JP2023136551A - Image processing device, image processing method and image processing program - Google Patents

Abstract

To provide an image processing device, an image processing method and an image processing program that correctly set a recognition region even when characters included in an image are handwritten.SOLUTION: An image processing function of an operation part 30 of MFP comprises: a character determination part 303 which determines whether characters entered into a recognition region where characters entered into an image are to be recognized are handwritten or printed; a first correction part 305 which varies the size of the recognition region when the character determination part 303 determines that the characters entered into the recognition region are handwritten; and a second correction part 308 which moves the position of the recognition region when the character determination part 303 determines that the characters entered into the recognition region are printed.SELECTED DRAWING: Figure 3

Description

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

There is a technology called character recognition processing (OCR) that extracts areas where characters are printed from images of forms, documents, etc. read with an MFP (Multifunction Peripheral/Printer/Product) or scanner and recognizes the types. In such technology, in order to accurately extract the area where characters are printed, there are cases in which characteristic areas such as table borders are extracted from the document and a recognition area is set for character recognition. The area may be set manually. However, in the case of a document in which only necessary information is added to a pre-printed frame line, characters may appear outside the pre-set recognition area due to printing misalignment or the like. Therefore, a technique is known that detects the misalignment of print on a read document and corrects the recognition area.

As an example of such technology, for example, Patent Document 1 describes a method for reading print data in an electronic image of a document including a frame line using a scanner, and detects print misalignment data mixed in an area where data is not printed. , calculation of the degree of overlap between the frame area and the circumscribed rectangle of the printing misalignment data, the relationship between the position of the frame line that separates the two frames, the position of the overlapping character, and the center position of the frame, and the circumscribing rectangle of the printing misalignment data. A technique has been disclosed that uses the size of the frame, the size of the frame, and the global direction of print deviation to determine which frame the print data is out of.

However, if the object of character recognition is printed text whose deviation is uniform, it is possible to associate the character with the recognition area by detecting the global deviation. In the case of the characters, there was a problem in that the recognition area could not be set correctly and erroneous recognition was likely to occur.

The present application has been made in view of the above, and an object thereof is to correctly set a recognition area even when characters included in an image are handwritten.

In order to solve the above-mentioned problems and achieve the objects, the present invention provides a character recognition method for determining whether characters written in a recognition area, which is an area where characters written in an image are recognized, are handwritten or printed. a determination unit; a first correction unit that changes the size of the recognition area when the determination unit determines that the character written in the recognition area is handwritten; and a first correction unit that changes the size of the recognition area written in the recognition area by the determination unit; and a second correction unit that moves the position of the recognition area when the detected character is determined to be a printed character.

According to the present invention, it is possible to correctly set a recognition area even when characters included in an image are handwritten.

FIG. 1 is a diagram showing an example of the configuration of an image processing system 1 according to an embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of the MFP 10 according to the embodiment. FIG. 3 is a block diagram showing a module configuration regarding the image processing function of the operation unit 30. FIG. 4 is a flowchart showing the flow of image processing by the MFP 10. FIG. 5 is a diagram showing an example of an image showing a document including handwritten characters. FIG. 6 is a diagram illustrating an example of determination by the protrusion determination unit 304. FIG. 7 is a diagram illustrating an example of correction of the recognition area by the first correction unit 305. FIG. 8 is a diagram illustrating an example of determination by the additional write determination unit 306. FIG. 9 is a diagram illustrating an example of extracting a rectangle of a character string printed out of the recognition area. FIG. 10 is a diagram illustrating an example of calculation of the amount of deviation by the calculation unit 307. FIG. 11 is a diagram illustrating an example of correction of the recognition area by the second correction unit 308.

Embodiments of an image processing device, an image processing method, and an image processing program will be described in detail below with reference to the accompanying drawings. In the embodiments shown below, an example will be explained in which the image processing apparatus of the present invention is a multifunction peripheral (MFP), but the present invention is not limited to this. Note that a multifunction device is a device that has at least two functions among a printing function, a copying function, a scanner function, and a facsimile function.

(Embodiment)
First, an overview of the entire image processing system 1 including an image processing apparatus (MFP) 10 according to an embodiment will be described using FIG. FIG. 1 is a diagram showing an example of the configuration of an image processing system 1 according to an embodiment. As shown in FIG. 1, the image processing system 1 includes an MFP 10, a PC (Personal Computer) 11, a server 12, and a storage device 13. The MFP 10, a PC (Personal Computer) 11, a server 12, and a storage device 13 are connected via a network 14. Examples of the network 14 include a LAN (Local Area Network) and the Internet. Note that the image processing system 1 shown in FIG. 1 may include multiple MFPs 10, multiple PCs (Personal Computers) 11, multiple servers 12, and multiple storage devices 13.

The MFP 10 reads a document and executes recognition processing for characters included in an image representing the document. Further, if information regarding a recognition area, which is an area where character recognition processing is performed, is not set for the document to be read, the MFP 10 extracts the recognition area.

The PC 11 is an information processing device used by a user. For example, the PC 11 is used by the user to confirm the recognition result of the recognition process performed by the MFP 10. Further, the PC 11 is used by the user to modify the recognition area.

Note that the character recognition process and the setting of the recognition area may be executed by the PC 11 or the server 12 after receiving from the MFP 10 an image showing the document read by the MFP 10. Furthermore, the recognition area may not be set automatically when the MFP 10 reads the document, but may be set by the user manually operating the MFP 10 while viewing the image.

Further, although information regarding recognition results and recognition areas is basically stored in the PC 11 or server 12, it is also possible to store it in an external storage device 13.

Next, the configuration of the MFP 10 according to the embodiment will be described using FIG. 2. FIG. 2 is a diagram showing an example of the hardware configuration of the MFP 10 according to the embodiment. As shown in FIG. 2, the MFP 10, which is a multifunction device, includes a main body 20 that can implement various functions such as a copy function, a scanner function, a fax function, and a printer function, and an operation unit 30 that accepts user operations. Note that accepting a user's operation is a concept that includes accepting information (including signals indicating screen coordinate values and the like) input in response to a user's operation. The main body 20 and the operation section 30 are connected to be able to communicate with each other via a dedicated communication path 100. The communication path 100 may be of the USB (Universal Serial Bus) standard, for example, but may be of any standard, whether wired or wireless.

Note that the main body 20 can perform operations according to operations received by the operation unit 30. The main body 20 can also communicate with an external device such as a client PC (for example, the PC 11), and can perform operations according to instructions received from the external device.

First, the hardware configuration of the main body 20 will be explained. As shown in FIG. 2, the main body 20 includes a CPU 21, a ROM 22, a RAM 23, an HDD (hard disk drive) 24, a communication I/F (interface) 25, a connection I/F 26, and an engine section 27. . The CPU 21, ROM 22, RAM 23, HDD 24, communication I/F 25, connection I/F 26, and engine section 27 are interconnected via a system bus 28.

The CPU 21 centrally controls the operation of the main body 20. The CPU 21 controls the overall operation of the main body 20 by executing programs stored in the ROM 22 or the HDD 24 using the RAM 23 as a work area, and performs the above-mentioned copy function, scanner function, fax function, printer function, etc. Achieve various functions.

Communication I/F 25 is an interface for connecting to network 14. The connection I/F 26 is an interface for communicating with the operation unit 30 via the communication path 100.

The engine unit 27 is hardware that performs processing other than general-purpose information processing and communication in order to realize a copy function, a scanner function, a fax function, and a printer function. The engine unit 27 includes, for example, a scanner (image reading unit) that scans and reads an image of a document, a plotter (image forming unit) that prints on a sheet material such as paper, a fax unit that performs fax communication, etc. . Furthermore, the engine section 27 can also include specific options such as a finisher that sorts printed sheet materials and an ADF (automatic document feeder) that automatically feeds documents.

Next, the hardware configuration of the operation unit 30 will be explained. As shown in FIG. 2, the operation unit 30 includes a CPU 31, a ROM 32, a RAM 33, a flash memory 34, a communication I/F 35, a connection I/F 36, and an operation panel 37. The CPU 31, ROM 32, RAM 33, flash memory 34, communication I/F 35, connection I/F 36, and operation panel 37 are interconnected via a system bus 38.

The CPU 31 centrally controls the operation of the operation unit 30. The CPU 31 controls the overall operation of the operation unit 30 by executing programs stored in the ROM 32 or flash memory 34 using the RAM 33 as a work area (work area), and displays information (images) according to input received from the user. ), which will be described later.

Communication I/F 35 is an interface for connecting to network 14. The connection I/F 36 is an interface for communicating with the main body 20 via the communication path 100.

The operation panel 37 receives various inputs according to user operations, and displays various information (for example, information according to the received operations, information indicating the operating status of the MFP 10, information indicating the setting status, etc.). . In this example, the operation panel 37 is comprised of a liquid crystal display (LCD) equipped with a touch panel function, but is not limited to this. For example, the operation panel 37 may be configured with an organic EL display device equipped with a touch panel function. Further, the operation panel 37 may be provided with an operation section such as a hardware key or a display section such as a lamp in addition to or in place of this.

The image processing program executed by the operation unit 30 of the MFP 10 according to the present embodiment is provided as being pre-installed in a ROM or the like.

The image processing program executed on the operation unit 30 of the MFP 10 of this embodiment is a file in an installable or executable format and can be stored on a CD-ROM, flexible disk (FD), CD-R, or DVD (Digital Versatile). It may be configured to be recorded and provided on a computer-readable recording medium such as a computer-readable disk.

Further, the image processing program executed by the operation unit 30 of the MFP 10 of this embodiment may be stored on a computer connected to a network such as the Internet, and may be provided by being downloaded via the network. . Further, the image processing program executed by the operation unit 30 of the MFP 10 of this embodiment may be configured to be provided or distributed via a network such as the Internet.

The image processing program executed by the operation unit 30 of the MFP 10 of this embodiment includes each unit (image reception unit 301, recognition area acquisition unit 302, character determination unit 303, protrusion determination unit 304, first correction unit 305, It has a module configuration including an additional writing determination section 306, a calculation section 307, a second correction section 308, and a recognition area output section 309), and the actual hardware is a CPU (processor) that reads an image processing program from the ROM. By executing, the above-mentioned units are loaded onto the main storage device, including the image receiving unit 301, recognition area acquisition unit 302, character determination unit 303, protrusion determination unit 304, first correction unit 305, additional writing determination unit 306, and calculation unit 307. , a second correction unit 308 and a recognition area output unit 309 are generated on the main storage device.

Next, the voice assistance function executed by the operation unit 30 of the MFP 10 will be described using FIG. 3. FIG. 3 is a block diagram showing a module configuration regarding the image processing function of the operation unit 30.

As shown in FIG. 3, the program executed by the operation unit 30 of the MFP 10 of this embodiment includes each unit (image reception unit 301, recognition area acquisition unit 302, character determination unit 303, protrusion determination unit 304, first correction section 305, additional write determination section 306, calculation section 307, second correction section 308, and recognition area output section 309), and as for actual hardware, the CPU 31 reads the program from the ROM 32 or flash memory 34, etc. By reading and executing, the above-mentioned units are loaded onto the RAM 33, including the image receiving unit 301, recognition area acquisition unit 302, character determination unit 303, protrusion determination unit 304, first correction unit 305, additional writing determination unit 306, and calculation unit 307. , a second correction section 308 and a recognition area output section 309 are generated on the RAM 33.

Image receiving section 301 receives an image of a document read by the scanner function implemented by engine section 27 via communication path 100 .

The recognition area acquisition unit 302 acquires, from the PC 11 via the network 14, information regarding the recognition area, which is an area where character recognition processing is performed, of the image received by the image reception unit 301. Further, the recognition area acquisition unit 302 acquires information regarding the recognition area set by the user manually operating the MFP 10 while viewing an image showing the document.

If information regarding the recognition area cannot be acquired or if the recognition area has not been set, the recognition area acquisition unit 302 may extract and set the recognition area from the image representing the document. For example, the recognition area acquisition unit 302 extracts ruled lines and frames from the image, and sets the extracted frames as recognition areas.

Here, the ruled line extraction may be realized by, for example, using a means for extracting continuity of pixels in the horizontal and vertical directions, or a means for applying a filter to detect horizontal and vertical lines. Further, frame extraction may be realized by using means for finding intersections of ruled lines and extracting frame positions one by one based on their positional relationship. Furthermore, the extracted recognition area may be configured so that the user can modify it, such as adding or deleting it, while checking it.

Note that the recognition area extraction process and setting process by the recognition area acquisition unit 302 are not limited to the above-described method, and may be realized using any conventional technique.

The character determination unit 303 determines whether characters written in a recognition area, which is an area where characters written in an image are recognized, are handwritten or printed. For example, the character determination unit 303 extracts blocks of pixels of the same color from an image and connects blocks of adjacent pixels to extract a plurality of rectangles in units of one character. Here, if the rectangular size of each character is approximately constant, the character determination unit 303 determines these characters to be printed characters. On the other hand, if the rectangular sizes of each character are non-uniform, the character determination unit 303 determines that these characters are handwritten.

Note that the character determination unit 303 also determines whether the characters written in the image are handwritten or printed, using variations in the center position of the extracted characters and the linearity of line segments used within the characters. You may. Further, the character determination processing by the character determination unit 303 is not limited to the above-mentioned method, and may be realized using any conventional technique.

When the character written in the recognition area is determined to be handwritten, the protrusion determination unit 304 determines whether the character is outside the recognition area.

The first correction unit 305 changes the size of the recognition area when the character determination unit 303 determines that the characters written in the recognition area are handwritten. Further, the first correction unit 305 changes the size of the recognition area when the protrusion determination unit 304 determines that the characters written in the recognition area protrude. Further, the first correction unit 305 determines that the character written in the recognition area protrudes when pixel data exists within a predetermined range from the boundary of the recognition area.

When a character written in the recognition area is determined to be a printed character, the additional writing determination unit 306 determines whether the character is a character that has been printed in advance on the image or a character that has been added to the image. . Further, the additional writing determination unit 306 performs the following based on at least one of the position of the character written in the recognition area, the color of the character, the font type of the character, and the font size of the character. It is determined whether the character is a character previously printed on the image or a character added to the image.

The calculation unit 307 calculates the amount of deviation of the character from the recognition area when the additional writing determination unit 306 determines that the character written in the recognition area is a character added to the image.

The second correction unit 308 moves the position of the recognition area when the character determination unit 303 determines that the characters written in the recognition area are printed characters. Further, the second correction unit 308 moves the position of the recognition area according to the amount of deviation calculated by the calculation unit 307.

The recognition area output unit 309 associates a new recognition area that integrates the correction result by the first correction unit 305 and the correction result by the second correction unit 308 with the image, and outputs it to a module that executes character recognition processing in the MFP 10. Output against.

Next, the flow of image processing by the MFP 10 will be described using FIG. 4. FIG. 4 is a flowchart showing the flow of image processing by the MFP 10. As shown in FIG. 4, the MFP 10 reads a document using the scanner function (step S401).

Next, the MFP 10 acquires the recognition area set in the image obtained by reading the document (step S402). Next, the MFP 10 determines whether the characters written in each recognition area are handwritten or printed (step S403).

If the characters written in the recognition area are handwritten (step S404; Yes), the MFP 10 changes the size of the recognition area (step S405).

If the characters written in the recognition area are not handwritten (in other words, printed) (step S404; No), the MFP 10 moves the position of the recognition area (step S406).

Subsequently, the MFP 10 integrates the corrected recognition areas (step S407).

According to this embodiment, it is possible to determine whether the type of character written in the recognition area is printed or handwritten, and then shift the recognition area if it is printed or expand the recognition area if it is handwritten. Therefore, the recognition area can be set correctly. That is, according to this embodiment, even if the characters included in the image are handwritten, the recognition area can be set correctly.

In the above embodiment, the image processing apparatus of the present invention is applied to a multifunction machine having at least two functions among a copy function, a printer function, a scanner function, and a facsimile function. The present invention can be applied to any image processing device such as a printer, a scanner device, a facsimile device, or the like.

(Regarding processing by the protrusion determination unit 304 and first correction unit 305)
Next, a specific example of the processing by the protrusion determination section 304 and the first correction section 305 will be described using FIGS. 5 to 7. FIG. 5 is a diagram showing an example of an image showing a document including handwritten characters. FIG. 6 is a diagram illustrating an example of determination by the protrusion determination unit 304. FIG. 7 is a diagram illustrating an example of correction of the recognition area by the first correction unit 305.

As shown in FIG. 5, in many cases, item names are pre-printed (pre-printed) in type on the manuscript, and the corresponding content is added by hand by the user. For example, as shown in Figure 5 (A), the product name is written and the number of items you want to order is written by hand, or as shown in Figure 5 (B), you write your name, address, phone number, etc. It is something.

When the recognition area acquisition unit 302 executes recognition area extraction processing based on the information of ruled lines and intersections, the user will not be able to add additional information to the area where the item name is pre-printed (that is, it is not a recognition area). Therefore, recognition areas 500 to 503 are extracted for the original in FIG. 5A, and recognition areas 504 to 506 are extracted for the original in FIG. 5B. When additional notes are written by hand on a pre-printed document, the notes are written in each frame, so the deviation is not uniform with respect to the recognition area, unlike when additional notes are written in type on a pre-printed document. On the other hand, since the user writes additional notes while looking at the frame, it is difficult for large deviations such as characters to be written to be located in the center of two recognition areas as in the case of printed characters to occur.

Therefore, the protrusion determination unit 304 scans the pixels around the boundary of the recognition area, and determines that there is protrusion of the character if a black pixel is present. For example, in the example of FIG. 6, the protrusion determination unit 304 determines that the black pixels in the recognition area 500 are present in the area 600 so as to straddle the boundary of the recognition area 500, so the written character protrudes. It is determined that

On the other hand, since each black pixel within the recognition area 501 exists only within the recognition area 501, the protrusion determination unit 304 determines that the character written within the recognition area 501 does not protrude.

Then, as shown in FIG. 7, the first correction unit 305 changes the size of the recognition area 500 in which it is determined that the written character protrudes, and sets it as a new recognition area 510. For example, the first correction unit 305 enlarges the recognition area 500 and sets it as a recognition area 510 in order to deal with protruding characters. Note that the enlargement ratio may be uniformly set in advance, or the size of a rectangle (that is, a character) extracted by connecting blocks of black pixels may be determined and enlarged accordingly.

As described above, the first correction unit 305 enlarges only the recognition area where the written character protrudes, so that for characters that are within the recognition area, the first correction unit 305 enlarges the recognition area where the written character protrudes. is included to prevent noise from being mixed into the recognition results, and by expanding the recognition area for characters that are protruding from the recognition area, it is expected that all characters will fit within the recognition area and recognition accuracy will increase.

Note that the first correction unit 305 may reduce the recognition area according to the size of the character in order to further improve the recognition rate even if the character fits within the recognition area. .

(Regarding processing by the additional writing determination unit 306, calculation unit 307, and second correction unit 308)
Next, a specific example of processing by the additional writing determination unit 306, the calculation unit 307, and the second correction unit 308 will be described using FIGS. 8 to 11. FIG. 8 is a diagram illustrating an example of determination by the additional write determination unit 306. FIG. 9 is a diagram illustrating an example of extracting a rectangle of a character string printed out of the recognition area. FIG. 10 is a diagram illustrating an example of calculation of the amount of deviation by the calculation unit 307. FIG. 11 is a diagram illustrating an example of correction of the recognition area by the second correction unit 308.

Normally, the item name is pre-printed in type on the original, and when the user adds the corresponding content in type, even if it is printed over the original, the position will be different because the characters are aligned on the PC data. There is no difference in size. However, if the installation position of the paper is misaligned during printing or an error occurs during conveyance, as shown in FIG. 8, printing may occur outside the pre-printed frame. In this way, the printed characters are uniformly shifted in the same direction without changing the size.

When the above-mentioned recognition area acquisition unit 302 executes the recognition area extraction process on the image shown in FIG. Both regions 703 to 705 and regions 700 to 702 of additionally written characters are extracted as recognition regions. In addition, since the pre-printed characters are printed together with the frame and there is no positional deviation with respect to the frame, if printing deviation is determined including this area, the amount of printing deviation may be calculated incorrectly. There is sex.

Therefore, the additional writing determination unit 306 determines whether the characters in each area are pre-printed characters or additionally written characters. A characteristic of the area where pre-printed characters are written is that the characters are located at the top or left end of the frame because the item name is written therein. Furthermore, since the pre-printed characters are printed together with the ruled lines, they are reproduced in the same color. Furthermore, when comparing pre-printed characters and additionally written characters, there are many cases in which they are printed in different positions within the area, or in which characters use different character colors, font types, and font sizes. Using this information, the additional writing determining unit 306 determines that areas 700 to 702 are recognition areas, and areas 703 to 705 are pre-printed areas (that is, not recognition areas).

As shown in FIG. 9(A), after the recognition areas 700 to 702 are determined, the calculation unit 307 cuts out the recognition areas 700 to 702 as shown in FIG. 9(B), and calculates the black pixels in each area. Extract. Subsequently, the calculation unit 307 extracts black pixels connected to the black pixels extracted in FIG. 9(B), as shown in FIG. 9(C). Next, as shown in FIG. 9D, the calculation unit 307 converts the block of black pixels extracted from the recognition area 700 into a character string rectangle 710, and converts the block of black pixels extracted from the recognition area 701 into a character string rectangle 711. , a block of black pixels extracted from the recognition area 702 is specified as a character string rectangle 712. Note that the recognition area 702 also includes "0" corresponding to the character string rectangle 710 and "10" corresponding to the character string rectangle 711, but the calculation is not performed for the character string rectangles already detected from other recognition areas. Section 307 shall be ignored.

Subsequently, the calculation unit 307 calculates vectors from each of the extracted character string rectangles 710 to 712 to each of the recognition areas 700 to 702, as shown in FIG. Here, the left end, center, or right end of each of the character string rectangles 710 to 712 is used as the starting point of the vector. Further, as the end point of the vector, either the left end, center, or right end of each of the recognition areas 700 to 702 is used.

In the case of the character string rectangle 710, three vectors shown in FIG. 10(A) are calculated. Further, in the case of the character string rectangle 711, three vectors shown in FIG. 10(B) are calculated. Furthermore, in the case of the character string rectangle 712, three vectors shown in FIG. 10(C) are calculated. Since vector 800 is included in each of FIGS. 10A to 10C, calculation unit 307 calculates the amount of deviation of character string rectangles 710 to 712 (in other words, the added characters) to vector 800. Calculate the vector in the opposite direction. In this way, the calculation unit 307 can calculate the amount of shift of the additionally written character by finding the mode of the vector from each character string rectangle to the recognition area.

Then, as shown in FIG. 11, the second correction unit 308 moves the recognition areas 700 to 702, respectively, to create new recognition areas 720 to 722 based on the amount of deviation calculated as described above.

By performing the above processing, it is expected that the characters will fit within the recognition area and be recognized correctly. Note that, as disclosed in Patent Document 1, if ruled lines are removed and characters are complemented, recognition accuracy can be further improved.

10 MFP
20 Main body 30 Operation unit 301 Image reception unit 302 Recognition area acquisition unit 303 Character determination unit 304 Extrusion determination unit 305 First correction unit 306 Addition determination unit 307 Calculation unit 308 Second correction unit 309 Recognition area output unit

Japanese Patent Application Publication No. 2006-146741

Claims (7)

a character determination unit that determines whether characters written in a recognition area, which is an area where characters written in the image are recognized, are handwritten or printed;
a first correction unit that changes the size of the recognition area when the character determination unit determines that the character written in the recognition area is handwritten;
An image processing device comprising: a second correction unit that moves the position of the recognition area when the character determination unit determines that the character written in the recognition area is a printed character. Further comprising: an overflow determination unit that determines whether or not the character protrudes from the recognition area when the character written in the recognition area is determined to be handwritten;
The first correction section includes:
The image processing apparatus according to claim 1, wherein the size of the recognition area is changed when the protrusion determination unit determines that the characters written in the recognition area protrude. The protrusion determination section is
The image processing apparatus according to claim 2, wherein when pixel data exists within a predetermined range from a boundary of the recognition area, it is determined that the character written in the recognition area protrudes. an additional writing determination unit that determines, when it is determined that the characters written in the recognition area are printed characters, whether the characters are characters that have been printed in advance on the image or characters that have been added to the image; and,
a calculation unit that calculates a deviation amount of the character from the recognition area when the addition determination unit determines that the character written in the recognition area is a character added to the image; Prepare,
The second correction section includes:
The image processing device according to any one of claims 1 to 3, wherein the position of the recognition area is moved according to the amount of deviation calculated by the calculation unit. The additional writing determination unit includes:
The character written in the recognition area is displayed in the image based on at least one of the position of the character in the recognition area, the color of the character, the font type of the character, and the font size of the character. The image processing apparatus according to claim 4, wherein the image processing apparatus determines whether the character is a character printed in advance or a character added to the image. An image processing method executed by an image processing device, the method comprising:
a character determination step of determining whether the characters written in the recognition area, which is an area where characters written in the image are recognized, are handwritten or printed;
a first correction step of changing the size of the recognition area when the character written in the recognition area is determined to be handwritten in the character determination step;
An image processing method comprising: a second correction step of moving the position of the recognition region when the character written in the recognition region is determined to be a printed character in the character determination step. a character determination procedure for determining whether characters written in a recognition area, which is an area where characters written in the image are recognized, are handwritten or printed;
a first correction procedure of changing the size of the recognition area when the character written in the recognition area is determined to be handwritten by the character determination procedure;
and a second correction procedure of moving the position of the recognition area when the character written in the recognition area is determined to be printed by the character determination process. Processing program.

Images