correction processing is performed uniformly on the entire image, dirt, distortion, and the like of the image do not necessarily exist uniformly over the entire image. For example, a part of the image may be locally dirty or distorted.

  The present invention has been made in view of the above points, and an object of the present invention is to improve the efficiency of processing for improving character recognition accuracy.

  Therefore, in order to solve the above-described problem, the image processing apparatus executes a character recognition process on the image, and performs a correction process on the image based on a first extraction unit that extracts characters and an extraction result by the extraction unit. A determination unit that determines a region to be a target of the correction, a correction unit that performs correction processing on the region determined by the determination unit, and character recognition processing performed on the image on which the correction processing has been performed, And a second extraction unit for extracting characters.

  The processing for improving the character recognition accuracy can be made efficient.

It is a figure which shows the structural example of the delivery management system in 1st embodiment. It is a figure which shows the hardware structural example of the delivery management server in 1st embodiment. It is a figure which shows the function structural example of the image forming apparatus and distribution management apparatus in 1st embodiment. It is a flowchart for demonstrating an example of the process sequence which the delivery management server of 1st embodiment performs. It is a figure which shows the structural example of the delivery management system in 2nd embodiment. It is a figure which shows the function structural example of the image forming apparatus and distribution management apparatus in 2nd embodiment. It is a figure which shows the structural example of the delivery management system in 3rd embodiment. It is a figure which shows the function structural example of the image forming apparatus in 3rd embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram illustrating a configuration example of a distribution management system according to the first embodiment. In FIG. 1, the distribution management system 1 includes a distribution management server 10, one or more image forming apparatuses 30, a document management server 50, a mail server 60, and the like. Each device is communicably connected via a network such as a LAN (Local Area Network) or the Internet (whether wired or wireless).

  The image forming apparatus 30 is a device that reads image data to be distributed from a document. The distribution management server 10 is a computer that executes a preset workflow for image data read by the image forming apparatus 30. A workflow refers to, for example, a flow of processing realized by a combination of one or more processing units (tasks) that realize a function that is completed independently or independently. The processing unit may be applied to an activity in general workflow terms. In this embodiment, for the sake of convenience, character recognition processing (OCR (Optical Character Recognition) processing) is performed on image data, and text data obtained as a result of the character recognition processing is used as document management designated as a distribution destination. A case where a workflow to be transmitted to the server 50 or the mail server 60 is executed will be described.

  The document management server 50 and the mail server 60 are examples of computers that are distribution destinations in data distribution processing by the distribution management server 10. The document management server 50 is, for example, a computer having a database that manages data in association with its attribute information. When the document management server 50 is a distribution destination, the distributed data is stored in the database of the document management server 50. The mail server 60 is a computer that transfers electronic mail. When the mail server 60 is the distribution destination, the distributed data is attached to the e-mail and transferred to the e-mail address set in the executed workflow.

  FIG. 2 is a diagram illustrating a hardware configuration example of the distribution management server in the first embodiment. The distribution management server 10 in FIG. 2 includes a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, and the like that are mutually connected by a bus B.

  A program for realizing processing in the distribution management server 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 to the auxiliary storage device 102 via the drive device 100. However, the program need not be installed from the recording medium 101 and may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program and also stores necessary files and data.

  The memory device 103 reads the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program. The CPU 104 executes a function related to the distribution management server 10 according to a program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

  FIG. 3 is a diagram illustrating a functional configuration example of the image forming apparatus and the distribution management apparatus according to the first embodiment. In FIG. 3, the image forming apparatus 30 includes a reading unit 31, an image generation unit 32, a request transmission unit 33, and the like. Each of these units is realized by processing that one or more programs installed in the image forming apparatus 30 cause the image forming apparatus 30 to execute.

  The reading unit 31 controls a scanner or the like included in the image forming apparatus 30 to read a document. The image generation unit 32 generates image data based on the information read from the document by the reading unit 31. The request transmission unit 33 transmits a workflow execution request for the image data generated by the image generation unit 32 to the distribution management server 10. When reading a document, the user selects setting information for a workflow to be executed on image data, such as a distribution destination of image data. The request transmitted by the request transmission unit 33 includes selected setting information and the like together with image data.

  The distribution management server 10 includes a request reception unit 11, a character extraction unit 12, a correction area determination unit 13, an image correction unit 14, a distribution processing unit 15, and the like. Each of these units is realized by processing that one or more programs installed in the distribution management server 10 cause the CPU 104 to execute.

  The request receiving unit 11 receives a workflow execution request. The character extraction unit 12 extracts one or more characters from the image data included in the execution request. In FIG. 3, the character extraction unit 12 includes a character recognition unit 121, an extraction attribute generation unit 122, and the like. The character recognition unit 121 extracts one or more characters from the image data by character recognition processing. The extracted attribute generation unit 122 generates attribute information related to the character recognition process for each extracted character. As an example of the attribute information, there are a certainty factor, region information, and the like. The certainty factor is an index value indicating the certainty with respect to the extraction result. For example, when the extraction result is “A”, the certainty factor for the extraction result indicates the certainty that the character to be extracted is “A”. The area information is a coordinate value of an area or range where the extracted character is located in the image data. For example, the coordinate values of two diagonal vertices of a circumscribed rectangle (for example, the minimum circumscribed rectangle) surrounding the character may be used. The coordinate value is a coordinate value in a predetermined coordinate system for image data.

  Based on the result of the character recognition process, the correction area determination unit 13 determines an area to be corrected among the image areas indicated by the image data. The correction process refers to an image correction process for improving the accuracy of the character recognition process. In the present embodiment, an area where a character with low certainty is located is a target of correction processing. The correction process may be a known correction process such as noise removal or inclination correction.

  The image correction unit 14 performs correction processing on the region determined by the correction region determination unit 13. That is, the image correction unit 14 in the present embodiment does not set the entire image data as a processing target, but sets a part of the image data as a processing target.

  The distribution processing unit 15 distributes the text data extracted from the image data to the distribution destination included in the setting information specified in the workflow execution request. Image data may be distributed together with the result of the character recognition process.

  Hereinafter, a processing procedure executed by the distribution management server 10 will be described. FIG. 4 is a flowchart for explaining an example of a processing procedure executed by the distribution management server according to the first embodiment.

  In step S <b> 101, the request reception unit 11 receives a workflow execution request transmitted from the image forming apparatus 30. Subsequently, the character extraction unit 12 extracts one or more characters from the image data included in the execution request (S102). That is, the character recognition unit 121 extracts one or more characters from the image data using a character recognition technique. The extracted attribute generation unit 122 calculates a certainty factor and region information for each extracted character.

  Subsequently, the correction area determination unit 13 determines whether or not there is a character whose certainty factor is less than the threshold among the extracted characters (S103). When the corresponding character exists (Yes in S103), the correction area determination unit 13 determines the area indicated by the area information of the character as a target for the correction process (S104).

  Subsequently, the image correction unit 14 performs a correction process on the region (image region) determined by the correction region determination unit 13 (S105). That is, correction processing is executed for a part of the image data.

  In addition, when there are a plurality of characters having a certainty factor less than the threshold, the correction process is performed on the region indicated by the region information of each of the plurality of characters. At this time, if a plurality of regions are continuous, one correction process may be performed on a region obtained by integrating the plurality of regions (for example, a minimum circumscribed rectangular region of the plurality of regions). Furthermore, a plurality of regions may be integrated even if they are not continuous. For example, when the certainty factor is less than the threshold for every other character for a certain line, one correction process may be executed for the entire line.

  In addition, for each region, a correction process suitable for an aspect of image quality degradation such as dirt or distortion of an image in the region may be selected and executed. As a result, it is possible to expect improvement in character recognition accuracy by processing with a smaller load than when correction processing is executed uniformly on the entire image.

  Subsequently, the character extraction unit 12 extracts a new character from the image data after the correction process (S106). At this time, the area targeted for the character recognition process may be the same as the area targeted for the correction process in step S105. That is, the character recognition process in step S106 may be performed not on the entire image data but on a partial area of the image data. As a result, an increase in processing load caused by executing the character recognition process twice can be reduced.

  On the other hand, when there is no character whose certainty is less than the threshold (No in S103), steps 104 to S106 are not executed.

  Subsequently, the distribution processing unit 15 distributes text data, image data, and the like as a result of the character recognition process to the distribution destination included in the setting information designated in the workflow execution request (S107).

  As described above, according to the first embodiment, it is possible to limit the correction process for the image data to be subjected to the character recognition process to a partial area of the image data. As a result, the processing load due to the correction process can be reduced. In particular, when a large number of workflow execution requests are concentrated on the distribution management server 10, it can be expected that the effect of reducing the processing load becomes remarkable.

  Note that the area to be subjected to the correction process may be determined based on the unnaturalness of words, sentences, and the like that the extracted characters constitute. For example, if a particle that is highly likely to be misused or a word that is not included in dictionary data prepared in advance is detected, correction is performed on the particle or the region of the character that constitutes the word. Processing may be executed. This method may be performed together with a method of determining a region to be corrected based on the certainty factor.

  Next, a second embodiment will be described. In the second embodiment, differences from the first embodiment will be described. Accordingly, points not particularly mentioned may be the same as those in the first embodiment.

  FIG. 5 is a diagram illustrating a configuration example of a distribution management system according to the second embodiment. In FIG. 5, the same parts as those in FIG.

  In FIG. 5, the client terminal 40 is connected to the distribution management server 10 via a network. The client terminal 40 is a terminal such as a PC (Personal Computer) that transmits a workflow execution request to the distribution management server 10. That is, in the second embodiment, it is indicated that the transmission source of a workflow execution request (that is, image data) to the distribution management server 10 is not limited to the image forming apparatus 30. The client terminal 40 may be a tablet terminal, a smartphone, a mobile phone, or the like.

  FIG. 6 is a diagram illustrating a functional configuration example of the image forming apparatus and the distribution management apparatus according to the second embodiment. In FIG. 6, the same parts as those in FIG. 3 are denoted by the same reference numerals, and the description thereof is omitted.

  In FIG. 6, the client terminal 40 includes an image input unit 41, a request transmission unit 42, and the like. Each of these units is realized by processing that one or more programs installed in the client terminal 40 cause the client terminal 40 to execute.

  The image input unit 41 receives input of image data to be processed in the workflow from a user or the like. For example, the image input unit 41 monitors a predetermined folder in the auxiliary storage device included in the client terminal 40. When a file storing image data is stored in the folder, the image input unit 41 recognizes the image data as a workflow target.

  The request transmission unit 42 transmits to the distribution management server 10 a workflow execution request relating to the image data that the image input unit 41 has accepted. Note that the setting information specified in the execution request may be specified, for example, by inputting a file including the setting information together with image data.

  In the second embodiment, the processing procedure executed by the distribution management server 10 may be the same as in the first embodiment.

  As described above, according to the second embodiment, the same effect as that of the first embodiment can be obtained with respect to the correction processing for image data transmitted from other than the image forming apparatus 30.

  The first embodiment and the second embodiment may be combined. That is, the client terminal 40 and the image forming apparatus 30 may exist simultaneously.

  Next, a third embodiment will be described. In the third embodiment, differences from the first embodiment will be described. Accordingly, points not particularly mentioned may be the same as those in the first embodiment.

  FIG. 7 is a diagram illustrating a configuration example of a distribution management system according to the third embodiment. In FIG. 7, the same parts as those in FIG.

  In FIG. 7, the distribution management server 10 is not connected to the network. The image forming apparatus 30 is replaced with an image forming apparatus 30a.

  FIG. 8 is a diagram illustrating a functional configuration example of the image forming apparatus according to the third embodiment. 8, parts that are the same as the parts shown in FIG. 3 are given the same reference numerals, and explanation thereof is omitted.

  As shown in FIG. 8, the image forming apparatus 30a has the functions of the image forming apparatus 30 and the distribution management server 10 in the first embodiment. That is, the third embodiment indicates that the image forming apparatus 30 may also serve as the distribution management server 10. The image forming apparatus 30 a may receive a workflow execution request from another image forming apparatus 30.

  In the third embodiment, the processing procedure executed by the image forming apparatus 30a in response to the workflow execution request may be the same as the processing procedure executed by the distribution management server 10 in the first embodiment.

  Note that the client terminal 40 in the second embodiment may also have the function of the distribution management server 10.

  As described above, according to the third embodiment, the same effects as those of the first embodiment can be obtained even when correction processing is executed in the image forming apparatus 30a.

  In each of the above embodiments, the distribution management server 10 and the image forming apparatus 30a are an example of an image processing apparatus. The character extraction unit 12 is an example of a first extraction unit and a second extraction unit. The correction area determination unit 13 is an example of a determination unit. The image correction unit 14 is an example of a correction unit.

  As mentioned above, although the Example of this invention was explained in full detail, this invention is not limited to such specific embodiment, In the range of the summary of this invention described in the claim, various deformation | transformation・ Change is possible.

DESCRIPTION OF SYMBOLS 1 Distribution management system 10 Distribution management server 11 Request receiving part 12 Character extraction part 13 Correction area determination part 14 Image correction part 15 Distribution processing part 30 Image forming apparatus 31 Reading part 32 Image generation part 33 Request transmission part 40 Client terminal 41 Image input Unit 42 Request transmission unit 50 Document management server 60 Mail server 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 CPU
105 interface device 121 character recognition unit 122 extraction attribute generation unit B bus

Japanese Patent Laid-Open No. 10-011528

Claims (5)

A first extraction unit that performs character recognition processing on the image and extracts characters;
A determination unit that determines a region to be corrected in the image based on an extraction result by the extraction unit;
A correction unit that executes correction processing on the area determined by the determination unit;
An image processing apparatus comprising: a second extraction unit that performs character recognition processing on the image subjected to the correction processing and extracts characters.   The image processing apparatus according to claim 1, wherein the determination unit determines an area to be corrected in the image based on a certainty factor for each character generated in the character recognition process.   The image processing apparatus according to claim 1, wherein the second extraction unit performs a character recognition process on the area determined by the determination unit. A first extraction procedure for performing character recognition processing on the image and extracting characters;
A determination procedure for determining a region to be corrected in the image based on an extraction result by the extraction unit;
A correction procedure for performing correction processing on the area determined by the determination unit;
An image processing method in which a computer executes character recognition processing on an image on which the correction processing has been executed, and a second extraction procedure for extracting characters. A first extraction procedure for performing character recognition processing on the image and extracting characters;
A determination procedure for determining a region to be corrected in the image based on an extraction result by the extraction unit;
A correction procedure for performing correction processing on the area determined by the determination unit;
A program that causes a computer to execute a character extraction process on an image that has been subjected to the correction process, and to extract a character.

Images