JP2021005234A - Form recognition device, form recognition method, and form recognition system - Google Patents

Abstract

To remove shaded pixels of various shapes.SOLUTION: A form recognition device comprises: a shaded area extraction unit that extracts a shaded area from a form image by extracting pixels in which a continuous length of black pixels is a predetermined value or less in units of rows and columns of the form image input from an image input unit; and a shading removal unit that removes shaded pixels from the form image by removing pixels in which a continuous length of black pixels is a predetermined value or less in units of rows and columns in the shaded area of the form image.SELECTED DRAWING: Figure 3

Description

The present invention relates to a technique for extracting a shaded area described on a form image, removing shaded pixels, and recognizing a form.

The form recognition device represented by the optical character recognition device (OCR) analyzes the layout of the ruled lines, frames, character strings, etc. of the form to be processed, and recognizes the characters in the character string.

In normal form recognition, characters written on a uniform background are recognized. However, the characters described in the shaded area cannot be recognized by normal OCR because the background and the characters cannot be correctly separated due to the influence of the shaded area. In order to recognize the characters on the shaded area, it is necessary to extract the shaded area and remove the shaded pixels.

As a technique for extracting a shaded area from a form and recognizing characters, for example, there is a technique disclosed in Patent Document 1. In this technique, a shaded area is determined by analyzing a histogram of isolated points, and shaded pixels are removed.

Japanese Unexamined Patent Publication No. 2001-76096

Since the method of Patent Document 1 uses a histogram of isolated points, only shading composed of small points can be supported. It cannot be used for shading where thin diagonal lines intersect.

An object of the present invention is to provide a technique for extracting a shaded area and removing the shaded area not only in a shaded pattern composed of isolated points but also in a shaded pattern in which lines intersect.

The form recognition device in the present invention preferably extracts a form image input from an image input unit in rows and columns so that the continuous length of black pixels is equal to or less than a predetermined value. In the shaded area extraction unit that extracts the shaded area from the form image and the shaded area of the form image, the continuous length of black pixels in row units and column units is equal to or less than a predetermined value. The form recognition device is configured to include a shading removal unit that removes shading pixels from the form image by removing the pixels of the above.

The present invention is also understood as a form recognition method and a form recognition system performed in the form recognition device.

According to one aspect of the present invention, various shaded pixels can be removed.

It is a block diagram of the form recognition apparatus of 1st Embodiment. This is an example of the form image to be input and the processing result. It is a figure which shows the flow of the shading removal processing of 1st Embodiment. This is an example of a form image to be input. This is an example of the shaded pixel candidate extraction processing result of the first embodiment. This is an example of the shaded pixel candidate extraction processing result of the first embodiment. This is an example of the shaded pixel candidate concatenation processing result of the first embodiment. This is an example of the shaded area extraction processing result of the first embodiment. This is an example of the shaded pixel removal processing result of the first embodiment. It is a figure which shows the GUI of the shading removal parameter setting of 2nd Embodiment. This is an example of a test image for confirming the behavior of the shading removal process. It is a figure which shows the flow which determines the parameter of the shading removal processing of 3rd Embodiment automatically. It is a figure which shows the configuration example of the form recognition system.

Hereinafter, embodiments will be described in detail with reference to the drawings. However, the present invention is not construed as being limited to the description of the embodiments shown below. It is easily understood by those skilled in the art that a specific configuration thereof can be changed without departing from the idea or purpose of the present invention.

In the configuration of the invention described below, the same reference numerals may be used in common among different drawings for the same parts or parts having similar functions, and duplicate description may be omitted.

The notations such as "first", "second", and "third" in the present specification and the like are attached to identify the components, and do not necessarily limit the number or order. In addition, numbers for identifying components are used for each context, and numbers used in one context do not always indicate the same composition in other contexts. Further, it does not prevent the component identified by a certain number from having the function of the component identified by another number.

The position, size, shape, range, etc. of each configuration shown in the drawings and the like may not represent the actual position, size, shape, range, etc. in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings and the like.

Components represented in the singular form herein shall include the plural form unless explicitly stated in the context.

Subsequently, the form recognition device, the form recognition method, and the form recognition program in this embodiment will be described in detail with reference to the drawings. First, the hardware configuration will be described.

FIG. 1 is a hardware configuration example of the form recognition device 100 in this embodiment. The form recognition device 100 is a computer device including an operation unit 110, a display unit 120, an image input unit 130, a storage unit 140, a control unit 150, and an interface (IF) 160.

The operation unit 110 is composed of devices that are general in terms of hardware, such as a keyboard used when a user inputs numbers and characters, and a button for instructing the start of scanning. The display unit 120 is composed of a device that is general as hardware, such as a liquid crystal display that displays an input image, a recognition result, or the like.

The image input unit 130 is derived from a device generally used as hardware, such as a flatbed scanner, a scanner with an auto sheet feeder, and a digital camera that captures an image using an image sensor such as a CCD (Charge Coupled Device). It is composed. The storage unit 140 is composed of devices that are general in terms of hardware, such as a storage device including a memory or a hard disk device. The storage unit 140 stores the image input by the image input unit 130, various internal processing programs, and various setting data. In addition, the storage unit 140 stores a character identification dictionary and the like.

The control unit 150 is composed of a device that is generally used as hardware, such as a CPU (Central Processing Unit). The control unit 150 performs form recognition for extracting a shaded area, removing shaded pixels, detecting a character string, recognizing a character string, and controlling the entire device. As the input image, the image data recorded in the storage unit 140 may be used instead of being imaged by the image input unit 130. The IF160 is composed of devices that are generally used as hardware, such as a NIC (Network Interface Card), and inputs / outputs data to and from other devices.

The processing in each of the following embodiments is realized by the control unit 150 reading the program stored in the storage unit 140, loading it into the memory, and executing the program. For example, the control unit 150 has functions such as an image input unit, a shaded area extraction unit, a shaded removal unit, a binarization unit, a character recognition unit, a parameter setting unit, a form recognition unit, a score calculation unit, and a parameter recording unit. Load and execute the program or module to realize.

The program may be downloaded from the network to the storage unit 140 via the IF 160, loaded into the memory, and executed by the control unit 150. In addition, it is directly loaded onto the memory from the storage medium via a reading device that reads and writes information to a storage medium that can be read by a portable computer such as a CD (Compact Disk) or DVD (Digital Versatile Disk). , May be executed by the control unit 150. Further, the program may be recorded on the storage medium in a file in a computer-installable format or an executable format, provided, or distributed. Further, the above program may be provided or distributed by storing it on a computer connected to a communication network and downloading it via the network.

(First Embodiment)
The form device 100 in the present embodiment generates an image obtained by removing the shading shown in FIG. 2 (B) from the input image shown in FIG. 2 (A). FIG. 3 shows a schematic processing flow of form recognition in the control unit 150. The shaded area is an area on the form to be processed in which a predetermined minute pattern (for example, a point) or the intersection of thin lines is periodically arranged. Further, in the following description, the term "character" includes not only character information such as kana and kanji, but also various identification information such as alphanumeric characters, symbols, symbols, and figures. These points are the same for each embodiment from the first embodiment to the third embodiment. In the description of the present embodiment, the shaded image of FIG. 4 will be described as an example. While FIG. 2 shows shaded isolated points, FIG. 4 shows shaded lines at the intersection of lines rather than isolated points. The following example is also effective for shading represented by isolated points in FIG.

FIG. 3 shows a processing flow diagram of form recognition executed by the control unit 150.
First, in the image input in step 300, the control unit 150 (shaded area extraction unit) reads out the form image input by the image input unit 130. Since the subsequent processing is based on the assumption of a binary image, when a color image form is input, the control unit 150 (binary unit) is binarized and a binary image form is input. Is used as it is for the subsequent processing.

There is "run length coding" as a method of coding a binary image. Run-length coding is a method of replacing information on the starting point coordinates of continuous black pixels and the continuous length (run-length). For example, the run-length code in the horizontal direction records the length continuous with the start point coordinates of the black pixels for the black pixels continuous in the horizontal direction. The run-length code in the vertical direction is similarly encoded for consecutive black pixels in the vertical direction. In this embodiment, an example of processing using a run-length code will be described. However, other coding methods may be used.

Next, in the shaded area extraction process of step 305, the control unit 150 (shaded area extraction unit) extracts the shaded area from the input form image. Step 305 is composed of five processes from step 310 to step 350.

In the horizontal shaded pixel candidate extraction process of step 310, the control unit 150 (shaded area extraction unit) obtains shaded pixel candidates for each row of the binary image. Specifically, the shaded area extraction unit selects runs having a length equal to or less than a predetermined length, and if the distance between the selected runs is within a predetermined distance, candidates for shaded pixels in the horizontal direction are selected. And. In the example of FIG. 5A, it is a processing result when the length of the run in the horizontal direction is 3 pixels or less and the interval is 3 pixels or less with respect to the input image of FIG. Among the black pixels in FIG. 4, the pixels extracted as candidates for shaded pixels are represented by black, and the pixels that are not candidates for shaded pixels are represented by hatching. A quadrangle (for example, quadrangle 501) that surrounds pixels in line units indicates that the interval between runs of shaded pixel candidates is 3 pixels or less, and is a region that is close to each other in the horizontal direction. In this way, the shaded area extraction unit evaluates the continuity of the black pixels in the horizontal direction of the form image and extracts candidates for the shaded pixels in the horizontal direction.

Next, in the vertical shaded pixel candidate extraction process in step 320, the control unit 150 (shaded area extraction unit) executes the same process as in step 310 in column units. FIG. 5B is the result of executing the process of step 320 on the input image of FIG. A quadrangle (for example, a quadrangle 502) that surrounds pixels in a column unit indicates that the interval between runs of shaded pixel candidates is 3 pixels or less, and the regions are close to each other in the vertical direction. In this way, the shaded area extraction unit evaluates the continuity of the black pixels in the vertical direction of the form image and extracts candidates for the shaded pixels in the vertical direction.

Next, in the shaded pixel candidate extraction process in step 330, the control unit 150 (shaded area extraction unit) takes the logical product of the pixels extracted in the processes of step 310 and step 320. The shaded area extraction unit uses the black pixels after taking this logical product as candidates for shaded pixels. FIG. 6 is a result of taking a logical product between the black pixels of FIGS. 5 (A) and 5 (B). Black is a pixel whose logical product result is true, and hatching and white are pixels whose logical product result is false. The shaded area extraction unit uses pixels that are true in the logical product as candidates for shaded pixels. As described above, the shaded area extraction unit extracts the black pixels common to both the candidate for the shaded pixel in the horizontal direction and the candidate for the shaded pixel in the vertical direction as the shaded pixel.

Next, in the shaded pixel candidate connection process of step 340, the control unit 150 (shaded area extraction unit) connects when the pixels obtained by ANDing in step 330 are close to each other. FIG. 7 is an example in which intervals of 5 pixels or less are connected to the shaded pixel candidates of FIG. First, the result of connecting in the horizontal direction is FIG. 7 (A), and the result of connecting FIG. 7 (A) in the vertical direction is FIG. 7 (B).

Next, in the shaded area selection process of step 350, the control unit 150 (shaded area extraction unit) detects an area in which the black pixels in the image obtained in step 340 are connected, and shades the area. Let it be an area. The black pixel area of FIG. 8 is a shaded area selected from the image of FIG. 4 based on the result of FIG. 7 ((B) of FIG. 7), and the black pixel of FIG. 4 or 7 (B). Is an area containing. In this way, the shaded area extraction unit uses the adjacently obtained areas obtained by connecting the shaded pixel candidates as the shaded area.

Next, in the shading removal process of step 360, the control unit 150 (shading removing unit) removes the shading pixels from the shading region extracted in step 305. Step 360 is composed of two processes, step 370 and step 380. If necessary, these two processes are repeated N times. The repetition will be described later with reference to FIG. 9B.

In the horizontal shading pixel removal process of step 370, the control unit 150 (shading removing unit) extracts and removes the shaded pixels line by line from the shaded area selected in step 305. The criterion for removing the shading is, for example, the shaded pixel candidate extracted in step 330. In addition, the run is shorter than the reference length (for example, 3 pixels), and there are no black pixels above and below the run. These pixels are removed as shaded pixels.

Next, in the vertical shading pixel removal processing in step 380, the control unit 150 (shading removing unit) executes the same processing as in step 370 in column units. In this way, the shading removal unit evaluates the continuity of the black pixels in the horizontal direction and the vertical direction from the image of the input form corresponding to the shading area extracted by the shading area extraction unit. It is determined that the pixels are shaded, and the shaded pixels are removed.

FIG. 9A shows the result of performing shading removal on FIG. However, since the shaded pixels that are in contact with the boundary line of the characters remain, the vicinity of the boundary is not a straight line.

Therefore, the control unit 150 (shading removal unit) may re-execute the processes of step 370 and step 380 under different conditions. For example, the shading removal unit sets the reference for shading removal in step 370 as a run shorter than the reference length (for example, 3 pixels), and black pixels having white pixels above or below the run. Remove as shaded pixels. Step 380 also implements the same criteria column by column.

FIG. 9B is the result of executing the second shading removal (step 370 and step 380) with respect to FIG. In FIG. 9B, it can be seen that the shading of the character boundaries is removed as compared with FIG. 9A. There is no limit to the number of times the processing of step 370 and step 380 is repeated. However, as the number of times increases, the black pixels of the characters are also removed.

As described above, according to the present embodiment, the shaded area on the form can be detected, and various shaded pixels in the shaded area can be extracted and removed. Therefore, the shaded area can be removed by ordinary OCR. Can recognize the characters in.

(Second Embodiment)
In the first embodiment, a shaded area is extracted from the input image, and shaded pixels in the extracted area are removed. On the other hand, the second embodiment relates to a GUI for adjusting parameters for extracting shaded areas and removing shaded areas.

FIG. 10 is an example of a screen for setting parameters for shading removal. The operation unit 110 receives an operation from the user, and the control unit 150 displays the screen on the display unit 120.

The area 1000 is an area for displaying an input image. If the image cannot be displayed in this area, it can be scrolled. Further, a function of enlargement / reduction may be provided.

The area 1010 is an area for selecting which processing result is obtained from the image shown in the area 1000. In the example of region 1010, the process can be selected with a check box. For example, the control unit 150 displays a check box corresponding to each step shown in FIG. 3, and when any of the check boxes is checked, an image when the checked process is executed is stored in the storage unit 140. Read and display in area 1000. It is assumed that the image in each step is stored in the storage unit 150 in association with the step name at the time of executing each step in FIG. This allows the user to easily confirm what kind of image was generated in which step.

Further, in FIG. 10, the control unit 150 displays the characters recognized by the control unit 150 (character recognition unit) by analyzing the image obtained by the execution of FIG. 3 in the area 1011. As a result, the user can easily grasp what kind of character the input image is finally recognized as. Further, the user can easily grasp the difference between the image in each step and the finally recognized character by comparing the character displayed in the area 1011 with the image displayed in the area 1000 in each step. can do.

The area 1020 is an area for setting parameters for shaded pixel extraction. In this example, the control unit 150 can set the upper limit of the length of the short runs in the vertical direction and the horizontal direction and the upper limit of the interval between the short runs.

Region 1030 is a region for setting parameters for shading removal. In this example, first, the number of times to repeat the shading removal process is specified. Furthermore, the length of the short run in the vertical direction and the horizontal direction can be set. Further, for the pixels on both sides of the short run, there is a check box for selecting whether to remove the pixels unless both sides are white pixels or if one side is white pixels. If not all parameters can be displayed in this area, you can scroll to display them part by part.

As described above, according to the present embodiment, the optimum parameter for shading removal can be set by checking the removal result while changing the parameter according to the shading state on the form.

Further, by using the test image or the test sheet as shown in FIG. 11, the behavior of shading removal can be visualized in detail.

For example, the test image or test sheet shown in FIG. 11 is input to the device to determine whether or not the device can execute the shading removal shown in FIG. 3, and the processing is executed by the device. In the case of an apparatus that cannot remove shading as in this embodiment, only four of the seven shading test patterns shown in FIG. 11, test patterns 1101 to 1104, can be removed. Therefore, it can be determined that the device cannot perform the shading removal as shown in FIG. On the contrary, when all of the seven shaded test patterns shown in FIG. 11 can be removed, it is determined that the device is the device performing the shaded removal as shown in FIG. can do.

(Third Embodiment)
In the second embodiment, the parameters of shading area extraction and shading removal were adjusted using GUI. On the other hand, in the third embodiment, the optimum parameter is automatically determined.

FIG. 12 is a processing flow diagram of parameter determination.
First, in step 1200, the control unit 150 (parameter setting unit) sets the initial value of the maximum score.

Next, in step 1210, the control unit 150 (parameter setting unit) sets the parameters for shading area extraction and shading removal.

Next, in step 1220, the control unit 150 (form recognition unit) executes the shaded area extraction process, the shaded area removal process, and the subsequent character recognition process shown in FIG. 3 using the parameters set in step 1210. ..

Next, in step 1230, the control unit 150 (score calculation unit) calculates a score for evaluating shading removal based on the recognition result in step 1220. Examples of scores include the number and area ratio of isolated points, the number and area ratio of short runs, and the total value of certainty indicating the certainty of the character recognition result obtained when recognizing a character.

Next, in step 1240, the control unit 150 (parameter recording unit) compares the score calculated in step 1230 with the recorded maximum score.

If the score calculated in step 1230 is lower (S1240; No), the process proceeds without doing anything.

If the score calculated in step 1230 is higher (S1240; Yes), in step 1250, the control unit 150 (parameter recording unit) records the parameter set in step 1210.

Next, in step 1260, the control unit 150 (parameter recording unit) records the score calculated in step 1230 as the maximum score.

The process from step 1210 to step 1260 is repeated a plurality of times by changing the parameters of step 1210.

As described above, according to the present embodiment, the optimum shading removal parameter can be determined. The experimental results of each parameter may be displayed on the GUI shown in FIG. 10, for example.

The present invention is not limited to the above-described embodiment, and includes various modifications. For example, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to those having all the described configurations. Further, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.

In the above description, the form recognition device 100 shown in FIG. 1 executes the process shown in FIG. However, for example, the process shown in FIG. 3 may be executed as the form recognition system as shown in FIG. Specifically, when considering a system in which the form recognition device 100 and the server device 200 are connected via the network N, in step 300 shown in FIG. 3, the control unit 150 (shaded area) of the form recognition device 100 The extraction unit) reads the form image input by the image input unit 130, and transmits the read form image to the server device 200 via the IF 160. The control unit 230 of the server device 200 takes the form image received from the form recognition device 100 as an input, executes the same processing as in steps 305 and 360 of FIG. 3, and outputs the image after shading removal via the IF 250. It is transmitted to the form recognition device 100. The control unit 150 of the form recognition device 100 outputs the image after removing the shading received from the server device 200 and displays it on the display unit 120.

With such a configuration, for example, the server device 200 in the cloud environment receives requests for providing the shaded image from various companies having the form recognition device 100 or various departments in the company. Then, the image after shading removal generated according to the request can be transmitted to the above-mentioned company or department. Therefore, in these companies and departments, a desired image after shading can be obtained only by transmitting the above provision request to the server device 200.

Further, the parameter settings in the case of the above configuration may be as follows. For example, when the control unit 150 of the form recognition device 100 displays a check box corresponding to each step shown in FIG. 3 and one of the check boxes is checked, an image when the checked process is executed. Sends a read request to the server device 200. When the control unit 230 of the server device 200 receives the read request from the form recognition device 100, the control unit 230 reads the image when the above-checked process is executed from the storage unit 240 from the storage unit 240 and transmits it to the form recognition device 100. .. The control unit 150 of the form recognition device 100 displays an image received from the server device 200 when the above-mentioned checked process is executed in the area 1000. In this case, it is assumed that the image in each step is stored in the storage unit 240 in association with the step name by the control unit 230 of the server 200 at the time of executing each step in FIG. Similarly, for the characters displayed in the area 1011 the server device 200 executes the process according to the request from the form recognition device 100, the form recognition device 100 receives the result, and the server device 200 executes the process of FIG. The characters recognized by analyzing the image obtained by the above may be displayed in the area 1011.

Each of the above configurations, functions, processing units, processing means, etc. may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

The form recognition method or form recognition device / system described above includes a form recognition program for causing a computer to execute each procedure, a computer-readable recording medium on which the form recognition program is recorded, and a form recognition program, and is an internal memory of the computer. It can be provided by a program product that can be loaded into the computer, a computer such as a server that includes the program, and the like.

100 Form recognition device 110 Operation unit 120 Display unit 130 Image input unit 140 Storage unit 150 Control unit 160 Interface (IF)
200 Server device 210 Operation unit 220 Display unit 230 Control unit 240 Storage unit 250 Interface (IF)

Claims (7)

A shaded area is extracted from the form image by extracting pixels in which the continuous length of black pixels is equal to or less than a predetermined value in units of rows and columns of the form image input from the image input unit. Shading area extraction unit and
In the shaded area of the form image, the shaded pixels are removed from the form image by removing the pixels in which the continuous length of the black pixels is equal to or less than a predetermined value in units of rows and columns. Shading remover and
A form recognition device characterized by being equipped with. The form recognition device according to claim 1.
The shaded area extraction unit evaluates the continuity of black pixels in the horizontal direction of the form image, extracts candidates for shaded pixels in the horizontal direction, and determines the continuity of black pixels in the vertical direction of the form image. After evaluation, candidates for shaded pixels in the vertical direction are extracted, and black pixels common to both the candidates for shaded pixels in the horizontal direction and the candidates for shaded pixels in the vertical direction are extracted as shaded pixels. The adjacently obtained area obtained by connecting the shaded pixel candidates is defined as the shaded area.
A form recognition device characterized by this. The form recognition device according to claim 1.
The shading removal unit is shaded by evaluating the continuity of black pixels in the horizontal direction and the vertical direction from the image of the input form corresponding to the shading area extracted by the shading area extraction unit. It is determined that the pixel is a pixel of, and the shaded pixel is removed.
A form recognition device characterized by this. The form recognition device according to claim 1.
The display area of the form image input from the image input unit, the display area of the image obtained as the processing result of the shading area extraction unit, and the display area of the image obtained as the processing result of the shading removal unit. A control unit that displays a screen including an area for inputting and displaying the parameters for extracting the shaded area and an area for inputting and displaying the parameters for removing the shaded area on the display unit.
A form recognition device characterized by being equipped with. The form recognition device according to claim 1.
For the form image input from the image input unit, a parameter setting unit for setting the parameters for shading area extraction performed by the shading area extraction unit and the parameters for shading removal performed by the shading removal unit, and
A form recognition unit that executes form recognition using the set parameters,
It has a score calculation unit that calculates a score for evaluating shading removal using the result of form recognition.
Parameter recording that changes the parameters and repeats the processes of the parameter setting unit, the form recognition unit, and the score calculation unit, and determines the parameter that maximizes the score as the parameter for extracting the shaded area and removing the shaded area. Department and
A form recognition device characterized by being equipped with. The shaded area extraction unit extracts the form image input from the image input unit in units of rows and columns, and the continuous length of black pixels is equal to or less than a predetermined value. Extract the shaded area from the inside and
In the shaded area of the form image, the shading removal unit removes pixels in which the continuous length of black pixels is equal to or less than a predetermined value in units of rows and columns, thereby forming the inside of the form image. Remove shaded pixels from,
A form recognition method characterized by this. A form recognition system in which a form recognition device and a server device are connected via a network.
The form recognition device is
Image input section for inputting form images and
A communication unit that transmits a form image input by the image input unit to the server device and receives an image in which shaded pixels are removed from the server device.
A control unit that outputs an image from which the shaded pixels received by the communication unit have been removed is provided.
The server device is
A server communication unit that receives the form image from the form recognition device and transmits the image from which the shaded pixels have been removed to the form recognition device.
By extracting pixels in which the continuous length of black pixels is equal to or less than a predetermined value in row units and column units from the form image received from the form recognition device, a shaded area is obtained from the form image. The shaded area extractor to be extracted and
In the shaded area of the form image, the shaded pixels are removed from the form image by removing the pixels in which the continuous length of the black pixels is equal to or less than a predetermined value in units of rows and columns. Shading remover and
A form recognition system characterized by being equipped with.

Images