JP7063121B2 - Information processing equipment and programs - Google Patents

Description

The present invention relates to an information processing apparatus and a program.

Electronic filing is performed to scan paper documents and store them as electronic document files. In Patent Document 1, when defining the input format data of the input material, only the characters, numerical values, images, etc. inside the handwritten closed figure or underlined are read and recognized, and the recognition target area is recognized as characters. It is described that the data is converted into recognition character data and an output data file for each recognition target is generated. In Patent Document 2, in an image processing apparatus that performs image processing for binarizing optically read form image information, a binarized image different for each region is generated from the form identification information registered in advance. It is stated that.

Japanese Unexamined Patent Publication No. 2000-132542 Japanese Unexamined Patent Publication No. 2004-341656

In the present invention, as image data representing a designated image, the image quality of the target area is reduced by performing different image processing for each target area included in the designated image to reduce the amount of data of the generated image data. It is an object of the present invention to provide a technique for suppressing deterioration of the image.

The information processing apparatus according to claim 1 of the present invention includes an extraction means for extracting an image of a target area from a designated image, an acquisition means for acquiring an image type of the extracted target area, and the extracted target area. An image processing means that executes image processing corresponding to the type of the target area, an image represented by the image-processed image data, and a designated image of an area other than the target area are used for the image data representing the image of the above. When the size of the compositing means to be synthesized and the image data representing the image synthesized by the compositing means exceeds a predetermined threshold, the image data of the target area included in the designated image and the extracted target area are not included. It is characterized by having a processing means for reducing the amount of data for at least one of the image data in the region and performing a processing preset for each type.

The information processing apparatus according to claim 2 of the present invention has the configuration according to claim 1, wherein the processing means has a threshold value in which the number of pixels in a range in which the gradation value is predetermined in the target region is predetermined. It is characterized in that the above-mentioned processing is executed within a range not less than the above.

The information processing apparatus according to claim 3 of the present invention further has a recognition means for recognizing characters or images with respect to an image of a target area processed by the processing means in the configuration according to claim 1 or 2. The processing means is characterized in that, for a target area where the recognition means fails in the recognition process, the image data before the processing for reducing the amount of the data is performed is used as the image data of the target area.

The information processing apparatus according to claim 4 of the present invention has the configuration according to any one of claims 1 to 3, wherein the processing means has a resolution for image data in a region other than the extracted target region. It is characterized in that at least one of a process of lowering the pressure and a process of increasing the compression ratio are performed.

The information processing apparatus according to claim 5 of the present invention has the configuration according to any one of claims 1 to 4, wherein the processing means reduces the resolution of the image data in the target area and the compression rate. It is characterized in that at least one of a process of increasing the image size and a process of reducing the image size is performed.

The program according to claim 6 of the present invention includes a step of extracting an image of a target area from a designated image, a step of acquiring an image type of the extracted target area, and a step of acquiring the extracted target area on a computer. A step of executing image processing corresponding to the type of the target area on the image data representing the image, a step of synthesizing the image represented by the image-processed image data, and a designated image of an area other than the target area. When the size of the image data representing the combined image exceeds a predetermined threshold, at least the image data of the target area included in the designated image and the image data of the area other than the extracted target area. It is characterized in that it is a program for executing a process of reducing the amount of data and a step of performing a process preset for each type for any one of them.

According to the inventions according to claims 1 and 6, as image data representing a designated image, a process of reducing the amount of image data generated by executing different image processing for each target area included in the designated image is performed. In such a case, deterioration of the image quality of the target area is suppressed.
According to the second aspect of the present invention, it is possible to prevent the characters and images in the target area from becoming unrecognizable.
According to the third aspect of the present invention, it is possible to prevent the characters and images in the target area from becoming unrecognizable.
According to the invention of claim 4, it is possible to reduce the data size of the entire file while suppressing the deterioration of the image quality of the target area.
According to the invention of claim 5, as image data representing a designated image, a process of reducing the amount of image data generated by executing different image processing for each target area included in the designated image is performed. In, deterioration of the image quality of the target area is suppressed.

A block diagram illustrating the configuration of an information processing system. The block diagram which illustrates the functional structure of the information processing apparatus 10. The block diagram which illustrates the hardware composition of the information processing apparatus 10. The block diagram illustrating the hardware configuration of the server 20. The figure which illustrates the manuscript. A flowchart illustrating the flow of processing for determining the reading resolution. A flowchart illustrating the flow of image data generation processing. A flowchart illustrating the flow of processing for determining the output resolution. A flowchart illustrating the flow of processing for synthesizing images in a target area. A flowchart illustrating the flow of processing for adjusting the data size. The figure which illustrates the image to be combined.

[1] Configuration Figure 1 is a block diagram illustrating the configuration of the information processing system 1 according to the present embodiment. The information processing system 1 includes an information processing device 10 and a server 20. The information processing apparatus 10 performs image processing such as image forming processing for forming an image on a medium such as paper and image reading processing for reading an image formed on a medium such as a document. The server 20 provides various services such as a storage service. The information processing device 10 is connected to the server 20 by the communication line 2. The communication line 2 includes, for example, at least one of the Internet, a mobile communication network, a telephone line, a LAN (local area network), and the like.

FIG. 2 is a block diagram illustrating a functional configuration of the information processing apparatus 10. The information processing apparatus 10 includes an extraction means 11, an acquisition means 12, an image processing means 13, a synthesis means 14, a processing means 15, and a recognition means 16. The extraction means 11 extracts an image of the target area from the designated image. In this embodiment, the designated image is an image to be processed, for example, an image of a document (medium) read by an image reading means. The target area is an area including a specific image designated by the user (an image of a stamped seal, a barcode image, an image of a handwritten signature, etc.). The acquisition means 12 acquires the type of image of the target area extracted by the extraction means 11. The image processing means 13 executes image processing corresponding to the type of the target area on the image data representing the image of the target area extracted by the extraction means 11. The image processing corresponding to the type of the target area is, for example, binarization processing, noise removal processing, resolution conversion processing, and density adjustment processing. The synthesizing means 14 synthesizes an image represented by the image data image-processed by the image processing means 13 and a designated image in an area other than the target area.

When the size of the image data representing the image synthesized by the compositing means 14 exceeds a predetermined threshold, the processing means 15 sets the image data of the target area included in the designated image and the target extracted by the extracting means 11. It is a process of reducing the amount of data for at least one of the image data in the area other than the area, and the process set in advance for each type of the target area is performed. The process of lowering the data is, for example, a process of lowering the resolution, a process of reducing the size (scale) of the image, or a process of lowering the compression rate.

The recognition means 16 performs a process of recognizing a character or an image of an image in a target area that has been processed by the processing means 15 to reduce the amount of data. In this case, for the target area where the recognition means 16 fails in the recognition process, the image data before the process of reducing the amount of data is used as the image data of the target area.

FIG. 3 is a diagram illustrating a hardware configuration of the information processing apparatus 10. The processor 101 is a processor that controls other elements of the information processing device 10. The memory 102 is a storage device that functions as a work area for the processor 101 to execute a program, and includes, for example, a RAM (Random Access Memory). The storage 103 is a storage device for storing various programs and data, and includes, for example, an SSD (Solid State Drive) or an HDD (Hard Disk Drive). The communication IF 104 communicates with other devices in accordance with predetermined wireless or wired communication standards (eg, Wi-Fi®, Bluetooth®, or Ethernet®).

The UI unit 105 includes, for example, a touch screen and keys. The UI unit 105 may be built in the information processing device 10 or may be externally connected to the UI unit 105. The image forming unit 106 forms an image on a medium such as paper by an electrophotographic method. The image reading unit 107 optically reads an image of a document (medium). The image processing unit 108 includes, for example, a DSP (Digital Signal Processor) or a GPU (Graphics Processing Unit), and executes various image processing. The paper feeding unit 109 supplies a medium such as paper to the image forming unit 106.

In this example, the function shown in FIG. 2 is implemented by the processor 101 or the image processing unit 108 executing the program stored in the memory 102 or the storage 103. The processor 101 or the image processing unit 108 executing the program is an example of the extraction means 11, the acquisition means 12, the image processing means 13, the synthesis means 14, and the processing means 15. The image reading unit 107 is an example of an image reading means.

FIG. 4 is a diagram illustrating a hardware configuration of the server 20. The processor 201 is a processor that controls other elements of the server 20. The memory 202 is a storage device that functions as a work area for the processor 201 to execute a program, and includes, for example, a RAM. The storage 203 is a storage device for storing various programs and data, and includes, for example, an SSD or an HDD. The communication IF 204 communicates with other devices according to a predetermined wireless or wired communication standard.

[2] Operation In this operation example, the information processing apparatus 10 reads a document and stores image data representing the read document in a server 20 which is a storage server. The manuscript to be read contains characters (and images) and is, for example, an invoice, a receipt, a receipt, a driver's license, or a membership card. The manuscript to be read may include a stamped seal, a handwritten signature, or an image of a barcode.

FIG. 5 is a diagram illustrating a document read by the information processing apparatus 10. In the example of FIG. 5, the manuscript A1 includes a character area A101 and a character area A102 in which a text character string is described, and also has an image area A201, a barcode image area A202, and a handwritten sign area A203 of the stamped seal. Is included.

When scanning a manuscript, the user determines whether or not the manuscript to be read includes an image of a stamped seal (hereinafter referred to as "seal image"), whether or not a barcode image is included, and a handwritten signature. An operation is performed to set whether or not an image (hereinafter referred to as "handwritten image") is included by using the UI unit 105 of the information processing apparatus 10. The UI unit 105 causes the UI unit 105 to display a screen for allowing the user to select whether or not the stamp image, the barcode image, and the handwritten image are included, and the user makes a selection using the displayed screen. .. Information representing the content selected by the user (hereinafter referred to as “selection information”) is stored in the memory 102 or the storage 103. After completing the selection operation for the document to be scanned, the user sets the document in the information processing apparatus 10 and instructs the image scanning by pressing the start button or the like. In the following description, for convenience of explanation, when it is not necessary to distinguish between the stamp image, the barcode image, and the handwritten image, these are referred to as "specific images".

FIG. 6 is a flowchart illustrating the flow of a process of determining a resolution (hereinafter referred to as “reading resolution”) in the reading process performed by the information processing apparatus 10. The process shown in FIG. 6 is started when the document is set in the information processing apparatus 10 by the user and the image reading is instructed by pressing the start button or the like.

In step S101, the processor 101 of the information processing apparatus 10 determines whether the stamp image is included in the document to be read. This determination is made by referring to the selection information stored in the storage 103. When the seal image is included (step S101; YES), the processor 101 proceeds to the process of step S102. In step S102, the processor 101 sets the reading resolution to 300 dpi. On the other hand, when the seal stamp image is not included (step S102; NO), the processor 101 skips the process of step S102 and proceeds to the process of step S103.

In step S103, the processor 101 determines whether the original image includes a barcode image. This determination is made by referring to the selection information stored in the storage 103. If the barcode image is included (step S103; YES), the processor 101 proceeds to the process of step S104. In step S104, the processor 101 sets the reading resolution to a value of 400 dpi or more. In this embodiment, the reading resolution is set to 400 dpi. When the upper limit value that can be set for the reading resolution of the device is a value of 400 dpi or more, a value of 400 dpi or more may be set. On the other hand, when the barcode image is not included (step S104; NO), the processor 101 skips the process of step S104 and proceeds to the process of step S105.

In step S105, the processor 101 determines whether the original image includes a handwritten image. This determination is made by referring to the selection information stored in the storage 103. When the handwritten image is included (step S105; YES), the processor 101 proceeds to the process of step S106. In step S106, the processor 101 sets the reading resolution to a value of 200 dpi or more. In this embodiment, the reading resolution is set to 200 dpi. The reading resolution may be set to a value of 200 dpi or more in step S106. In step S106, when a value of 200 dpi or more is already set as the reading resolution by the process of step S102 or step S104, the value is used as the reading resolution as it is set.

If the handwritten image is not included in step S105 (step S105; NO), the processor 101 proceeds to the process of step S107. In step S107, the processor 101 sets the reading resolution to a default value (eg, 200 dpi).

By executing the process of FIG. 6, the reading resolution is determined. That is, in this embodiment, when the original contains a stamp image, the reading resolution is set to a value of 300 dpi or more. When the original contains a barcode image, the reading resolution is set to a value of 400 dpi or more. When the original contains a handwritten image, the reading resolution is set to a value of 200 dpi or more.

FIG. 7 is a flowchart illustrating the flow of the image data generation process. In the example of FIG. 7, the processor 101 extracts a specific image from a target area including a specific image such as a seal image, a barcode image, and a handwritten image from the image of the scanned document, and an image of the extracted target area. Get the type of. Further, the processor 101 executes image processing corresponding to the type of the target area on the image data representing the extracted image of the target area. As the image processing, for example, the processor 101 performs binarization processing different for each type of the target area so that the on-pixels in the target area are maximized. In this embodiment, the processor 101 makes the binarization method and parameters different for each type of the target area. Specifically, for example, the information processing apparatus 10 performs processing such as detecting red and black for a stamp image and lowering the threshold value for simple binarization for a handwritten image.

In step S201 of FIG. 7, the processor 101 instructs the image reading unit 107 to perform image reading processing at the reading resolution determined by the processing of FIG. 6, and causes the image reading unit 107 to perform image reading. In step S202, the processor 101 determines whether the image of the scanned document (hereinafter referred to as "manuscript image") includes the stamp image. This determination is made by referring to the selection information stored in the storage 103. When the seal image is included (step S202; YES), the processor 101 proceeds to the process of step S203. On the other hand, when the seal stamp image is not included (step S202; NO), the processor 101 proceeds to the process of step S205.

In step S203, the processor 101 performs area separation processing on the original image, separates the text area and the image area, and performs image processing such as pattern matching processing on the image area, and performs image processing such as pattern matching processing on the image area (hereinafter, "" "Seal area") is extracted. In step S204, the processor 101 acquires the type of the image of the extracted target area (seal stamp area), and performs the binarization process on the extracted seal stamp area using the parameters for the seal stamp area. The type of the target area is specified from the processing result of image processing such as pattern matching processing. As processing for each type of image in the target area, for example, the processor 101 performs red-black detection processing on the stamp area. The seal image data generated by the binarization process in step S204 is stored in the memory 102 or the storage 103.

In step S205, the processor 101 determines whether the original image contains a barcode image. This determination is made by referring to the selection information stored in the storage 103. If the barcode image is included (step S205; YES), the processor 101 proceeds to the process of step S206. On the other hand, when the barcode image is not included (step S205; NO), the processor 101 proceeds to the process of step S208.

In step S206, the processor 101 extracts a barcode area specified by image processing such as pattern matching processing on the original image. In step S207, the processor 101 acquires the type of the image of the extracted target area (bar code area), and performs the binarization process on the extracted bar code area using the parameters for the bar code area. .. For example, the processor 101 performs the binarization process using a threshold value higher than the binarization threshold value for the handwriting area. The barcode image data generated by the binarization process in step S207 is stored in the memory 102 or the storage 103.

In step S208, the processor 101 determines whether the original image includes a handwritten image. This determination is made by referring to the selection information stored in the storage 103. If the handwritten image is included (step S208; YES), the processor 101 proceeds to the process of step S209. On the other hand, when the handwritten image is not included (step S208; NO), the processor 101 proceeds to the process of step S211.

In step S209, the processor 101 extracts a handwritten area specified by image processing such as pattern matching processing on the original image. In step S210, the processor 101 acquires the type of the image of the extracted target area (handwriting area), and performs the binarization process on the extracted handwriting area using the parameters for the handwriting area. For example, the processor 101 performs the binarization process using a threshold value lower than the binarization threshold value for the barcode area. The handwritten image data generated by the binarization process in step S210 is stored in the memory 102 or the storage 103. As described above, in this embodiment, the binarization process is executed by changing the binarization method and parameters for each type of the target area (steps S204, S207, and S210 in FIG. 7).

In step S211 the processor 101 performs image processing such as color conversion processing on the image data of the image of the area other than the target area extracted in step S203, step S206, or step S209 (hereinafter referred to as "whole image"). , Generates image data of the whole image (hereinafter referred to as "whole image data").

In step S212, the processor 101 determines the resolution of the image data to be output (hereinafter referred to as "output resolution").

FIG. 8 is a flowchart illustrating the flow of the process of determining the output resolution (process of step S212 of FIG. 7). In step S301, the processor 101 determines whether the original image includes the stamp image. This determination is made by referring to the selection information stored in the storage 103. When the seal image is included (step S301; YES), the processor 101 proceeds to the process of step S302. On the other hand, when the seal stamp image is not included (step S301; NO), the processor 101 proceeds to the process of step S305.

In step S302, the processor 101 determines whether the number of on-pixels per unit area in the stamp area is larger than a predetermined threshold value. When the number of on pixels is larger than the threshold value (step S302; YES), the processor 101 proceeds to the process of step S303. In step S303, the processor 101 sets the output resolution to 200 dpi. On the other hand, when the number of on-pixels is equal to or less than the threshold value (step S302; NO), the processor 101 proceeds to the process of step S304. In step S304, the processor 101 sets the output resolution to 300 dpi.

In step S305, the processor 101 determines whether the original image contains a barcode image. This determination is made by referring to the selection information stored in the storage 103. If the barcode image is included (step S305; YES), the processor 101 proceeds to the process of step S306. On the other hand, when the barcode image is not included (step S305; NO), the processor 101 proceeds to the process of step S309.

In step S306, the processor 101 performs image recognition processing on the barcode area, and determines whether the barcode is readable (recognizable). If the barcode is recognizable (step S306; YES), the processor 101 proceeds to the process of step S307. In step S307, the processor 101 sets the output resolution to 200 dpi. On the other hand, if the barcode is not recognizable (step S306; NO), the processor 101 proceeds to the process of step S308. In step S308, the processor 101 sets the output resolution to 400 dpi.

In step S309, the processor 101 determines whether the manuscript image contains a handwritten image. This determination is made by referring to the selection information stored in the storage 103. When the handwritten image is included (step S309; YES), the processor 101 proceeds to the process of step S310. On the other hand, when the handwritten image is not included (step S309; NO), the processor 101 ends the process.

In step S310, the processor 101 determines whether the number of on-pixels per unit area in the handwriting area is larger than a predetermined threshold value. When the number of on-pixels is larger than the threshold value (step S310; YES), the processor 101 proceeds to the process of step S311. In step S311 the processor 101 sets the output resolution to 200 dpi. On the other hand, when the number of on-pixels is equal to or less than the threshold value (step S310; NO), the processor 101 proceeds to the process of step S312. In step S312, the processor 101 sets the output resolution to 300 dpi.

As shown in FIG. 8, in this embodiment, the output resolution is set to the lowest possible resolution in order to shorten the transfer time. Specifically, for example, when the original image includes a stamp area, the number of on-pixels per unit area of the stamp area is larger than the threshold value (that is, the print amount is large), and the number of on-pixels is small (that is, when the print amount is large). That is, the output resolution is set lower than when the print amount is small). Further, when the original image includes a barcode area, the barcode image is image-recognized, and when the image is unrecognizable, the output resolution is set lower than when the image is recognizable. Further, when the handwritten area is included in the original image, the output resolution is set lower when the number of on-pixels per unit area of the handwritten area is larger than the threshold value and when the number of on-pixels is smaller than the threshold value.

Returning to the description of FIG. In step S213, the processor 101 converts the resolution of the image in the target area according to the output resolution determined in the process of step S212 (process of FIG. 8). In step S214, the processor 101 executes a process of synthesizing the image of the target area and the entire image.

FIG. 9 is a flowchart illustrating the flow of the process of synthesizing the image of the target area and the entire image (process of step S214 of FIG. 7). In step S401, the processor 101 acquires the entire image data. In step S402, the processor 101 determines whether the original image includes the stamp image. This determination is made by referring to the selection information stored in the storage 103. When the seal image is included (step S402; YES), the processor 101 proceeds to the process of step S403. In step S403, the processor 101 acquires image data (hereinafter referred to as “seal stamp image data”) of the stamp area whose resolution has been converted in step S213 of FIG. 7. On the other hand, when the seal stamp image is not included (step S402; NO), the processor 101 proceeds to the process of step S404.

In step S404, the processor 101 determines whether the original image contains a barcode image. This determination is made by referring to the selection information stored in the storage 103. If the barcode image is included (step S404; YES), the processor 101 proceeds to the process of step S405. On the other hand, when the barcode image is not included (step S404; NO), the processor 101 proceeds to the process of step S408.

In step S405, the processor 101 determines (in step S213 of FIG. 7) whether the resolution of the barcode image has been converted. When the resolution is converted (step S405; YES), the processor 101 proceeds to the process of step S406. On the other hand, if the resolution has not been converted (step S405; NO), the processor 101 proceeds to the process of step S407.

When the resolution of the barcode image is not converted, in step S407, the processor 101 acquires the barcode image data generated by the binarization process for the barcode image (process of step S207 in FIG. 7). On the other hand, when the resolution is converted, in step S406, the processor 101 performs recognition processing on the barcode image read at high resolution, and uses the recognition result to generate a barcode image with the converted resolution. ..

In step S408, the processor 101 determines whether the original image contains a handwritten image. This determination is made by referring to the selection information stored in the storage 103. If the handwritten image is included (step S408; YES), the processor 101 proceeds to the process of step S409. In step S409, the processor 101 acquires image data (hereinafter referred to as “handwritten image data”) of the handwritten area whose resolution has been converted in step S213 of FIG. 7. On the other hand, when the handwritten image is not included (step S408; NO), the processor 101 proceeds to the process of step S410.

In step S410, the processor 101 synthesizes an image of the acquired or generated target area. In this example, the processor 101 has the seal image data acquired in step S403, the barcode image data acquired in step S407, the barcode image data generated in step S406, and the handwritten image data acquired in step S409. To synthesize.

In step S411, the processor 101 synthesizes a composite image of the target region synthesized in step S410 with the entire image acquired in step S401. In step S412, the processor 101 executes a process of adjusting (reducing) the size of the data amount of the entire file. In this embodiment, the process of reducing the amount of data is, for example, a process of reducing the resolution, a process of reducing the size (scale) of the image, or a process of reducing the compression rate. In this embodiment, the processor 101 performs a process of reducing the amount of data to the extent that the specific image is not impossible to recognize (character recognition, image recognition, etc.).

FIG. 10 is a flowchart illustrating the flow of the file data size adjustment process (process of step S412 in FIG. 9). In the example of FIG. 10, when the size of the composite image data synthesized by step S411 of FIG. 9 exceeds a predetermined threshold value, the processor 101 has the image data of the target area included in the original image and the target area other than the target area. It is a process of reducing the amount of data for at least one of the image data of the area, and a process preset for each type of the target area is performed.

In step S501 of FIG. 10, the processor 101 determines whether the file size is larger than the predetermined threshold value T1. If the file size is larger than the threshold value T1 (step S501; YES), the processor 101 proceeds to the process of step S502. On the other hand, when the file size is equal to or less than the threshold value T1 (step S501; NO), the processor 101 skips the process of step S502 and proceeds to the process of step S503.

In step S502, the processor 101 executes a process of reducing the data size of the entire image. In this embodiment, the processor 101 performs at least one of a process of lowering the resolution of the image data of the entire image and a process of increasing the compression rate.

In step S503, the processor 101 again determines whether the file size is larger than the threshold value T2 (step S503). The threshold value T2 used in this determination may be the same value as the threshold value T1 or may be a different value. When the file size is larger than the threshold value T2 (step S503; YES), the processor 101 proceeds to the process of step S504. On the other hand, when the file size is equal to or less than the threshold value T2 (step S503; NO), the processor 101 skips the processes of steps S504 and S505 and proceeds to the process of step S506.

In step S504, the processor 101 determines whether the original image contains a barcode image. This determination is made by referring to the selection information stored in the storage 103. If the barcode image is included (step S205; YES), the processor 101 proceeds to the process of step S505. In step S505, the processor 101 performs a process of reducing the scale of the barcode image. On the other hand, when the barcode image is not included (step S505; NO), the processor 101 skips the process of step S505 and proceeds to the process of step S506.

In step S506, the processor 101 determines whether the file size is larger than the predetermined threshold value T3. The threshold value T3 used in this determination may be the same value as the threshold values T1 and T2, or may be different values. If the file size is larger than the threshold T3 (step S506; YES), the processor 101 proceeds to the process of step S507. In step S507, the processor 101 executes a process of lowering the resolution of the entire composite image data. On the other hand, when the file size is equal to or less than the threshold value T3 (step S506; NO), the processor 101 skips the process of step S507 and proceeds to the process of step S508.

In step S508, the processor 101 executes a process of synthesizing the processed images of each target area. In step S509, the processor 101 executes a process of synthesizing the processed composite image with the entire image. At this time, if overlap occurs, for example, the processor 101 may superimpose and synthesize specific images according to a predetermined priority for each type of the target area, or perform an OR operation for each dot. By doing so, the images may be combined.

FIG. 11 is a diagram illustrating an image to be synthesized. In the example of FIG. 11, the binarization process is performed in each of the barcode area A112, the stamp area A113, and the handwritten area A114 by different parameters or different binarization methods. For example, the parameter P1 is used for the barcode area A112, the parameter P2 is used for the stamp area A113, and the parameter P3 is used for the handwritten area A114. The image data generated by using different parameters in this way is combined with the whole image A111, and the combined image A115 is generated.

The composite image data generated by the information processing apparatus 10 is transmitted to the server 20 and stored. The server 20 executes recognition processing such as stamp recognition processing and handwriting recognition processing on the composite image data. That is, in this embodiment, the barcode recognition process is performed by the information processing apparatus 10, while the seal stamp recognition process and the handwriting recognition process are performed by the server 20.

By the way, when scanning a manuscript containing a stamped stamp image or a handwritten signature, the character recognition of the handwritten signature after scanning or the image recognition of the stamp image may not be possible due to the thin printing. In this embodiment, the information processing apparatus 10 changes the binarization method and parameters depending on the type of the image to be recognized. Specifically, for example, the red-black extraction process is performed for the seal stamp image, and the threshold value for simple binarization is set low for the handwritten signature image. Further, in this embodiment, a process preset for each target area is performed as a process for reducing the amount of image data generated by executing different image processing for each target area.

[3] Modifications The above-described embodiment is merely an example of the embodiment of the present invention, and may be modified as follows. In addition, the above-described embodiment and each of the following modifications may be combined and implemented as necessary.

(1) In the above-described embodiment, the case where the binarization process is performed as the image process corresponding to the type of the target area has been described (steps S204, S207 and S210, etc. in FIG. 7). The image processing corresponding to the type of the target area is not limited to that shown in the above-described embodiment. The image processing corresponding to the type of the target area may be, for example, noise removal processing or density adjustment processing.

(2) The process of reducing the amount of data in the target area is not limited to that shown in the above-described embodiment. For example, in the processor 101, the gradation value is included in a predetermined range in the target area (for example, the density is equal to or higher than the predetermined threshold value, and the density is equal to or higher than the intermediate value between the lower limit value and the upper limit value). ,, Etc.) The process of reducing the amount of data in the target area may be executed so that the number of pixels per unit area does not fall below a predetermined threshold value. As a result, it is possible to prevent the number of on-pixels from becoming too small in the target area, and it is possible to prevent the image or character from being unrecognizable.

(3) In the above-described embodiment, the processor 101 performs a process of recognizing a character or an image on an image in a target area for which a process of reducing the amount of data has been performed, and a data amount of the target area in which the recognition process fails. The image data before the process of lowering the image may be used as the image data of the target area. In this embodiment, failure in recognition processing means that data in a predetermined data format cannot be generated by image recognition. For example, when image recognition processing is performed on a two-dimensional bar code image, a text character string is used. This means the case where the text data could not be generated due to the character recognition process or the case where the text data could not be generated. In this case, the compositing process is performed using the image data of the target area before the process of reducing the amount of data is performed. As a result, it is possible to prevent the image or character in the target area from becoming unrecognizable.

(4) In the above-described embodiment, as a process of reducing the amount of data in the target area, a process of reducing the image size (scale) of the barcode image (step S505 in FIG. 10) is exemplified. The process of reducing the amount of data in the target area is not limited to that shown in the above-described embodiment. For example, as a process of reducing the amount of data in the target area, a process of reducing the image size (scale) of the stamp image may be performed. Further, as another example, for example, a process of increasing the compression rate of the target area or a process of lowering the resolution may be performed.

(5) In the above-described embodiment, the user inputs using the UI unit 105 to determine whether the manuscript contains a specific image such as a stamp image, and the input selection information is referred to to determine. rice field. The method for determining whether the manuscript contains a specific image is not limited to that shown in the above-described embodiment. For example, the processor 101 may determine whether or not a specific image is included in the document by reading the image of the document and performing processing such as pattern matching.

(6) In the above-described embodiment, the information processing apparatus 10 performs the barcode recognition process, while the server 20 performs the seal stamp recognition process and the handwriting recognition process. The apparatus performed by various recognition processes is not limited to that shown in the above-described embodiment. For example, the information processing apparatus 10 may execute character recognition processing such as seal stamp recognition processing and handwriting recognition processing, and for example, the server 20 may perform bar code recognition processing. As described above, a part of the processing executed by the information processing apparatus 10 in the above-described embodiment may be executed by another apparatus such as the server 20. Further, for example, each function shown in FIG. 2 may be implemented by the cooperation of the information processing apparatus 10 and the server 20.

(7) In the above-described embodiment, the program executed by the processor 101 of the information processing apparatus 10 or the processor 201 of the server 20 may be downloaded via a communication line such as the Internet. In addition, these programs are provided in a state of being recorded on a computer-readable recording medium such as a magnetic recording medium (magnetic tape, magnetic disk, etc.), an optical recording medium (optical disk, etc.), an optical magnetic recording medium, or a semiconductor memory. May be done.

10 ... Information processing device, 11 ... Extraction means, 12 ... Acquisition means, 13 ... Image processing means, 14 ... Synthesis means, 15 ... Processing means, 16 ... Recognition means, 101 ... Processor, 102 ... Memory, 103 ... Storage, 104 ... Communication IF, 105 ... UI unit, 106 ... Image forming unit, 107 ... Image reading unit, 108 ... Image processing unit.

Claims (5)

Extraction means to extract the image of the target area from the specified image,
An acquisition means for acquiring the type of the image of the extracted target area, and
An image processing means that executes image processing corresponding to the type of the target area on the image data representing the image of the extracted target area, and
A compositing means for synthesizing an image represented by the image-processed image data and an image in a region other than the target region.
When the size of the image data representing the image synthesized by the synthesizing means exceeds a predetermined threshold value, the image data of the target area included in the designated image and the image data of the area other than the extracted target area A processing means for reducing the amount of data for at least one of them and performing a process preset for each type .
As a recognition means for recognizing characters or images with respect to the image of the target area processed by the processing means.
Have,
For the target area where the recognition means fails in the recognition process, the processing means uses the image data before the processing for reducing the amount of data as the image data of the target area.
Information processing equipment. The information processing apparatus according to claim 1, wherein the processing means executes the processing within a range in which the number of pixels in a predetermined range of gradation values does not fall below a predetermined threshold value in the target region. The information processing according to claim 1 or 2 , wherein the processing means performs at least one of a process of lowering the resolution and a process of increasing the compression rate for image data in an area other than the extracted target area. Device. Any one of claims 1 to 3 , wherein the processing means performs at least one of a process of lowering the resolution, a process of increasing the compression rate, and a process of reducing the image size of the image data in the target area. The information processing device described in the section. On the computer
Steps to extract the image of the target area from the specified image,
The step of acquiring the image type of the extracted target area and
A step of executing image processing corresponding to the type of the target area on the image data representing the image of the extracted target area, and
A step of synthesizing an image represented by the image-processed image data and an image of an area other than the target area.
When the size of the image data representing the combined image exceeds a predetermined threshold value, at least one of the image data of the target area included in the designated image and the image data of the area other than the extracted target area. On the other hand, there is a step of reducing the amount of data and performing a process preset for each type .
With the step of recognizing characters or images for the processed image of the target area
It is a program to execute
For the target area where the recognition process failed in the recognition step in the step of performing the process, the image data before the process of reducing the amount of data is used as the image data of the target area.
program.

Images