JP2001312691A - Image processing method and apparatus, and storage medium - Google Patents

Abstract

(57) [Problem] To provide an image processing apparatus and an image processing method capable of automatically extracting a specific area on a form even if a template does not exist. A document image is read, and an area surrounded by ruled lines on the document is extracted as a cell area (S201, S20).
2) A tag character area is extracted from the extracted cell area (S204), and tag characters in the area are recognized (S204). Then, a keyword search is performed using the recognized tag character, and a cell region having the corresponding tag character string is extracted (S206). Then, the image information of the extracted cell area is stored (S207).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and an image processing method capable of extracting a specific area in a form without using a template, and a storage medium storing a computer-readable program. Things.

[0002]

2. Description of the Related Art Conventionally, for example, when extracting information existing in a specific area on a form, a template having information such as the position and size of the area is prepared in advance and read by a photoelectric conversion device such as an image scanner. Methods and apparatuses for applying a template to an image and extracting the image within the region are known.

For example, when an imprint on a form is taken out for comparison with a registered imprint, first, template information corresponding to the form is taken out, and the position / size information of the imprint area stored in the template is used. By specifying the imprint area of the form image, an imprint image can be obtained.

In this case, in order to select a template corresponding to a form, a form ID recorded at a predetermined position on the form is first read, and the template is specified using the result. I have. The form ID is an individually determined number that specifies the type of form, and characters, marks, bar codes, and the like are used as the form ID.

When the input form image is sent to a remote place by communication and the input operation is performed while displaying the image on the destination device, only the necessary area is taken out instead of the entire form image in order to reduce the communication amount. Some are configured to transmit image data. However, in this case as well, the area to be transmitted is specified using a template, as in the above-described known technique.

[0006]

However, according to the above-mentioned conventional technology, only a form in which a template already exists can be read, and when a new form is input, an area must be manually designated or There was a problem that a new template had to be created.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problem, and has as its object to enable a specific area on a form to be automatically extracted even if no template exists.

[0008]

An image processing apparatus according to an embodiment of the present invention for achieving the above object has, for example, the following arrangement. That is, a cell region extracting means for extracting a region surrounded by a predetermined diagram on the document as a cell region,
A character image extracting means for extracting a character image in the cell area; a character recognizing means for recognizing a character in the extracted character image; and a character string corresponding to a designated keyword from a character recognition result by the character recognizing means. A search unit; and a determination unit that determines a designated cell based on a cell area including the character string searched by the search unit.

Further, an image processing method according to an aspect of the present invention for achieving the above object has, for example, the following configuration. That is, a cell region extracting step of extracting a region surrounded by a predetermined diagram on the document as a cell region, a character image extracting step of extracting a character image in the cell region, A character recognition step of recognizing, a search step of searching for a character string corresponding to a specified keyword from the character recognition result of the character recognition step, and a cell designated based on a cell area including the character string searched by the search step And a determining step of determining

[0010]

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings.

[First Embodiment] FIG. 1 is a block diagram showing a configuration of an image processing apparatus according to a first embodiment of the present invention. A CPU 101 controls the entire apparatus according to a control program stored in a ROM 102. A RAM 103 functions as a main memory of the CPU 101. Reference numeral 104 denotes an external storage device such as a magnetic disk, which stores files such as text files and image files. 105 is a display, 106
Is a keyboard, and 107 is a pointing device such as a mouse. Reference numeral 108 denotes a photoelectric conversion device such as an image scanner, which reads a form by using the
103 or the external storage device 104. 109
Is a network interface, which can read and write files from and to another external storage device via a network (not shown). When the present invention is implemented by a general-purpose computer or the like, the processing according to the present invention is converted into a program code, the program is supplied by a computer-readable recording medium, and is executed by the CPU 101 of the general-purpose computer or the like. It is composed of

FIG. 4 is a diagram showing an example of a form 401 to be processed by the apparatus embodying the present invention. Reports are usually
The field is divided by ruled lines, and tag characters indicating contents to be described therein, such as an address and a name, are written therein. In FIG. 4, reference numeral 402 denotes an address field, 403 denotes a telephone number field, 404 denotes a name field, 405 denotes a name field, and 406 denotes a seal field. , "Name" and "seal". Then, for example, the entry person fills in the necessary items in the respective fields, and seals the seal field 406.

The outline of the processing according to the present embodiment will be described with reference to the flowchart of FIG.

In step S201, the photoelectric conversion device 10
8, or reads a target form image from a file stored in the external storage device 104.

In step S202, cells are extracted from the read image. The cell here is a rectangular area surrounded by ruled lines. In step S203, a tag character area (or tag character image) included in the extracted cell is extracted. The cell is extracted by extracting a ruled line from the continuity of pixels, and based on the shape and the connection state of the ruled line. The character area (or character image) is extracted from the state of connection with neighboring pixels. Note that specific cell extraction or character area (or character image) extraction can be realized by using, for example, a method described in Japanese Patent Application Laid-Open No. H10-83431. The tag character is smaller than the entry character, and it is possible to distinguish the tag character from the entry character by using size and position information such as being at the upper left in the cell area.

If the tag characters can be extracted, step S2
In step 04, tag character recognition is performed. After the recognition is completed, in step S205, a tag character specified by the keyword is searched for from the tag characters that have been character-recognized using the keyword determined in advance. The keyword is used to specify an area to be extracted. For example, when it is desired to extract an imprint portion, “seal” or the like is used as the keyword. Where "seal" and "seal" or "address" and "place"
For example, different expressions of the same object are regarded as the same, and a search is performed using the plurality of character strings. For example, when the keyword “seal” is designated, the tag character of the cell 406 is searched for a substantially synonymous character such as “seal” or “seal”.

In step S206, a cell containing the searched keyword is specified, and the cell is extracted. Further, in step S207, the image in the extracted area is stored in the external storage device 104. If the extracted image is a character image, character recognition may be performed in step S207 to form a character code string, and then the character code string may be stored in the external storage device 104.

As described above, according to the present embodiment, a cell including a specific tag character can be specified from a form enclosed by ruled lines, and a plurality of expressions have the same meaning. This has the effect of correctly reading the information held.

It should be noted that the present embodiment and the second
The apparatus according to the embodiment may use an image file or a program in a remote storage device or the like using a communication unit via the network interface 109. The character recognition processing or means may include processing or means for improving recognition accuracy.

As described above, according to the first embodiment, a desired cell can be extracted by recognizing a character (tag) for specifying a field and searching the recognition result. For this reason, even if a template is not prepared in advance, there is an effect that a specific area on a form can be automatically extracted.

Further, according to the present embodiment, there is no need to specify a template, and there is an effect that restrictions on the format of a form can be eliminated.

Further, according to the present embodiment, since only a required part of the image is handled without handling the entire form, when saving the image, the saving area is small,
When transmitting, there is an effect that the amount of transmission is small.

[Second Embodiment] A second embodiment of the present invention will be described. Since the configuration of the image processing apparatus according to the present embodiment is the same as the configuration of the apparatus according to the first embodiment shown in FIG. 1, the description of the configuration of the image processing apparatus is omitted.

FIG. 5 is a diagram showing an example of a form 501 to be processed by the apparatus according to the present embodiment. In the form of FIG. 5, 502 is an address tag, 503 is an address field,
04 is a telephone number tag, 505 is a telephone number field, 5
Tag characters are cells, such as 06, a name tag, 507, a name field, 508, a seal tag, and 509, a seal field.

The outline of the processing according to the second embodiment of the present invention will be described with reference to the flowchart of FIG.

As in the processing shown in FIG. 2 used in describing the first embodiment, a form image is read in step S301, and cells are extracted from the read image in step S302. In step S303, a tag character area (or tag character image) included in the cell is extracted,
In step S304, character recognition of tag characters is performed. In step S305, a keyword is searched from the character of the recognition result, and a cell including the keyword is specified.

In step S306, it is determined whether the specified cell is only a tag character. If the area of the tag character is sufficiently larger than the size of the cell and there is no room to enter other information, it is determined that the cell contains only the tag character. In step S303, the tag character area (or
If an image area (or a character image) other than a tag exists in the same cell when extracting the tag character image), it is determined in step S306 that the cell is not only a tag character.

If it is determined in step S306 that only a tag character exists in the cell, the process proceeds to step S307, and in step S307, a nearby cell is specified as a cell to be extracted. In the case of horizontal writing, the desired cell generally exists to the right of or below the cell containing the tag. If there is a cell that has the same height and touches the right, there is a right cell.If there is a cell that has the same width and touches the bottom, the lower cell.
Let it be a specific cell.

If it is determined in step S306 that the cell is not only a tag character, the flow advances from step S306 to step S308. In step S307, step S20 shown in FIG. 2 according to the first embodiment is executed.
Similarly to 6, the cell including the tag character is set as the specific cell.

In step S309, the image in the extracted area is transmitted via the network interface 109.

As described above, according to the second embodiment, in addition to the effect of the first embodiment, even if there is no character serving as a tag in a cell, a corresponding cell in the vicinity is specified and necessary. There is an effect that an area in which a tag exists can be extracted.

In the above embodiment, a form is taken as an example of a document to be processed. However, the present invention is not limited to this, and it goes without saying that the present invention can be applied to various document formats.

Although the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device including one device (for example, a copying machine, a facsimile machine) Etc.).

Further, an object of the present invention is to supply a storage medium (or a recording medium) storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or a computer) of the system or apparatus. It is needless to say that the present invention can also be achieved by a CPU or an MPU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention. Also,
When the computer executes the readout program code, not only the functions of the above-described embodiments are realized, but also the operating system (OS) running on the computer based on the instructions of the program code.
It goes without saying that a case where the functions of the above-described embodiments are implemented by performing some or all of the actual processing, and the processing performs the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written into a memory provided in a function expansion card inserted into the computer or a function expansion unit connected to the computer, the program code is read based on the instruction of the program code. Needless to say, the CPU included in the function expansion card or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

When the present invention is applied to the storage medium, the storage medium stores program codes corresponding to the above-described flowcharts (shown in FIG. 2 and / or FIG. 3).

[0037]

As described above, according to the present invention,
Even if a template does not exist, a specific area on a form can be automatically extracted.

[Brief description of the drawings]

FIG. 1 is a block diagram of an image processing apparatus according to an embodiment of the present invention.

FIG. 2 is performed by the image processing apparatus according to the first embodiment;
It is a flowchart which shows an example of a processing step.

FIG. 3 is performed by an image processing apparatus according to a second embodiment;
It is a flowchart which shows an example of a processing step.

FIG. 4 is a diagram illustrating a form image to be processed by the image processing apparatus according to the first embodiment.

FIG. 5 is a diagram illustrating a form image to be processed by an image processing apparatus according to a second embodiment.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) // G06F 17/30 170 G06F 17/30 170B

Claims (19)

[Claims] 1. A cell area extracting means for extracting an area surrounded by a predetermined diagram on a document as a cell area; a character image extracting means for extracting a character image in the cell area; Character recognition means for character recognition of an image; search means for searching a character string corresponding to a specified keyword from character recognition results by the character recognition means; and designation based on a cell area including the character string searched by the search means Determining means for determining a selected cell. 2. The image processing apparatus according to claim 1, wherein the search unit treats different character strings representing the same object as the same character string. 3. The image processing apparatus according to claim 1, wherein the character image extracting unit extracts a character existing in a predetermined area in the extracted cell area. 4. The image processing apparatus according to claim 1, wherein the character image extracting unit extracts a character smaller than a predetermined size in the extracted cell area. 5. The image processing apparatus according to claim 1, wherein the determining unit determines a cell area including the searched character string as the specified cell. 6. A determination unit for determining whether a ratio of a character string area searched by the search unit in a cell area including the character string exceeds a predetermined value, wherein the determination unit includes: 2. The image processing apparatus according to claim 1, wherein when the determination unit determines that the ratio exceeds a predetermined value, another cell area adjacent to the cell area is determined as a designated cell. apparatus. 7. The method according to claim 6, wherein the determining unit determines the cell area as a designated cell when the determining unit determines that the ratio does not exceed a predetermined value. Image processing device. 8. The image processing apparatus according to claim 1, further comprising a storage unit configured to store image information of a cell determined in the cell designated by the determination unit. 9. The image processing apparatus according to claim 1, further comprising a transmission unit configured to transmit image information of a cell determined to the cell specified by the determination unit to an external device. 10. A cell region extracting step of extracting a region surrounded by a predetermined diagram on a document as a cell region, a character image extracting step of extracting a character image in the cell region, and the extracted character A character recognition step of recognizing characters in an image, a search step of searching for a character string corresponding to a specified keyword from a character recognition result of the character recognition step, and a designation based on a cell region including the character string searched in the search step And a determining step of determining the selected cell. 11. The image processing method according to claim 10, wherein in the search step, different character strings representing the same object are treated as the same character string. 12. The image processing method according to claim 10, wherein the character image extracting step extracts characters existing in a predetermined area in the extracted cell area. 13. The image processing method according to claim 10, wherein the character image extracting step extracts a character smaller than a predetermined size in the extracted cell region. 14. The image processing method according to claim 10, wherein the determining step determines a cell area including the searched character string as the specified cell. 15. The method according to claim 15, further comprising: determining whether a ratio of an area of the character string searched in the search step to a cell area including the character string exceeds a predetermined value. 11. The image processing apparatus according to claim 10, wherein when the determination step determines that the ratio exceeds a predetermined value, another cell area adjacent to the cell area is determined as a designated cell. Method. 16. The method according to claim 15, wherein the determining step determines the cell area as a designated cell when the determining step determines that the ratio does not exceed a predetermined value. Image processing method. 17. The image processing method according to claim 10, further comprising a storage step of storing image information of the cell determined in the cell specified in the determination step. 18. The image processing method according to claim 10, further comprising a transmission step of transmitting image information of the cell determined to the cell designated in the determination step to an external device. 19. A storage medium for storing a control program for causing a computer to execute the image processing method according to claim 10.