JP2007086956A - Image processor, image processing method and computer program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a device and method for changing the working configurations of an original image to be stored in the case of character recognition processing according to OCR probability. <P>SOLUTION: The probability of character recognition processing is calculated. As for a data region whose probability is high, original image working is executed by increasing a data reduction rate, and as for a data region whose probability is low, image working is executed by decreasing a data reduction rate. Thus, as for the data region whose character recognition probability is low, and whose original image reference possibility is high, the image data can be accurately restored, and as for the region data whose character recognition probability is high, and whose image reference possibility is low, a worked image can be generated and stored by increasing the data reduction rate, and data quantity to be stored in a storage means is reduced. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image processing method, an image processing method, and a computer program. More specifically, the present invention relates to an image processing apparatus, an image processing method, and a computer program that generate electronic document data by character recognition processing (OCR: Optical Character Recognition) and store original document image data.

  When a document document is stored electronically, it is common to store the document as image data. In particular, from the viewpoint of data reusability, the text region is preferably encoded and stored by character recognition processing (OCR: Optical Character Recognition).

  The character recognition rate by OCR is greatly related to the reliability of electronic documents. However, the OCR recognition rate and the accuracy of character determination are not 100%. In many cases, when an electronic document is stored, it is necessary to store the original document image together with the electronic data. This is to make it possible to refer to the original document image when checking the digitized data and examining the OCR processing result such as correction.

  As a conventional technique that discloses a document image confirmation processing configuration at the time of examining an OCR processing result, for example, a configuration in which an area determined to have low recognition accuracy at the time of OCR processing is displayed and used as a reference for correction by a user is patented. It is disclosed in Document 1. Further, as a conventional technique using the OCR accuracy, Patent Document 2 discloses a configuration in which character recognition accuracy is determined for each character, and a character determined to have low accuracy is replaced with a space or a specific character.

Characters that are erroneously recognized in the OCR can be corrected by referring to the original document image by the operator. Specifically, it is an operation in which a human compares the original document image data with the digitized text data (OCR result) visually to correct the text. However, if the document image is stored without compression or at a low compression rate because of fear of missing information, large-capacity image data will squeeze the disk capacity. On the other hand, if irreversible compression processing with a high compression ratio is performed, restoration of original image data may fail, and correction based on the original data may be difficult.
JP-A-8-96075 JP 2003-203204 A

  The present invention has been made in view of the above-mentioned problems, and a storage mode of original document image data when electronic document data is generated by character recognition processing (OCR) and the original document image data is stored. That is, an image processing apparatus, an image processing method, and a computer program that realize efficient data storage are provided as a configuration that dynamically changes an image processing processing mode such as compression processing according to the probability of character recognition. The purpose is to do.

The first aspect of the present invention is:
Character recognition processing means for executing character recognition processing based on input image data;
A character recognition probability calculating unit for calculating the probability of the character recognition processing executed in the character recognition processing means for each data area;
Based on the character recognition probability for each data area calculated by the character recognition probability calculation unit, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing unit for executing processing,
A storage unit for storing processed image data processed by the image processing unit;
An image processing apparatus characterized by comprising:

  Furthermore, in an embodiment of the image processing apparatus of the present invention, the character recognition processing unit is configured to execute a character recognition process for each layout category detected by layout analysis, and the character recognition probability calculation unit includes: The probability of the character recognition processing executed in the character recognition processing means is calculated for each layout category, and the image processing unit determines the character recognition probability for each layout category calculated by the character recognition probability calculation unit. Based on the above, the original image data to be subjected to the character recognition process is characterized in that a processing mode is determined for each layout section, and an image processing process is executed for each layout section in the determined processing mode.

  Furthermore, in an embodiment of the image processing apparatus of the present invention, the image processing unit sets a high data reduction rate for a data region having a high character recognition probability value calculated by the character recognition probability calculation unit. The image processing of the aspect is executed, and for the data area having a low character recognition probability calculated by the character recognition probability calculation unit, the image processing of the aspect in which the data reduction rate is set low is executed. It is characterized by that.

  Furthermore, in one embodiment of the image processing apparatus of the present invention, the image processing unit performs irreversible compression processing on a data region having a high character recognition probability calculated by the character recognition probability calculation unit. The data region having a low character recognition probability calculated by the character recognition probability calculation unit is configured to perform a reversible compression process.

  Furthermore, in an embodiment of the image processing apparatus of the present invention, the image processing unit performs character recognition accuracy for at least one of compression processing, resolution conversion processing, resolution conversion mode, reduction processing, and color mode conversion processing. The image processing is performed by changing the processing mode in accordance with the character recognition probability calculated by the calculation unit.

Furthermore, the second aspect of the present invention provides
A character recognition processing step for executing character recognition processing based on input image data;
A character recognition probability calculating step for calculating the certainty of the character recognition processing executed in the character recognition processing step for each data area;
Based on the character recognition probability for each data area calculated in the character recognition probability calculation step, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing step for executing the processing,
An image processing method characterized by comprising:

  Furthermore, in an embodiment of the image processing method of the present invention, the character recognition processing step includes a step of executing character recognition processing for each layout category detected by layout analysis, and the character recognition probability calculation step includes The probability of the character recognition processing executed in the character recognition processing step is calculated for each layout category, and the image processing step is the character recognition probability for each layout category calculated in the character recognition accuracy calculation step. On the basis of the above, for the original image data to be subjected to character recognition processing, a processing mode is determined for each layout section, and image processing is executed in units of layout sections in the determined processing mode. .

  Furthermore, in one embodiment of the image processing method of the present invention, the image processing step sets a high data reduction rate for a data region having a high value of the character recognition probability calculated in the character recognition probability calculation step. The image processing of the aspect is executed, and for the data region having a low character recognition probability calculated by the character recognition probability calculation step, the image processing of the aspect in which the data reduction rate is set low is executed. And

  Furthermore, in an embodiment of the image processing method of the present invention, the image processing step performs irreversible compression processing on a data area having a high value of the character recognition probability calculated in the character recognition probability calculation step. A reversible compression process is performed for a data region having a low character recognition probability value calculated in the character recognition probability calculation step.

  Furthermore, in one embodiment of the image processing method of the present invention, the image processing step includes character recognition probability for at least one of compression processing, resolution conversion processing, resolution conversion mode, reduction processing, and color mode conversion processing. It is a step of executing an image processing process in which the processing mode is changed according to the character recognition probability calculated by the calculation unit.

Furthermore, the third aspect of the present invention provides
A computer program for causing an image processing apparatus to execute image processing;
A character recognition processing step for executing character recognition processing based on input image data;
A character recognition probability calculating step for calculating the certainty of the character recognition processing executed in the character recognition processing step for each data area;
Based on the character recognition probability for each data area calculated in the character recognition probability calculation step, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing step for executing the processing,
There is a computer program characterized by comprising:

  Note that the computer program of the present invention is a recording medium provided in a computer-readable format for a computer system capable of executing various program codes, for example, a recording medium such as a CD, FD, or MO. A computer program that can be provided by a medium or a communication medium such as a network. By providing such a program in a computer-readable format, processing corresponding to the program is realized on the computer system.

  Other objects, features, and advantages of the present invention will become apparent from a more detailed description based on embodiments of the present invention described later and the accompanying drawings. In this specification, the system is a logical set configuration of a plurality of devices, and is not limited to one in which the devices of each configuration are in the same casing.

  According to the configuration of the present invention, the character recognition processing means (OCR) executes the character recognition processing based on the input image data, calculates the likelihood of the executed character recognition processing, and calculates the probability of the calculated character recognition. Based on this, the processing mode of the original image data for storage is determined, the image processing is performed, and the data is stored in the storage unit. Specifically, the probability of the character recognition processing executed in the character recognition processing means is calculated for each data area, and based on the character recognition probability for each data area, the original image data that is the character recognition processing target The processing mode for each data area is determined, and the processed image data generated by executing the image processing in the determined processing mode is stored in the storage unit.

  That is, for a data area having a high character recognition probability, an image processing process with a high data reduction rate is performed, and for a data area having a low character recognition probability, a data reduction rate is set. The image processing of the aspect set low is performed. With this configuration, it is possible to reliably restore original image data corresponding to an area that has a low character recognition accuracy and a high possibility of referring to the original image, and has a high character recognition accuracy and a low possibility of referring to the original image. Corresponding original image data can be stored and held at a high data reduction rate, and the amount of data stored in the storage means can be reduced.

  Hereinafter, an image processing apparatus, an image processing method, and a computer program according to embodiments of the present invention will be described in detail with reference to the drawings.

  First, the configuration and processing of an image processing apparatus according to an embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus 100 according to an embodiment of the present invention. The data processing executed by the image processing apparatus 100 of the present invention is executed by applying the hardware of the image processing apparatus 100 and a computer program as software, and the diagram shown in FIG. FIG. 5 is a block diagram showing a plurality of processes executed in the image processing apparatus of the present invention as blocks for each process in order to individually explain the processes. A specific example of the hardware configuration of the image processing apparatus will be described later.

  As shown in FIG. 1, the image processing apparatus 100 includes an image input unit 101, an OCR (Optical Character Recognition) unit 102 as a character recognition processing unit, an OCR result output unit 103, a character recognition probability calculation unit 104, a user input unit. 105, an image processing unit 106, and a data storage unit 107. The OCR unit 102 includes a binarization unit 111, a layout analysis unit 113, and a character recognition unit 113.

  The image input unit 101 inputs image data to be subjected to character recognition processing, that is, image data of a document document including characters. For example, it is input from image data read by a scanner or a database such as a hard disk. Note that the input document includes various data such as image data, text data, and a document including attribute data such as layout information.

  The document data input to the image input unit 101 is subjected to character recognition processing (OCR: Optical Character Recognition) in the OCR unit 102. The OCR unit 102 includes a binarization unit 111, a layout analysis unit 113, and a character recognition unit 113. In the binarization unit 111, the image data input from the image input unit 101 is binarized by applying a preset threshold value, that is, by applying a threshold value that specifies, for example, a gray level, A binarization process of white [0] and black [1] is performed on the data.

  The layout analysis unit 112 inputs image data of a document to be analyzed, and executes document layout analysis. If layout information is included as attribute information in the original document, that information may be applied. If layout information is not included, layout analysis is performed based on document image data. The layout analysis in the layout analysis unit 112 includes a process of setting a plurality of layout division areas by a division process of character areas included in the document.

  The character recognition unit 113 performs character recognition based on the binarization information of the image data generated by the binarization unit 111. The character recognition process is executed for each layout category as a layout analysis result in the layout analysis unit 112.

  The processing result of the character recognition unit 113 is output to a display or a printer via the OCR result output unit 103 shown in FIG. Further, the processing result of the character recognition unit 113 is calculated by the character recognition probability calculation unit 104. The character recognition probability calculation unit 104 executes processing for verifying the probability of the character recognition processing executed in the OCR unit 102 for each layout unit.

  With reference to FIG. 2, a specific processing example executed in the OCR unit 102 and the character recognition probability calculation unit 104 will be described. For example, the image input unit 101 reads image data based on a document image 201 to be scanned. The scan process in step S11 illustrated in FIG. 2 corresponds to the process of the image input unit 101.

  Thereafter, in step S12 shown in FIG. 2, binarization processing and layout analysis processing by the OCR means are executed. The analysis image data 202 shown in FIG. 2 is an example of the result of binarization processing and layout analysis processing. The image data is divided into a plurality of layout sections L1 to Ln. Thereafter, in step S13, character recognition processing in the character recognition unit 105 is executed, and for example, character recognition result data 203 shown in FIG. 2 is generated.

  In the example shown in FIG. 2, all characters are correctly recognized in the layout segment L3, but the erroneously recognized characters are included in the layout segments L1 and L2. The character recognition probability calculation unit 104 illustrated in FIG. 1 calculates the character recognition probability of the character recognition unit 113 for each layout category.

  The certainty is a value calculated as a value indicating the reliability of the character code information obtained as a character recognition result of the character recognition unit 113. For example, the reliability value of a character described in Japanese Patent No. 2991779 can be applied. As shown in FIG. 2, the character recognition probability calculation unit 104 calculates the character recognition probability of the character recognition unit 113 for each layout category as a layout analysis result in the layout analysis unit 112.

In the example shown in FIG.
Probability of layout division L1 = 60%
Probability of layout division L2 = 75%
Probability of layout division L3 = 100%
An example in which the result is calculated by the character recognition probability calculation unit 104 is shown. Thus, the character recognition probability calculation unit 104 calculates the probability of character recognition for each layout category.

  The value of the probability of character recognition for each layout section is input to the image processing unit 106 shown in FIG. Original image data to be subjected to character recognition processing is input from the image input unit 101 to the image processing unit 106. For example, in accordance with user input information from the user input unit 105, processed data (for example, compression processing, Processed data by color mode change processing) is generated, and the generated processed image data is stored in the data storage unit 107.

  The data storage unit 107 stores the OCR result output from the OCR result output unit 103 and the processed image data generated based on the original image by the image processing unit 106. In the image processing unit 106, an optimal image processing process is selected and executed for each layout section in accordance with the probability of character recognition for each layout section.

A processing example in the image processing unit 106 will be described with reference to FIG. As described above with reference to FIG. 2, the character recognition probability calculation unit 104 calculates the probability of character recognition for each layout category. As shown in FIG.
Probability of layout division L1 = 60%
Probability of layout division L2 = 75%
Probability of layout division L3 = 100%
Such a result is calculated by the character recognition probability calculation unit 104.

  The image processing unit 106 changes the processing mode of the original image data in accordance with these certainty values. For example, as shown in FIG. 3, for the layout segment L1 with character recognition accuracy = 60%, the lossless compression processing and for the layout segment L2 with character recognition accuracy = 75%, the lossy compression processing and the character recognition accuracy are performed. For the layout category L3 = 100%, the processing mode is changed, such as lossy compression processing. As the lossless compression, an LZW method, a Huffman coding method, a JPEG method, or the like can be applied. As the lossy compression, an irreversible JPEG compression or the like can be applied.

  This is because, for a layout category having a low probability value, for example, the layout category L1, it is highly necessary to correct the OCR result based on the original image. Therefore, lossless compression that can reliably restore the original image is performed. The other layout sections have high probability values and are less likely to refer to the original image, and are therefore irreversible compression capable of reducing the data by increasing the compression rate.

  Note that the image processing unit 106 not only changes the compression mode for each layout, but also performs processing for changing other data processing modes according to the probability of OCR recognition. The types of processing mode changes will be described with reference to FIG.

In FIG. 4, as the types of image processing to change the processing mode,
(1) compression processing,
(2) Resolution conversion processing,
(3) Resolution conversion mode,
(4) Reduction processing,
(5) Color mode conversion processing,
These five processing modes are shown as examples.

For example,
(1) About compression processing
Depending on the value of OCR recognition accuracy [high → low] of the layout category,
(A) High probability: lossy compression applying a high compression ratio parameter,
(B) Probability Medium-high: lossy compression applying a medium compression ratio parameter,
(C) Prediction medium low: lossy compression applying a low compression ratio parameter,
(B) Low probability: lossless compression,
These processing modes are set and the compression process is executed for each layout section.

(2) About resolution conversion processing
(A) Probability height: 100 dpi,
(B) Medium probability: 300 dpi,
(C) Low probability: 600 dpi,
These processing modes are set, and resolution conversion is executed for each layout section.

(3) For resolution conversion mode,
(A) High probability: nearest neighbor method,
(B) Medium probability: bilinear interpolation,
(C) Low probability: CubicConvolution method,
These processing modes are set, and different resolution conversion modes are applied to the respective layout sections.

  The nearest neighbor method is a kind of simple conversion method. This is a process to make the converted pixel value equal to the value of the nearest pixel among the pixels located at the four surrounding points when reversely mapped on the original image, and is a speed-priority method and inferior to other methods in terms of image quality Conversion mode. The bilinear interpolation method is a kind of enlargement / reduction method (interpolation method) by interpolation. When the converted pixel values are inversely mapped on the original image, linear values are obtained from the values of the pixels located at the surrounding four points. (Linearly) is obtained by interpolation, and the amount of calculation is not so large, and a relatively smooth image can be obtained, but a slight blur occurs. The Cubic Convolution method is a kind of enlargement / reduction method (convolution method) by interpolation, and 16 pixel points when the converted pixel values are inversely mapped on the original image and sinc ( x) = sin (x) / x is a technique for obtaining by a convolution operation with an approximate function. Although this method has a large amount of calculation, it has the best image quality because of its features such as suppression of aliasing distortion due to reduction.

(4) About reduction processing,
(A) High probability: reduction rate 75%,
(B) Medium probability: reduction rate 50%,
(C) Low probability: reduction rate 0%,
These processing modes are set, and the reduction process is executed for each layout section.

(5) For color mode,
(A) High probability: black and white binary,
(B) High probability medium: black and white gray,
(C) Prediction medium to low: index color method,
(D) Low probability: full color,
By setting these processing modes, different color modes are set for each layout section.

  As described above, the image processing unit 106 performs the data processing process that enables data restoration more reliably than the data reduction rate for the layout category having a low probability value, and the layout category having a high probability value. Performs data processing in a manner of increasing the data reduction rate, and stores the processed data in the data storage unit 107.

  Note that the type of data processing to be executed in the data processing unit 106 may be specified via the user input unit 105, and data processing corresponding to the specified type may be performed. For example, designation and processing such as only compression processing or only color mode setting are realized. In addition, without setting the processing execution configuration based on the user input, the processing determination table in which the processing mode to be executed based on the value of the probability of layout is set in advance in association with each other is stored in the memory of the data processing unit 106. A configuration may be adopted in which processing to be executed is selected and executed from the processing determination table based on the probability value of the layout category.

  As described above, according to the image processing apparatus of the present invention, in character recognition processing such as OCR, the probability for each layout category is calculated, and the layout category of the original image data is determined according to the value of the probability. Since the image processing processing mode such as each compression mode is determined, and processed image data according to the determined processing mode is generated and stored in the storage unit, the character recognition accuracy is low, and the original image is referred to Original image data corresponding to a highly likely layout category can be reliably restored, while data reduction is possible for original image data corresponding to a layout category with a high probability of character recognition and a low possibility of referring to the original image. Since it is configured to generate processed images with a high rate, it is possible to reduce the amount of data stored in the storage means The ability.

  Next, a processing procedure of the image processing apparatus according to the present embodiment will be described with reference to a flowchart shown in FIG. In step S101, for example, image data read by a scanner or image data to be subjected to OCR processing is input from a database such as a hard disk.

  Next, in steps S102 to S104, processing by the OCR means is executed. Step S102 is a process of the binarization unit 111 shown in FIG. 1, and the input image data is binarized by applying a preset threshold value. Step S103 is a process of the layout analysis unit 112. Yes, image data of the document to be analyzed is input, and layout analysis of the document is executed. Step S104 is processing of the character recognition unit 113, and performs character recognition based on the binarization information of the image data generated by the binarization unit 111. The character recognition process is executed as a pattern matching process for determining the degree of coincidence with pattern data prepared for each character in advance and determining a recognized character.

  The next step S105 is a process for outputting and saving the result data in the OCR process, and a display process or a printer output process or a storage process for the storage means is performed.

  The next step S106 is a process of the character recognition probability calculation unit 104, which calculates the probability of character recognition for each layout category as a layout analysis result in the layout analysis means 112.

  The next step S107 is a data processing method determination process, in which the image processing unit 106 shown in FIG. 1 determines an image processing method to be applied to each layout section based on the probability value of each layout section. Note that user-specified information may be applied as information on what type of processing is executed, or preset information may be applied.

In step S108, the processing method determined in step S107 is applied to execute processing of original image data corresponding to each layout category. Specifically, (1) compression processing described with reference to FIG.
(2) Resolution conversion processing,
(3) Resolution conversion mode,
(4) Reduction processing,
(5) Color mode conversion processing,
In these processes, an image processing process is executed based on a processing mode corresponding to the probability value calculated corresponding to each layout category.

  In step S109, the processed image data generated in step S108 is stored in the storage unit. The processed image data is preferably stored in the storage unit as data associated with the OCR result data.

  Finally, with reference to FIG. 6, a hardware configuration example of the image processing apparatus of the present invention will be described. The configuration illustrated in FIG. 6 is an image processing apparatus configured by, for example, a PC, and illustrates a hardware configuration example including a data reading unit 531 such as a scanner and a data output unit 532 such as a printer.

  A CPU (Central Processing Unit) 501 complies with a computer program that describes execution sequences of various types of data processing described in the above-described embodiments, that is, OCR processing, probability calculation processing, image processing processing, and the like. It is a control part which performs a process.

  A ROM (Read Only Memory) 502 stores programs used by the CPU 501, calculation parameters, and the like. A RAM (Random Access Memory) 503 stores programs used in the execution of the CPU 501, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 504 including a CPU bus.

  The host bus 504 is connected to an external bus 506 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 505.

  A keyboard 508 and a pointing device 509 are input devices operated by the user. The display 510 includes a liquid crystal display device, a CRT (Cathode Ray Tube), or the like, and displays various information as text or image information.

  An HDD (Hard Disk Drive) 511 includes a hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 501 and information. The hard disk stores OCR result data based on input image data, and further processed image data processed by the above-described processing. Further, various computer programs such as various other data processing programs are stored.

  The drive 512 reads data or a program recorded on a removable recording medium 521 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read out from the interface 507 and the external bus 506. , And supplied to the RAM 503 connected via the bridge 505 and the host bus 504. The removable recording medium 521 can also be used as a data recording area similar to a hard disk.

  The connection port 514 is a port for connecting the external connection device 522 and has a connection unit such as USB or IEEE1394. The connection port 514 is connected to the CPU 501 and the like via the interface 507, the external bus 506, the bridge 505, the host bus 504, and the like. The communication unit 515 is connected to a network and executes data communication processing with the outside. The data reading unit 531 executes document reading processing, and the data output unit 532 executes document data output processing.

  Note that the hardware configuration example of the image processing device shown in FIG. 6 shows one device example, and the image processing device of the present invention is not limited to the configuration shown in FIG. Any configuration capable of executing the process may be used.

  The present invention has been described in detail above with reference to specific embodiments. However, it is obvious that those skilled in the art can make modifications and substitutions of the embodiments without departing from the gist of the present invention. In other words, the present invention has been disclosed in the form of exemplification, and should not be interpreted in a limited manner. In order to determine the gist of the present invention, the claims should be taken into consideration.

  The series of processes described in the specification can be executed by hardware, software, or a combined configuration of both. When executing processing by software, the program recording the processing sequence is installed in a memory in a computer incorporated in dedicated hardware and executed, or the program is executed on a general-purpose computer capable of executing various processing. It can be installed and run.

  For example, the program can be recorded in advance on a hard disk or ROM (Read Only Memory) as a recording medium. Alternatively, the program is temporarily or permanently stored on a removable recording medium such as a flexible disk, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto optical) disk, a DVD (Digital Versatile Disc), a magnetic disk, or a semiconductor memory. It can be stored (recorded). Such a removable recording medium can be provided as so-called package software.

  The program is installed on the computer from the removable recording medium as described above, or is wirelessly transferred from the download site to the computer, or is wired to the computer via a network such as a LAN (Local Area Network) or the Internet. The computer can receive the program transferred in this manner and install it on a recording medium such as a built-in hard disk.

  Note that the various processes described in the specification are not only executed in time series according to the description, but may be executed in parallel or individually according to the processing capability of the apparatus that executes the processes or as necessary. Further, in this specification, the system is a logical set configuration of a plurality of devices, and the devices of each configuration are not limited to being in the same casing.

  As described above, according to the configuration of the present invention, the character recognition processing means (OCR) executes the character recognition processing based on the input image data, calculates the certainty of the executed character recognition processing, Based on the calculated character recognition probability, the processing mode of the original image data for storage is determined, and the image is processed and stored in the storage unit. Specifically, the probability of the character recognition processing executed in the character recognition processing means is calculated for each data area, and based on the character recognition probability for each data area, the original image data that is the character recognition processing target The processing mode for each data area is determined, and the processed image data generated by executing the image processing in the determined processing mode is stored in the storage unit.

  That is, for a data area having a high character recognition probability, an image processing process with a high data reduction rate is performed, and for a data area having a low character recognition probability, a data reduction rate is set. The image processing of the aspect set low is performed. With this configuration, it is possible to reliably restore original image data corresponding to an area that has a low character recognition accuracy and a high possibility of referring to the original image, and has a high character recognition accuracy and a low possibility of referring to the original image. Corresponding original image data can be stored and held at a high data reduction rate, and the amount of data stored in the storage means can be reduced.

1 is a block diagram illustrating a configuration of an image processing apparatus according to an embodiment of the present invention. It is a figure explaining the process example which the image processing apparatus which concerns on one Example of this invention performs. It is a figure explaining the image process based on the value of the probability which the image processing apparatus which concerns on one Example of this invention performs. It is a figure explaining the kind and aspect of an image processing process which the image processing apparatus which concerns on one Example of this invention performs. It is a figure which shows the flowchart explaining the process sequence which the image processing apparatus which concerns on one Example of this invention performs. It is a figure explaining the hardware structural example of the image processing apparatus of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Image processing apparatus 101 Image input part 102 OCR means 103 OCR result output part 104 Character recognition probability calculation part 105 User input part 106 Image processing part 107 Data storage part 111 Binarization part 112 Layout analysis part 113 Character recognition part 501 CPU (Central Processing Unit)
502 ROM (Read-Only-Memory)
503 RAM (Random Access Memory)
504 Host bus 505 Bridge 506 External bus 507 Interface 508 Keyboard 509 Pointing device 510 Display 511 HDD (Hard Disk Drive)
512 drive 514 connection port 515 communication unit 521 removable recording medium 522 external connection device 531 data reading unit 532 data output unit

Claims (11)

Character recognition processing means for executing character recognition processing based on input image data;
A character recognition probability calculating unit for calculating the probability of the character recognition processing executed in the character recognition processing means for each data area;
Based on the character recognition probability for each data area calculated by the character recognition probability calculation unit, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing unit for executing processing,
A storage unit for storing processed image data processed by the image processing unit;
An image processing apparatus comprising: The character recognition processing means includes:
It is a configuration that executes character recognition processing for each layout category detected by layout analysis,
The character recognition accuracy calculation unit
The probability of the character recognition process executed in the character recognition processing means is calculated for each layout category,
The image processing unit
Based on the character recognition probability for each layout category calculated by the character recognition accuracy calculation unit, for the original image data targeted for character recognition processing, determine the processing mode for each layout category, in the determined processing mode, The image processing apparatus according to claim 1, wherein the image processing processing is executed in units of layout sections. The image processing unit
For a data region having a high character recognition probability calculated by the character recognition accuracy calculation unit, an image processing process in which the data reduction rate is set high is executed,
The data area having a low character recognition probability calculated by the character recognition probability calculation unit is configured to execute an image processing process in a mode in which the data reduction rate is set low. The image processing apparatus described. The image processing unit
For a data area having a high character recognition probability calculated by the character recognition accuracy calculation unit, a lossy compression process is performed,
The image processing apparatus according to claim 1, wherein a reversible compression process is executed for a data area having a low character recognition probability calculated by the character recognition probability calculation unit. The image processing unit
An image processing process in which the processing mode is changed according to the character recognition probability calculated by the character recognition probability calculation unit for at least one of compression processing, resolution conversion processing, resolution conversion mode, reduction processing, and color mode conversion processing The image processing apparatus according to claim 1, wherein the image processing apparatus is configured to execute A character recognition processing step for executing character recognition processing based on input image data;
A character recognition probability calculating step for calculating the certainty of the character recognition processing executed in the character recognition processing step for each data area;
Based on the character recognition probability for each data area calculated in the character recognition probability calculation step, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing step for executing the processing,
An image processing method comprising: The character recognition processing step includes:
A step of performing character recognition processing for each layout category detected by layout analysis;
The character recognition probability calculating step includes:
The probability of the character recognition process executed in the character recognition process step is calculated for each layout category,
The image processing step includes
Based on the character recognition probability for each layout category calculated in the character recognition accuracy calculation step, for the original image data targeted for character recognition processing, determine the processing mode for each layout category, in the determined processing mode, The image processing method according to claim 6, wherein the image processing is a step of executing image processing in units of layout sections. The image processing step includes
For a data region having a high character recognition probability value calculated in the character recognition probability calculation step, an image processing process in which the data reduction rate is set high is executed,
7. The image according to claim 6, wherein an image processing process in which the data reduction rate is set low is executed for a data area having a low character recognition probability calculated by the character recognition probability calculation step. Processing method. The image processing step includes
For a data region having a high character recognition probability calculated in the character recognition probability calculation step, an irreversible compression process is executed,
The image processing method according to claim 6, wherein a lossless compression process is executed for a data area having a low character recognition probability calculated in the character recognition probability calculation step. The image processing step includes
An image processing process in which the processing mode is changed according to the character recognition probability calculated by the character recognition probability calculation unit for at least one of compression processing, resolution conversion processing, resolution conversion mode, reduction processing, and color mode conversion processing The image processing method according to claim 6, wherein the image processing method is a step of executing the following. A computer program for causing an image processing apparatus to execute image processing;
A character recognition processing step for executing character recognition processing based on input image data;
A character recognition probability calculating step for calculating the certainty of the character recognition processing executed in the character recognition processing step for each data area;
Based on the character recognition probability for each data area calculated in the character recognition probability calculation step, a processing mode for each data area of the original image data to be subjected to character recognition processing is determined, and an image in the determined processing mode is determined. An image processing step for executing the processing,
A computer program characterized by comprising:

Images