JP7494586B2 - Image processing device and image processing program - Google Patents

Description

The present invention relates to an image processing device and an image processing program.

Conventionally, there are known multifunction devices equipped with a printer unit that records an image on a medium, a scanner unit that reads an image recorded on an original document and generates image data, and a fax unit that transmits the image data by fax to an external device. Such multifunction devices can perform image processing (compression) of the image data generated by the scanner unit to match the capabilities of the destination device, and transmit the image data after image processing to the destination device.

Among multifunction devices capable of carrying out the above-mentioned processing, there are some that have the function of previewing the image data shown as image data after image processing on a display, allowing the operator to check the image quality before sending it (see, for example, Patent Document 1).

Although the multifunction device with the above configuration can stop the transmission of image data whose image quality has been excessively degraded, the operator must adjust the image quality and have the scanner unit read the document again. This places a heavy burden on the operator.

The present invention has been made to solve these problems, and aims to provide an image processing device that can appropriately adjust and transmit image quality of image data after image processing without increasing the operational burden on the operator.

To solve the above problem, the image processing device includes a display that displays an image, an input unit that accepts input operations from an operator, a communication interface that communicates with an external device, and a controller, and the controller performs image processing on the input image data to generate output image data, displays an output image represented by the output image data on the display, transmits the output image data to the external device through the communication interface when permission to transmit the output image data is input to the input unit, and extracts characters contained in the input image data and the output image data when a refusal to transmit the output image data is input to the input unit, cuts out an image of an erroneous recognition area in the input image represented by the input image data, in which the recognition results of the characters extracted from the input image data and the output image data differ, to generate cut-out image data, combines the cut-out image represented by the cut-out image data with the erroneous recognition area of the output image, and transmits the output image data representing the output image after the cut-out image has been combined to the external device through the communication interface.

According to the present invention, it is possible to appropriately adjust the image quality of image data after image processing and transmit the data without increasing the operational burden on the operator.

FIG. 1 is a schematic diagram of an image processing system. FIG. 2 is a diagram showing the hardware configuration of an MFP. FIG. 2 is a functional block diagram of the MFP. 13 is a flowchart of an image data transmission process. (A) is the fax sending screen, and (B) is the preview screen. 4 is a flowchart of an image quality adjustment process. (A) is the result of OCR processing on scanned image data, and (B) is the result of OCR processing on compressed image data. 5A and 5B are diagrams for explaining the processing of a binarization processing unit.

Below, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a schematic diagram of an image processing system 1. The image processing system 1 is a system that transmits and receives image data between multiple devices connected via a communication network 2. As shown in FIG. 1, in the image processing system 1, multiple MFPs 100A, 100B, and 100C (hereinafter, these may be referred to as "MFPs 100") and a PC 110 are connected via the communication network 2.

MFP100 (MFP: Multifunction Peripheral/Product/Printer) is an example of an image processing device equipped with a printer function for recording an image on a medium, a scanner function for reading an image recorded on an original and generating image data, and a fax function for faxing the image data to an external device. PC110 is another example of an image processing device that has a function for editing image data and is configured to be able to send and receive image data via communication network 2. Furthermore, other examples of image processing devices such as a tablet terminal or a smartphone may be connected to image processing system 1.

Additionally, MFPs 100A, 100B, and 100C are assigned destination information (e.g., FAX number, IP address, etc.) that uniquely identifies the device on communication network 2. In this embodiment, the destination information of MFP 100A is "xx-xxxx-xxxx", the destination information of MFP 100B is "yy-yyyy-yyyy", and the destination information of MFP 100C is "zz-zzzz-zzzz". Although not shown in the figure, destination information is also assigned to PC 110.

Furthermore, MFPs 100A, 100B, and 100C may differ from each other in processing capabilities (e.g., paper size, resolution, color). Paper size refers to, for example, the size of an original that can be read by scanner unit 231 and the size of a medium on which an image can be formed by printer unit 232. Resolution refers to, for example, the resolution of image data that can be generated by scanner unit 231 and the resolution of image data that can be formed by printer unit 232. Color refers to, for example, the colors that can be read by scanner unit 231 and the colors that can be formed on a medium by printer unit 232.

In this embodiment, MFPs 100A and 100C support paper sizes "A3", "A4", and "A5", resolutions "600 dpi", "400 dpi", and "300 dpi", and colors "color" and "monochrome". MFP 100B supports the maximum paper sizes "A4" and "A5", maximum resolutions "400 dpi" and "300 dpi", and color "monochrome". MFPs 100A, 100B, and 100C can mutually exchange (transmit and receive) capability information indicating processing capabilities using NSF and DIS based on ITU-T Recommendation T.30.

The communication network 2 is composed of part or all of the Internet, public telephone lines, LAN, etc. Furthermore, the communication network 2 may support not only wired communication but also wireless communication. The devices 100A, 100B, 100C, and 110 connected to the communication network 2 can communicate in a manner conforming to various protocols such as HTTP, FTP, and FAX protocols.

Figure 2 is a hardware configuration diagram of the MFP 100. As shown in Figure 2, the MFP 100 includes a controller 210, a short-range communication I/F 220, an engine control unit 230, an operation panel 240 (input unit), and a network I/F 250 (communication interface).

Of these, the controller 210 has a CPU 201, which is the main part of the computer, a system memory (MEM-P) 202, a north bridge (NB) 203, a south bridge (SB) 204, an ASIC (Application Specific Integrated Circuit) 206, a local memory (MEM-C) 207, which is a storage unit, a HDD controller 208, and a HD 209, which is also a storage unit, and is configured such that the NB 203 and the ASIC 206 are connected by an AGP (Accelerated Graphics Port) bus 221.

Of these, the CPU 201 is a control unit that performs overall control of the MFP 100. The NB 203 is a bridge that connects the CPU 201 with the MEM-P 202, the SB 204, and the AGP bus 221, and includes a memory controller that controls reading and writing to the MEM-P 202, a PCI (Peripheral Component Interconnect) master, and an AGP target.

The MEM-P 202 consists of a ROM 202a, which is memory for storing programs and data that realize the various functions of the controller 210, and a RAM 202b, which is used for expanding programs and data, and as a drawing memory during memory printing. The programs stored in the RAM 202b may be provided by recording them in an installable or executable format on a computer-readable recording medium such as a CD-ROM, CD-R, or DVD.

SB204 is a bridge for connecting NB203 with PCI devices and peripheral devices. ASIC206 is an IC (Integrated Circuit) for image processing purposes that has hardware elements for image processing, and plays the role of a bridge connecting AGP bus221, PCI bus222, HDD controller208, and MEM-C207. This ASIC206 is composed of a PCI target and AGP master, an arbiter (ARB) that is the core of ASIC206, a memory controller that controls MEM-C207, multiple DMACs (Direct Memory Access Controllers) that rotate image data using hardware logic, and a PCI unit that transfers data between scanner unit231, printer unit232, and FAX unit233 via PCI bus222. In addition, a USB (Universal Serial Bus) interface or an IEEE 1394 (Institute of Electrical and Electronics Engineers 1394) interface may be connected to the ASIC 206.

The MEM-C 207 is a local memory used as an image buffer for copying and a code buffer. The HD 209 is a storage for storing image data, font data used during printing, and forms. The HD 209 controls the reading and writing of data from and to the HD 209 under the control of the CPU 201. The AGP bus 221 is a bus interface for a graphics accelerator card proposed to speed up graphic processing, and by directly accessing the MEM-P 202 with high throughput, the graphics accelerator card can be made faster.

The short-range communication I/F 220 also includes a short-range communication circuit 220a. The short-range communication circuit 220a is a communication circuit such as NFC or Bluetooth (registered trademark).

The engine control unit 230 is also connected to a scanner unit 231, a printer unit 232, and a fax unit 233. The scanner unit 231 reads an original document set on the contact glass or an ADF (Auto Document Feeder) and generates image data. The printer unit 232 forms an image indicated by the specified image data on a medium (e.g., paper, an OHP sheet). The fax unit 233 transmits and receives image data to and from an external device in accordance with the fax protocol.

The operation panel 240 also includes a panel display unit 240a (display) such as a touch panel that displays the current settings and selection screens and accepts input from the operator, and an operation panel 240b that includes a numeric keypad that accepts settings for image formation conditions such as density settings and a start key that accepts a copy start command. The controller 210 controls the entire MFP 100, and controls, for example, drawing, communication, and input from the operation panel 240.

The MFP 100 can sequentially switch between the document box function, copy function, printer function, and facsimile function using the application switching key on the operation panel 240. When the document box function is selected, the mode becomes document box mode, when the copy function is selected, the mode becomes copy mode, when the printer function is selected, the mode becomes printer mode, and when the facsimile mode is selected, the mode becomes facsimile mode.

The network I/F 250 is an interface for data communication using the communication network 2. The short-range communication I/F 220 and the network I/F 250 are electrically connected to the ASIC 206 via the PCI bus 222.

Next, the processing executed by the controller 210 will be described with reference to Figures 3 to 5. Figure 3 is a functional block diagram of the MFP 100. Figure 4 is a flowchart of the image data transmission processing. Figure 5 shows an example of a screen displayed on the panel display unit 240a during the image data transmission processing, where (A) shows a FAX transmission screen and (B) shows a preview screen.

As shown in FIG. 3, the MFP 100 includes a scan processing unit 310, an image compression unit (image processing unit) 320, a preview processing unit 330, a FAX transmission unit 340, and an image quality adjustment unit 350. The image quality adjustment unit 350 also includes an OCR processing unit 351, an image cropping unit 352, a binarization processing unit 353, and an image synthesis unit 354. Each of the functional blocks 310 to 354 shown in FIG. 3 is a functional unit that is realized when the CPU 301 in the controller 210 loads an image processing program stored in the HD 209 into the RAM 202b and executes the program.

The image data transmission process shown in FIG. 3 is started, for example, when the FAX unit 233 is started via the operation panel 240. Below, an example will be described in which the controller 210 of the MFP 100A executes the image data transmission process. However, the image data transmission process may also be executed by the MFP 100B, 100C, or the PC 110.

First, the scan processing unit 310 displays the fax transmission screen shown in FIG. 5(A) on the panel display unit 240a (S401). The fax transmission screen is a screen that allows the operator to specify the conditions for fax transmission (e.g., destination information, document reading conditions, etc.). However, the layout of the fax transmission screen is not limited to that shown in FIG. 5(A).

5A, the FAX transmission screen includes a text box 511 for receiving input of destination information, pull-down menus 512, 513, and 514 for receiving selection of document size, reading resolution _R1 (first resolution), and reading color, and an [Execute] button 515. A plurality of options corresponding to capability information of the MFP 100 are set in the pull-down menus 512, 513, and 514.

Then, the scan processing unit 310 waits to execute the processes from step S403 onwards until a destination is entered in the text box 511 via the operation panel 240, reading conditions are set in the pull-down menus 512 to 514, and the [Execute] button 515 is pressed (S402: No). In this embodiment, the following process will be described assuming that destination information "yy-yyyy-yyyy" is entered in the text box 511, and document size "A4", reading resolution _R1 "600 dpi", and reading color "monochrome" are selected in the pull-down menus 512, 513, and 514 as shown in FIG. 5A.

Next, when the [Execute] button 515 is pressed (S402: Yes), the scan processing unit 310 causes the scanner unit 231 to read the document set on the contact glass or ADF according to the reading conditions specified in the pull-down menu (S403). That is, the scanner unit 231 reads the image recorded on the A4-sized document, generates monochrome read image data (input image data) with a resolution of 600 dpi, and saves the generated read image data in the HD 209. The scan processing unit 310 then hands over control to the image compression unit 320 (S404).

Next, image compression unit 320, which has taken over control from scan processing unit 310, acquires capability information from MFP 100B identified by destination information "yy-yyyy-yyyy" entered in text box 511, via network I/F 250 (S404). Hereinafter, the maximum resolution "400 dpi" included in the capability information of MFP 100B will be referred to as "destination resolution _R2 (second resolution)." Then, image compression unit 320 compares reading resolution _R1 with destination resolution _R2 (S405).

When the reading resolution _R1 is greater than the destination resolution _R2 (S405: Yes), the image compression unit 320 compresses the read image data of the reading resolution _R1 to generate compressed image data (input image data) of the destination resolution _R2 , and stores the generated compressed image data in the HD 209 (S406). In other words, the compressed image data is image data with a lower resolution than the read image data. Well-known techniques can be used to compress image data. Hereinafter, an image represented by the read image data will be referred to as a "read image (input image)" and an image represented by the compressed image data will be referred to as a "compressed image (output image)".

Then, the image compression unit 320 passes control to the preview processing unit 330 (S407). On the other hand, if the reading resolution _R1 is equal to or lower than the destination resolution _R2 (S405: No), the image compression unit 320 skips the processes of steps S407 to S409 and passes control to the FAX transmission unit 340 (S410).

Next, the preview processing unit 330, which has taken over control from the image compression unit 320, displays the preview screen shown in FIG. 5(B) on the panel display unit 240a (S407). The preview screen is a screen that allows the operator to check the compressed image represented by the compressed image data. However, the layout of the preview screen is not limited to the example of FIG. 5(B).

As shown in FIG. 5 (B), the preview screen includes a preview area 521 that displays the compressed image, a [+ Enlarge] button 522, a [- Reduce] button 523, a [Send] button 524, and an [Adjust] button 525. The [+ Enlarge] button 522 is a button that instructs the compressed image to be displayed enlarged in the preview area 521. The [- Reduce] button 523 is a button that instructs the compressed image to be displayed reduced in the preview area 521. The [Send] button 524 is a button that allows the transmission of compressed image data. The [Adjust] button 525 is a button that refuses the transmission of compressed image data (in other words, instructs the adjustment of the compressed image data).

Then, the preview processing unit 330 waits to execute the processes from step S409 onwards until either the [Send] button 524 or the [Adjust] button 525 is pressed via the operation panel 240 (S408). Furthermore, when the [+ Enlarge] button 522 is pressed, the preview processing unit 330 increases the magnification of the compressed image in the preview area 521, and when the [- Reduce] button 523 is pressed, the preview processing unit 330 decreases the magnification of the compressed image in the preview area 521.

The operator checks the image quality of the compressed image displayed in the preview area 521 while pressing the [+ Zoom in] button 522 and the [- Zoom out] button 523 as necessary. Then, if there is no problem with the image quality of the compressed image (for example, if the characters contained in the compressed image are distinguishable), the operator presses the [Send] button 524. On the other hand, if there is a problem with the image quality of the compressed image (for example, if the compressed image contains characters that are difficult to distinguish), the operator presses the [Adjust] button 525.

Then, when the [Adjust] button 525 is pressed (i.e., a refusal to send compressed image data is input) (S408: Adjust), the preview processing unit 330 hands over control to the image quality adjustment unit 350 (S409). On the other hand, when the [Send] button 524 is pressed (i.e., permission to send compressed image data is input) (S408: Send), the preview processing unit 330 hands over control to the FAX sending unit 340 (S410).

The FAX transmission unit 340, which has taken over control from the preview processing unit 330, controls the FAX unit 233 to FAX the compressed image data stored in the HD 209 to the MFP 100B specified by the destination information "yy-yyyy-yyyy" through the network I/F 250 (S410). The FAX transmission unit 340, which has taken over control from the image compression unit 320, controls the FAX unit 233 to FAX the scanned image data stored in the HD 209 to the MFP 100B specified by the destination information "yy-yyyy-yyyy" through the network I/F 250 (S410). Note that "FAX transmission" refers to the transmission of image data in a procedure that complies with the FAX protocol.

Furthermore, the image quality adjustment unit 350, which has taken over control from the preview processing unit 330, executes image quality adjustment processing (S409). Figure 6 is a flowchart of the image quality adjustment processing. Figure 7 (A) shows the result of OCR processing on the scanned image data, and (B) shows the result of OCR processing on the compressed image data. Figure 8 is a diagram for explaining the processing of the binarization processing unit 353. The image quality adjustment processing is processing for adjusting the image quality of the compressed image data stored in HD 209.

First, the OCR processing unit 351 of the image quality adjustment unit 350 performs filtering, binarization, and OCR processing on the scanned image data and compressed image data stored in the HD 209 (S601). The image quality adjustment unit 350 then stores the processing results in the HD 209 and hands over control to the image cutout unit 352 (S602).

More specifically, the OCR processing unit 351 performs filter processing to enhance edges on both the scanned image data and the compressed image data. An edge refers to the boundary between the background color and the characters contained in the image represented by the image data. A specific example of filter processing to enhance edges is a Laplacian filter.

Next, the OCR processing unit 351 binarizes each of the scanned image data and compressed image data after the filter processing. Binarization is a process in which, of the multiple pixel values that make up each image data, a pixel value of "1" is set to pixels whose pixel values are equal to or greater than the binarization threshold, and a pixel value of "0" is set to pixels whose pixel values are less than the binarization threshold. As a result, of the images shown by each image data, a pixel value of "1" is set to pixels that make up characters, and a pixel value of "0" is set to pixels that make up the background color. The binarization threshold may be a predetermined fixed value, or a variable value that matches the characteristics of the image data.

Next, the OCR processing unit 351 performs OCR processing on each of the scanned image data and compressed image data after the binarization processing. The OCR processing is a process for extracting characters contained in each image. More specifically, the OCR processing is a process for extracting character codes (e.g., ASCII, Unicode, etc.) corresponding to character images contained in each image.

OCR processing is realized, for example, by a well-known OCR engine, and is performed, for example, according to the following procedure. First, the OCR processing unit 351 normalizes the character image extracted from the image to a predetermined size and extracts features (directional components). Next, the OCR processing unit 351 matches the features extracted from the character image with a standard pattern prepared in advance. Then, the OCR processing unit 351 extracts the character code associated with the standard pattern with the highest degree of match of features as the character code corresponding to the character image. However, the specific processing method of OCR processing is not limited to the above example.

Next, the image cutout unit 352, which has taken over the process from the OCR processing unit 351, compares the characters (character codes) extracted from the corresponding areas of the read image and the compressed image. Then, the OCR processing unit 351 identifies an erroneous recognition area where the recognition results of the characters extracted from the corresponding areas differ (S602). In the example of FIG. 7, of the corresponding areas of the read image and the compressed image, the recognition results of the character "c" extracted from the read image (FIG. 7(A)) and the character "o" extracted from the compressed image (FIG. 7(B)) differ.

Next, the image cutting unit 352 cuts out the image of the erroneous recognition area from the read image to generate cut-out image data. In this embodiment, as shown in FIG. 8, a rectangular image surrounding the letter "c" in FIG. 7(A) is cut out. The image cutting unit 352 also compresses the generated cut-out image data from the reading resolution _R1 to the destination resolution _R2 , and stores the compressed cut-out image data in the HD 209 (S603). That is, in step S603, the image cutting unit 352 performs image processing on the cut-out image data to generate output image data from the input image data. Hereinafter, the image represented by the cut-out image data will be referred to as a "cut-out image". Then, the image cutting unit 352 hands over control to the binarization processing unit 353.

Next, the binarization processing unit 353, which has taken over control from the image cropping unit 352, executes a filter process (first filter process) on the cropped image data compressed to the destination resolution _R2 (S604). The filter process in step S604 is a process for enhancing the edges of the cropped image, and the specific method may be the same as that in step S601.

Next, the binarization processing unit 353 extracts the minimum pixel value _Pmin of the edge pixels and the maximum pixel value _Pmax of the non-edge pixels from the cut-out image data after the filter processing (S605). The edge pixels are pixels that make up the edges in the cut-out image, and refer to pixels such as 1-D, 1-E, 2-B, 2-C, 2-E, 3-C, and 3-D in Fig. 8. The non-edge pixels are pixels that make up the background color in the cut-out image, and refer to pixels other than the aforementioned pixels in Fig. 8.

The minimum pixel value _Pmin indicates the pixel value of the pixel (e.g., pixel 2-B) that is closest to the background color among the multiple edge pixels that make up the edge of the cutout image. On the other hand, the pixel values of the non-edge pixels vary due to dust on the document, noise during reading, etc. Therefore, the maximum pixel value _Pmax indicates the pixel value of the pixel that has the most components other than the background color among the multiple non-edge pixels that make up the background color of the cutout image.

Next, the binarization processing unit 353 compares the minimum pixel value _Pmin of the edge pixels with the maximum pixel value _Pmax of the non-edge pixels (S606). If the minimum pixel value _Pmin is greater than the maximum pixel value _Pmax (S606: Yes), the binarization processing unit 353 performs binarization processing on the cutout image data using the maximum pixel value _Pmax as a binarization threshold value (S607).

On the other hand, if the minimum pixel value _Pmin is equal to or smaller than the maximum pixel value _Pmax (S606: No), the binarization processing unit 353 executes a second filter process on the cutout image data (S604).Then, the binarization processing unit 353 repeatedly executes the processes of steps S604 to S606 until the minimum pixel value _Pmin becomes greater than the maximum pixel value _Pmax (S606: No).

Note that in step S604 for the Nth (N is an integer equal to or greater than 2) time, the binarization processing unit 353 executes a filter process (Nth filter process) that further emphasizes edges compared to step S604 for the (N-1) time. As a specific method for further emphasizing edges, for example, the parameters of the Laplacian filter may be changed between the Nth filter process and the (N-1)th filter process, or filter processes using different algorithms may be executed.

The binarization process in step S607 may be the same as that in step S601. As a result, the pixels that make up the characters in the cut-out image are set to a pixel value of "1", and the pixels that make up the background color are set to a pixel value of "0". Next, the binarization processing unit 353 stores the cut-out image data after the binarization process in the HD 209. Then, the binarization processing unit 353 hands over control to the image synthesis unit 354 (S608).

Next, the image synthesis unit 354, which has taken over control from the binarization processing unit 353, synthesizes the cut-out image represented by the binarized cut-out image data into the erroneous recognition area of the compressed image represented by the binarized compressed image data (S608). In this embodiment, the rectangular image surrounding the letter "o" in FIG. 7(B) is replaced with a rectangular image surrounding the letter "c" in FIG. 8. Next, the image synthesis unit 354 overwrites the compressed image data stored in the HD 209 with compressed image data representing the compressed image after synthesis with the cut-out image. Then, the image synthesis unit 354 hands over control to the preview processing unit 330 (S407).

Returning to FIG. 4, the preview processing unit 330, which has taken over control from the image synthesis unit 354, executes the processes from step S407 onwards using the compressed image data whose image quality has been adjusted in the image quality adjustment process. That is, the controller 210 repeatedly executes the processes from step S407 to S409 until the operator presses the [Send] button 524. Then, when the operator presses the [Send] button 524 (S408: Send), the FAX transmission unit 340 causes the FAX unit 233 to FAX the compressed image data stored in the HD 209 (i.e., whose image quality has been adjusted) to the MFP 100B (S410).

The above embodiment provides the following advantages:

According to the above embodiment, if the operator judges that the characters are not legible when looking at the preview screen (S408: Adjustment), the image quality adjustment process (S409) is executed, so that the image quality of the compressed image data can be appropriately adjusted and sent without increasing the operational burden on the operator. Note that, although the above embodiment describes an example in which the preview screen is displayed again (S407) after the image quality adjustment process (S409), step S410 may be executed directly after the image quality adjustment process.

In addition, according to the above embodiment, a cut-out image is synthesized in an erroneous recognition area where the character recognition results extracted from the read image data and the compressed image data are different, so that it is possible to selectively adjust the image quality of parts where the characters are blurred and difficult to distinguish. In this way, the present invention has a particularly advantageous effect when reading an original (document original) that is mainly composed of characters to generate read image data. However, the input image data that is the subject of the present invention is not limited to that containing only characters, but may contain at least characters and also include patterns (e.g., illustrations, photographs, graphs, tables, etc.).

In addition, according to the above embodiment, the compressed image data and the cut-out image data are binarized before being combined, so the characters contained in each image become clearer. In this way, the present invention has a particularly advantageous effect when scanning an original in monochrome to generate scanned image data.

Furthermore, according to the above embodiment, the filtering process is repeatedly performed until the minimum pixel value _Pmin of the edge pixels becomes larger than the maximum pixel value _Pmax of the non-edge pixels, and the cut-out image data is binarized using the maximum pixel value _Pmax of the non-edge pixels as the binarization threshold value, so that the characters included in the cut-out image can be made even clearer.

In the above embodiment, the scanned image data generated by the scanner unit 231 has been described as an example of input image data, but specific examples of input image data are not limited to this. As another example, when the PC 110 executes the image data transmission process, image data created (edited) using an image creation (editing) application may be used as the input image data. As yet another example, when a tablet terminal or smartphone executes the image data transmission process, image data captured by a built-in camera may be used as the input image data.

In addition, in the above embodiment, an example of sending image data by fax has been described, but the protocol for sending image data is not limited to the fax protocol, and any protocol capable of sending and receiving image data, such as HTTP or FTP, can be applied.

In the above embodiment, the destination resolution _R2 is determined according to the capabilities of the destination device, but the method of determining the destination resolution _R2 is not limited to the above example. As another example, the destination resolution _R2 may be determined according to the bandwidth of the communication network 2, or may be a predetermined fixed value. The same applies to the method of determining the reading resolution _R1 .

Furthermore, in the above embodiment, an example was described in which the scanned image data was compressed to generate compressed image data, but the image processing for generating output image data from input image data is not limited to "compression". In other words, the controller 210 may perform image processing on the input image data that reduces image quality to generate output image data. Other examples of image processing include contrast correction, brightness correction, color correction, noise removal, enlargement and reduction, etc.

Each function of the above-described embodiments can be realized by one or more processing circuits. In this specification, the term "processing circuit" includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, and devices such as an ASIC (Application Specific Integrated Circuit), DSP (digital signal processor), FPGA (field programmable gate array), and conventional circuit modules designed to execute each function described above.

The correspondence table in the specification may be generated by the learning effect of machine learning. In addition, by classifying each parameter by machine learning, it is not necessary to use a correspondence table. Here, machine learning is a technology for enabling a computer to acquire human-like learning capabilities, and refers to a technology in which a computer autonomously generates an algorithm required for judgment such as data identification from learning data that is previously loaded, and applies this to new data to make predictions. The learning method for machine learning may be any of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning, or may be a combination of these learning methods. Any learning method for machine learning is acceptable.

The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the technical gist of the invention. All technical matters included in the technical ideas described in the claims are covered by the present invention. The above-described embodiment shows a preferred example, but a person skilled in the art can realize various modifications from the disclosed contents. Such modifications are also included in the technical scope described in the claims.

1: Image processing system 2: Communication network 100: MFP
110: PC
201: CPU
202a: ROM
202b: RAM
206: ASIC
208: HDD controller 210: Controller 220: Short-range communication I/F
220a: short-distance communication circuit 221: AGP bus 222: PCI bus 230: engine control unit 231: scanner unit 232: printer unit 233: FAX unit 240: operation panel 240a: panel display unit 240b: operation panel 250: network I/F
301: CPU
310: Scan processing section 320: Image compression section 330: Preview processing section 340: FAX transmission section 350: Image quality adjustment section 351: OCR processing section 352: Image cropping section 354: Image synthesis section 511: Text boxes 512, 513, 514: Pull-down menu 515: [Execute] button 521: Preview area 522: [+Enlarge] button 523: [-Reduce] button 524: [Send] button 525: [Adjust] button

JP 2016-058856 A

Claims (6)

A display for displaying an image;
an input unit that accepts input operations from an operator;
A communication interface for communicating with an external device;
A controller.
The controller:
performing image processing on the input image data to generate output image data;
displaying an output image represented by the output image data on the display;
When a transmission permission for the output image data is input to the input unit, the output image data is transmitted to an external device through the communication interface;
When a refusal to transmit the output image data is input to the input unit,
Extracting characters contained in each of the input image data and the output image data;
generating cut-out image data by cutting out an image of an erroneous recognition area in which the character recognition results extracted from the input image data and the output image data differ from each other, from the input image represented by the input image data;
The cut-out image represented by the cut-out image data is synthesized into the erroneous recognition area of the output image;
The image processing apparatus is characterized in that the output image data indicating the output image after the cut-out image is combined is transmitted to an external device via the communication interface. The image processing device according to claim 1, characterized in that the controller compresses the input image data of a first resolution as the image processing, and generates the output image data of a second resolution lower than the first resolution. The controller:
compressing the cropped image data from the first resolution to the second resolution;
repeatedly performing a filter process for emphasizing the edge on the cutout image data at the second resolution until a minimum pixel value at an edge position that is a boundary between a background color and a character becomes greater than a maximum pixel value at a background color position;
the maximum pixel value, which is smaller than the minimum pixel value, is used as a binarization threshold value to binarize the cut-out image data;
3. The image processing apparatus according to claim 2 , wherein the cut-out image represented by the binarized cut-out image data is synthesized into the erroneous recognition area of the output image . The controller:
A filter process is performed on each of the input image data and the output image data to emphasize edges that are boundaries between background colors and characters;
binarizing the input image data and the output image data after the filtering process;
3. The image processing apparatus according to claim 1, further comprising: extracting characters contained in the binarized input image data and the binarized output image data. a scanner unit that reads an image recorded on an original and generates the input image data;
5. The image processing apparatus according to claim 1, wherein the controller performs the image processing on the input image data generated by the scanner unit to generate the output image data. A display for displaying an image;
an input unit that accepts input operations from an operator;
An image processing program executed by a computer connected to a communication interface for communicating with an external device,
generating output image data by performing image processing on the input image data;
displaying an output image represented by the output image data on the display;
When a transmission permission for the output image data is input to the input unit, the output image data is transmitted to an external device through the communication interface;
When a refusal to transmit the output image data is input to the input unit,
Extracting characters contained in the input image data and the output image data,
generating cut-out image data by cutting out an image of an erroneous recognition area in which the character recognition results extracted from the input image data and the output image data differ from each other, from the input image represented by the input image data;
The cut-out image represented by the cut-out image data is synthesized into the erroneous recognition area of the output image;
An image processing program that causes the computer to execute a process of transmitting the output image data indicating the output image after the cut-out image is combined with an external device via the communication interface.