Image processing device and image processing method

Abstract

A character recognition processing unit (12): performs character recognition processing on an image portion of an entry field in a document image including a line that indicates an entry field and characters that have been hand written in the entry field; and identifies the characters. If a character and the line are in contact in the document image, a correction processing unit (13) determines whether the thickness of a specific portion of the line, said portion including the contact location of the character and the line, is constant; and, if it has been determined that the thickness of the specific portion of the line is not constant, the correction processing unit (13) determines that a portion of the character is overlapping the line, and corrects the identified character.

Description

Image processing apparatus and image processing method

[0007] ,

[0006] , ,

[0005] ,

[0001] The present invention relates to an image processing apparatus and an image processing method.

[0002] An information processing apparatus reads characters entered in an entry box. When the characters overlap the entry box, it derives the ratio of the number of pixels of the portion where the characters overlap the entry box to the number of pixels of the entry box as a contact ratio, and when the contact ratio exceeds a predetermined threshold, corrects the read characters to specific characters (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2018-37117

[0004] However, since there are individual differences in the shapes of the entered characters, in the above-described information processing apparatus, the variation in the contact ratio is large, and there is a possibility that the read characters may not be accurately corrected.

[0005] The present invention has been made in view of the above problems, and an object thereof is to accurately determine that handwritten characters overlap a straight line indicating a character entry field, and to obtain an image processing apparatus and an image processing method for accurately correcting the character recognition result of the handwritten characters.

[0006] The image processing apparatus according to the present invention includes a character recognition processing unit that performs character recognition processing on an image portion of the entry field in a document image including a straight line indicating the entry field and characters handwritten in the entry field, and identifies the characters, and a correction processing unit that corrects the identified characters. Then, when the character and the straight line are in contact with each other in the document image, the correction processing unit determines whether the thickness of a specific portion of the straight line including the contact portion between the character and the straight line is constant. When it is determined that the thickness of the specific portion of the straight line is not constant, it is determined that a part of the character overlaps the straight line, and the identified character is corrected.

[0007] The image processing method according to the present invention comprises a character recognition step of performing character recognition processing on the image portion of a document image that includes a line indicating an entry field and characters handwritten in the entry field, and identifying the characters, and a correction step of correcting the identified characters. In the correction step, (a) if the characters and the line are in contact in the document image, it is determined whether the thickness of the specific portion of the line, including the point of contact between the characters and the line, is constant; and (b) if it is determined that the thickness of the specific portion of the line is not constant, it is determined that a part of the characters overlaps with the line, and the identified characters are corrected.

[0008] The image processing program according to the present invention causes a computer to function as the character recognition processing unit and the correction processing unit described above.

[0009] According to the present invention, an image processing device and an image processing method are obtained that can accurately determine whether handwritten characters overlap with straight lines indicating character entry fields, and can accurately correct the character recognition results of the handwritten characters.

[0010] The above or other objects, features, and advantages of the present invention will become even more apparent from the following detailed description in conjunction with the accompanying drawings.

[0011] Figure 1 is a block diagram showing the configuration of an image processing apparatus according to an embodiment of the present invention. Figure 2 is a diagram showing a straight line indicating an entry field and an example of handwritten characters in the entry field. Figure 3 is a diagram showing another example of a straight line indicating an entry field and handwritten characters in the entry field. Figure 4 is a diagram showing an example of a specific portion of the straight line in the entry field shown in Figure 3. Figure 5 is a diagram illustrating the correction of the specified characters in the case of the specific portion shown in Figure 4. Figure 6 is a diagram showing an example of a specific portion of the straight line in the entry field shown in Figure 2. Figure 7 is a diagram illustrating the correction of the specified characters in the case of the specific portion shown in Figure 6. Figure 8 is a diagram showing another example of a specific portion of the straight line in the entry field shown in Figure 2. Figure 9 is a flowchart illustrating the operation of the image processing apparatus shown in Figure 1.

[0012] Embodiments of the present invention will be described below with reference to the figures.

[0013] Figure 1 is a block diagram showing the configuration of an image processing apparatus according to an embodiment of the present invention. The image processing apparatus shown in Figure 1 is an information processing apparatus such as a personal computer or a server, or an electronic device such as a digital camera or an image forming apparatus (scanner, multifunction printer, etc.), and comprises a processing unit 1, a storage device 2, a communication device 3, a display device 4, an input device 5, an internal device 6, and the like.

[0014] The arithmetic processing unit 1 includes a computer and operates as various processing units by executing image processing programs on that computer. Specifically, the computer includes a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and operates as a predetermined processing unit by loading programs stored in the ROM or storage device 2 into the RAM and executing them with the CPU. The arithmetic processing unit 1 may also include an ASIC (Application Specific Integrated Circuit) that functions as a specific processing unit.

[0015] The storage device 2 is a non-volatile storage device such as flash memory, and stores the image processing program 2a and data (such as form data 2b) necessary for the processing described later. The image processing program 2a is stored, for example, on a non-temporary, computer-readable recording medium and installed from that recording medium to the storage device 2.

[0016] Form data 2b is data that indicates the position and size of the input fields where the user will enter handwritten text within a specific document image.

[0017] Communication device 3 is a device that communicates data with external devices, such as a network interface or peripheral device interface. Display device 4 is a device that displays various information to the user, such as a display panel such as a liquid crystal display. Input device 5 is a device that detects user operations, such as a keyboard or touch panel.

[0018] The internal device 6 is a device that performs a predetermined function of the image processing device. For example, if the image processing device is an image forming apparatus, the internal device 6 may be an image reading device that optically reads an image from a document, or a printing device that prints an image onto printing paper.

[0019] In this configuration, the processing unit 1 operates based on the image processing program 2a as the aforementioned processing units: the target image acquisition unit 11, the character recognition processing unit 12, and the correction processing unit 13.

[0020] The target image acquisition unit 11 acquires document images as target images (raster image data) from the storage device 2, communication device 3, internal device 6, etc., and stores them in RAM or the like.

[0021] For example, this document image corresponds to form data 2b, and is a read image of a document in which the characters to be extracted are written in the input fields specified by form data 2b.

[0022] Figure 2 shows an example of a line indicating an entry field and handwritten characters in the entry field. Figure 3 shows another example of a line indicating an entry field and handwritten characters in the entry field. The character recognition processing unit 12 performs character recognition processing on the image of the entry field in a document image that includes a line indicating an entry field (a border in Figures 2 and 3) and handwritten characters in that entry field, as shown in Figures 2 and 3, and identifies the characters. The position and size of the entry field in the document image are determined based on the form data 2b. The line mentioned above is, for example, a rectangular border or underline, and is located at the boundary of the entry field. In the case of Figures 2 and 3, the character "1" is identified.

[0023] Figure 4 shows an example of a specific portion of the straight line in the entry field shown in Figure 3. Figure 5 is a diagram illustrating the correction of the identified character in the case of the specific portion shown in Figure 4.

[0024] The correction processing unit 13 corrects the characters identified by the character recognition processing unit 12. Specifically, the correction processing unit 13 (a) determines whether the thickness of a specific portion of the line, including the point of contact between the character and the line, is constant if the character and the line are in contact in the document image, and (b) if it determines that the thickness of a specific portion of the line is not constant, as shown in Figure 4 for example, it determines that a part of the character overlaps with the line, and corrects the identified character as shown in Figure 5 for example.

[0025] Furthermore, whether or not text and the aforementioned straight line are in contact in the document image is determined by whether or not another object (a text object) is continuous with the straight line of the input field identified based on the form data 2b.

[0026] Figure 6 shows an example of a specific portion of the straight line in the entry field shown in Figure 2. Figure 7 is a diagram illustrating the correction of the identified character in the case of the specific portion shown in Figure 6. Figure 8 shows another example of a specific portion of the straight line in the entry field shown in Figure 2.

[0027] Furthermore, the correction processing unit 13 (a) determines whether the thickness of a specific part of the straight line is constant, and whether the specific part has a different density than the other parts of the straight line; (b1) for example as shown in Figure 6, if it determines that the specific part has a different density than the other parts of the straight line, it determines that a part of the character overlaps with that straight line and corrects the specified character, for example as shown in Figure 7; (b2) for example as shown in Figure 8, if it determines that the specific part does not have a different density than the other parts of the straight line, it determines that a part of the character does not overlap with that straight line and does not correct the specified character.

[0028] Next, the operation of the image processing device shown in Figure 1 will be explained. Figure 9 is a flowchart illustrating the operation of the image processing device shown in Figure 1.

[0029] When the target image acquisition unit 11 acquires a document image, the character recognition processing unit 12 identifies the position and size of the input fields in the document image based on the form data 2b, performs character recognition processing on the image portion of the input field, and identifies the characters entered in the input field (step S1).

[0030] Next, the correction processing unit 13 determines whether the characters in the input field are in contact with the straight lines (border lines or underlines) of the input field (step S2). If it determines that the characters in the input field are in contact with the straight lines of the input field, it identifies the point of contact (step S3), and then determines whether the thickness of the specific part of the straight line including the point of contact is constant (step S4).

[0031] If the correction processing unit 13 determines that the thickness of a specific part is not uniform, it corrects the identified character (step S5). For example, the corrected character is predetermined for each character based on the position of the contact point with the character (top, bottom, etc.). At this time, the character recognition process may be performed again, including the part with the non-uniform thickness, to identify the corrected character.

[0032] On the other hand, if it is determined in step S4 that the thickness of the specific portion is constant, the correction processing unit 13 determines whether the specific portion of the straight line has a different density than the other portions (step S6).

[0033] If the correction processing unit 13 determines that a specific part of a line in the entry field has a different density than the other parts, it corrects the specified character (step S5).

[0034] On the other hand, if in step S2 it is determined that the character is not in contact with the straight line of the entry field, and in step S6 the specific part of the straight line of the entry field does not have a different density than the other parts (i.e., the density of the specific part is the same as the density of the other parts), the correction processing unit 13 does not correct the specified character.

[0035] As described above, according to the above embodiment, the character recognition processing unit 12 performs character recognition processing on the image portion of the entry field in a document image that includes a line indicating an entry field and characters handwritten in that entry field, and identifies the characters. The correction processing unit 13 (a) determines whether the thickness of a specific portion of the line, including the point of contact between the characters and the line, is constant if the characters and the line are in contact in the document image, and (b) determines that the thickness of a specific portion of the line is not constant, determines that a part of the characters overlaps with the line, and corrects the identified characters.

[0036] This allows the system to accurately determine if handwritten characters overlap with the lines indicating the character entry fields, and to accurately correct the character recognition results for the handwritten characters.

[0037] Furthermore, various changes and modifications to the embodiments described above will be obvious to those skilled in the art. Such changes and modifications may be made without deviating from the spirit and scope of the subject matter and without diminishing the intended advantages. In other words, such changes and modifications are intended to be included in the claims.

[0038] For example, in the above embodiment, the characters to be corrected may be registered in advance, and the characters to be corrected may be corrected when they meet the predetermined conditions as described above, while other characters may not be corrected. Furthermore, the characters to be corrected may be characters that are recognized as different characters when one stroke is removed.

[0039] The present invention is applicable, for example, to an image processing apparatus.

Claims

1. An image processing device comprising: a character recognition processing unit that performs character recognition processing on the image portion of a document image including a line indicating an entry field and characters handwritten in the entry field, and identifies the characters; and a correction processing unit that corrects the identified characters, wherein the correction processing unit (a) determines whether the thickness of a specific portion of the line including the point of contact between the character and the line is constant if the characters and the line are in contact in the document image; and (b) if it determines that the thickness of a specific portion of the line is not constant, it determines that a part of the character overlaps with the line and corrects the identified character.

2. The image processing apparatus according to claim 1, characterized in that the correction processing unit (a) determines whether the thickness of a specific portion of the straight line is constant, determines whether the specific portion has a different density than the straight line other than the specific portion; (b1) determines that the specific portion has a different density than the straight line other than the specific portion, determines that a part of the character overlaps the straight line, and corrects the character; and (b2) determines that the specific portion does not have a different density than the straight line other than the specific portion, determines that a part of the character does not overlap the straight line, and does not correct the character.

3. The image processing apparatus according to claim 1, characterized in that the straight line is a border line or underline at the boundary of the entry field.

4. An image processing method comprising: a character recognition step of performing character recognition processing on the image portion of a document image that includes a line indicating an entry field and handwritten characters in the entry field, and identifying the characters; and a correction step of correcting the identified characters, wherein in the correction step, (a) if the characters and the line are in contact in the document image, it is determined whether the thickness of the specific portion of the line, including the point of contact between the characters and the line, is constant; and (b) if it is determined that the thickness of the specific portion of the line is not constant, it is determined that a part of the characters overlaps with the line, and the identified characters are corrected.

Images