JP2016054564A5 - - Google Patents

Description

However, in the prior art, for each of a plurality of character regions, it is determined whether the character region is a character region to be subjected to binary compression, and character recognition processing is performed on each of the plurality of character regions. And, according to the determination result for each of the plurality of character areas, the binary compression is performed on the character areas determined to be subjected to the binary compression among the plurality of character areas. I did not do it.

An image processing apparatus according to the present invention includes a processing unit that performs a predetermined process for specifying a character region, a character recognition processing unit that performs a character recognition process, and binary compression on an image obtained based on reading of a document. And a binary compression unit that performs binary compression on each of a plurality of character regions specified from the image by the processing unit performing the predetermined process. Determining means for determining whether the character area is to be performed, and performing character recognition processing by the character recognition processing means for each of the plurality of character areas, and according to the determination result for each of the plurality of character areas, among a plurality of character areas, and a control means for binary compression against determined character area and should be done, to perform binary compression by the binary compression means, Characterized in that it has.

Character recognition processing is performed on each of a plurality of character areas, and binary compression is performed on a character area that is determined to be subjected to binary compression among the plurality of character areas. it can.

Claims (21)

A processing unit that performs a predetermined process for specifying a character region, a character recognition processing unit that performs a character recognition process, and a binary compression unit that performs binary compression on an image obtained based on reading of a document. In an image processing apparatus having
Determining means for determining whether the character area is a character area to be subjected to binary compression for each of a plurality of character areas specified from the image by the processing means performing the predetermined processing; ,
Character recognition processing by the character recognition processing unit is performed for each of a plurality of character areas, and binary compression should be performed among the plurality of character areas according to the determination result for each of the plurality of character areas. Control means for performing binary compression by the binary compression means on a character area determined to be present;
An image processing apparatus comprising: Having multi-value compression means for performing multi-value compression,
The control means performs the multi-value compression by the multi-value compression means without performing the binary compression by the binary compression means for the character area determined by the determination means that the binary compression should not be performed. The image processing apparatus according to claim 1, wherein: The image processing apparatus according to claim 2, wherein the control unit performs multi-value compression on the image by the multi-value compression unit. 4. The determination unit according to claim 1, wherein the determination unit determines that a character region in which a density difference between a background and a character is less than a threshold is a character region that should not be subjected to binary compression. The image processing apparatus according to item. The determination unit determines that a character region in which a character darker than the background is included in a portion having a background darker than a threshold is a character region that should not be subjected to binary compression. Item 4. The image processing device according to any one of Items 1 to 3. The determination unit determines that the character region is a character region that should not be subjected to binary compression when the edge pixels that are equal to or greater than the threshold number are included in a portion darker than the threshold value in the character region. The image processing apparatus according to claim 1, wherein the image processing apparatus is characterized. The determination unit determines that the character region is a character region where a binary image is to be performed when an edge pixel is included in a portion darker than the threshold value in the character region and less than the threshold number. The image processing apparatus according to claim 6. The control means includes at least a result of character recognition processing for each of the plurality of character regions, a result of binary compression for the corresponding character region of the plurality of character regions, and a result of multi-value compression of the image. The image processing apparatus according to claim 1, wherein the image processing apparatuses are combined into a file having a predetermined format. The image processing apparatus according to claim 8, wherein the control unit also collects the result of multi-value compression of the image into the file. The image processing apparatus according to claim 8, further comprising a transmission unit configured to transmit the file to an external apparatus. A processing process for performing a predetermined process for specifying a character area, a character recognition processing process for performing a character recognition process, and a binary compression process for performing binary compression on an image obtained based on reading of a document. In an image processing method having
A determination step of determining whether the character region is a character region to be subjected to binary compression for each of a plurality of character regions specified from the image by performing the predetermined processing in the processing step; ,
Character recognition processing by the character recognition processing step is performed for each of a plurality of character areas, and binary compression should be performed among the plurality of character areas according to the determination result for each of the plurality of character areas. A control step of performing binary compression by the binary compression step on a character region determined to be present;
An image processing method comprising: A multi-value compression process for performing multi-value compression,
The control step performs the multi-value compression by the multi-value compression step without performing the binary compression by the binary compression step on the character region determined by the determination step that the binary compression should not be performed. The image processing method according to claim 11, wherein: The image processing method according to claim 12, wherein the control step performs multi-value compression by the multi-value compression step on the image. 14. The determination process according to claim 11, wherein the determination step determines that a character area whose density difference between the background and the character is less than a threshold is a character area that should not be subjected to binary compression. The image processing method according to item. The determination step is characterized in that a character region including a character darker than the background inside a portion having a background darker than a threshold is determined as a character region that should not be subjected to binary compression. Item 14. The image processing method according to any one of Items 11 to 13. The determination step determines that the character region is a character region that should not be subjected to binary compression when the edge pixels equal to or greater than the threshold number are included in a portion darker than the threshold value in the character region. The image processing method according to claim 11, wherein the image processing method is any one of claims 11 to 13. The determination step determines that the character region is a character region in which a binary image is to be performed when an edge pixel is included in a portion darker than the threshold value in the character region and less than the threshold number. The image processing method according to claim 16. The control step includes at least a result of character recognition processing for each of the plurality of character regions, a result of binary compression for the corresponding character region of the plurality of character regions, and a result of multi-value compression of the image. The image processing method according to any one of claims 11 to 17, wherein the files are collected into a file having a predetermined format. The image processing method according to claim 18, wherein the control step collects the result of multi-value compression of the image into the file. The image processing method according to claim 18, further comprising a transmission step of transmitting the file to an external device. A program for causing a computer to execute the image processing method according to any one of claims 11 to 20.