JP2000339407A - Picture processor, picture processing method and computer readable storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a picture processor for recognizing the dislocation of a template and a slip picture without using a special mark for dislocation detection and to provide a picture processing method and a computer readable storage medium. SOLUTION: Plural areas are extracted from an inputted slip picture and the area (corresponding area) corresponding to one noticed area selected from areas which are previously stored in a template is retrieved from the extracted areas (S201-S203). When the corresponding area can be detected, shift quantity with the noticed area is calculated by using a coordinate value and the template is allocated to the slip picture in response to the calculated shift quantity. Thus, the dislocation of the slip picture against the template is corrected (S204-S205).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to an image processing apparatus, an image processing method, and a computer-readable storage medium.

[0002]

2. Description of the Related Art Conventionally, a form has been read by a scanner or the like, and the read image information (form image) has been subjected to character recognition processing to recognize characters and numerals described in the form. An image processing apparatus for reading a bar code or a mark has been proposed.

In general, in such an image processing apparatus, information on an area for character recognition included in a form to be read is used as template information (hereinafter, template).
Is stored in advance. In the character recognition processing of the read form, the template is superimposed on the image information (input image) of the read form, and the image information of the form included in the area stored as the character recognition area in the template Character recognition is performed on the image information in.

[0004] At this time, if the position of the template and the position of the input image are not superimposed in a predetermined positional relationship but are shifted, image information corresponding to a predetermined character recognition area cannot be processed. For this reason, a mark for alignment is printed in advance on a form, and the position of the mark is also stored in a template stored in advance in the image processing apparatus.
When the input image of the form is superimposed on the template, by searching for the registration mark of the form image near the position of the alignment mark stored in the template, It is configured such that a certain mark is sufficiently overlapped, thereby absorbing a shift between the template and the input image.

[0005]

However, in the above-described conventional method, the position of a mark in which no alignment mark exists on the form, or the case where the mark is not included in the input image due to any cause, is used. There is a drawback that the form cannot be removed, and the form in which the position is displaced outputs an incorrect processing result or cannot be processed.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and the present invention provides a method of combining a template with an input image (input image) without using a special mark for detecting a displacement. It is an object of the present invention to provide an image processing apparatus, an image processing method, and a computer-readable storage medium for recognizing displacement.

[0007]

To achieve the above object, an image processing apparatus according to the present invention has the following configuration.

That is, from an input image of a predetermined format,
A plurality of regions included in the input image are extracted, and region extraction means for detecting position information of each of the extracted regions, and, as template information, size and position information of a predetermined region to be included in the image are stored in advance. Storage means, and an area corresponding to size information selected at least one of the size information of the predetermined area stored as template information in the storage means in each area extracted by the area extraction means. And a search unit that searches from the search unit, and when a corresponding region is detected by the search unit, a shift amount between the detected region and a region selected from the template information is determined based on the position information of those regions. A shift amount recognizing means for detecting a relative shift amount between the input image and the template information by detecting the shift amount. To.

Further, for example, in the storage means, information for specifying an area to be searched when searching by the search means is registered in advance in the template information, and the search means It is preferable that only the area registered in the storage means is to be searched.

Further, for example, the search means searches for an area corresponding to one area selected from the template information from each area extracted by the area extraction means, and the displacement amount recognition means It is preferable that a relative shift amount between the input image and the template information is recognized based on the position information of the set of areas detected by the search unit.

Alternatively, in order to achieve the above object, an image processing method according to the present invention has the following configuration.

That is, from an input image in a predetermined format,
An area extracting step of extracting a plurality of areas included in the input image and detecting position information of each of the extracted areas; and previously storing size and position information of a predetermined area to be included in the input image as template information. A search step of selecting at least one of the size information of the predetermined area from the storage device, and searching for an area corresponding to the selected size information from the areas extracted in the area extraction step. And, when a corresponding area is detected in the search step, by detecting a shift amount between the detected area and an area selected from the template information based on the position information of those areas. And a shift amount recognizing step of recognizing a relative shift amount between the input image and the template information.

[0013] For example, of the template information, information for specifying an area to be searched when performing a search in the search step is registered in the storage device in advance, and in the search step, Preferably, only the area registered in the storage device is to be searched.

In the searching step, for example, an area corresponding to one area selected from the template information is searched from each area extracted in the area extracting step. In the method, it is preferable to recognize a relative shift amount between the input image and the template information based on position information of a set of areas detected in the search step.

Further, the invention is characterized by a computer-readable storage medium storing a program code for realizing the image processing apparatus and the image processing method by a computer.

[0016]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an image processing apparatus according to the present invention will be described in detail with reference to the drawings as an embodiment applied to a case where a form image is handled as an example of an input image.
The processing target of the image processing apparatus according to the present invention is not limited to a form image, but may be applied to any input image including a plurality of areas separated by ruled lines or the like.

[First Embodiment] FIG. 1 is a block diagram showing a configuration of an image processing apparatus to which the present invention can be applied.

In FIG. 1, reference numeral 101 denotes a CPU;
The control of the entire apparatus is performed according to a control program stored in the OM 102 in advance. 103 is a RAM, and C
It functions as a main memory of the PU 101 or a storage area for a form image or the like. Reference numeral 104 denotes an external storage device such as a magnetic disk, and reference numeral 108 denotes an image scanner for optically reading a form. 105 is a display, 10
Reference numeral 6 denotes a keyboard, and 107, a pointing device such as a mouse. Reference numeral 109 denotes a network interface which can transmit and receive a form image, template data described later, and the like to and from an external device.

Next, the operation executed by the image processing apparatus shown in FIG. 1 will be described.

FIG. 2 is a flowchart showing the form processing of the image processing apparatus according to the first embodiment.

In FIG. 1, step S201: an image (form image) of the form is obtained by reading a form in a predetermined format by the image scanner 108 having a general configuration. The form image may be obtained from an external device via the network interface 109.

Step S202: An area is extracted from the input form image. As a method for extracting a region, for example, a method disclosed in JP-A-8-235349 may be used.

As a result of the region extraction processing, for example, in the case of a form having the format shown in FIG. 4, a region 403 is extracted from a region 401 having a rectangular block shape. here,
An area 403 is a table area, and further includes an area 404 in cell units.
Are extracted from the region 412.

On the other hand, FIG. 5 shows a template to be compared with the form (form image) shown in FIG. 4. This template includes the position (2) of each area conceptually included in the template shown in FIG. In addition to (dimensional coordinate values), information for controlling the size of each area and reading processing (character recognition processing) is stored in advance. Here, the control information of the reading process includes a reading method such as character recognition or a bar code. In particular, when the stored reading method is the character recognition process, the control information of the handwriting character or the printed numeral is used. Character types and the like are further included. In addition, the area 50 which is the table area
In the case of 3, the reading process is not performed, but information such as the number of lines and columns of characters and numbers that should exist (should be described) is stored.

A template including these pieces of information is created in advance and stored in the external storage device 104 or the like.

Step S203: From among the regions extracted in step S202 (hereinafter referred to as "extracted regions"), an extracted region corresponding to a region previously stored in the template is determined.
Here, a method of determining a corresponding area (hereinafter, corresponding area) will be described.

FIG. 3 is a flowchart showing the processing for determining the corresponding area in the first embodiment, and shows the details of step S203 in FIG.

Referring to FIG. 3, in step S301, one of a plurality of regions included in a template is selected as a region of interest (hereinafter, region of interest), and the upper left coordinates of the selected region of interest are obtained.

Step S302: It is determined whether or not the corresponding area has been searched for all the area information extracted from the form image. If NO, the process proceeds to Step S303, and YES
If, the process ends.

Step S303: By acquiring the upper left coordinates of any one of the area information extracted from the form image, and comparing the coordinates with the upper left coordinates of the attention area acquired in step S301. Then, it is determined whether or not the area is near the attention area.

Here, the determination as to whether or not there is a neighborhood is made by applying a predetermined allowable range of coordinate values to the upper left coordinates of the attention area, and the upper left coordinates of the area to be currently determined within the range are determined. This is done by checking for the existence. This allowable range can be set to a smaller value if the form transport accuracy of the image scanner 108 is high.
If not, set it larger.

Step S305: If the determination in step S303 is YES, that is, if it is determined that the area currently being determined from the form image is present near the target area of the template, the area is In step S301, the region is set as a region corresponding to the region of interest selected from the templates, and the subsequent processing ends.

Step S304: If the determination in step S303 is NO, that is, if it is determined that the area currently being determined from the form image does not exist near the target area of the template, the form image Is selected as a new area to be determined, and the process returns to step S302.

Next, the description returns to step S204 and subsequent steps in FIG.

Step S204: Since the corresponding area corresponding to the attention area of the template has been obtained by the processing up to the previous step, the amount of deviation between the template and the input image is determined in step S204. The calculation of the amount of shift is performed by calculating the difference between the upper left coordinates of the attention area and the upper left coordinates of the corresponding area.

Step S205: By shifting the template by the shift amount calculated in step S204,
This is applied to the input form image (or the form image may be shifted by a shift amount with respect to the template).

Step S206: The form image corrected by the calculated shift amount in step S205 is subjected to a character recognition process or a recognition process such as a table analysis.
A general method is used for the recognition processing itself, and detailed description in the present embodiment will be omitted.

As described above, according to the present embodiment, the addition of special information for correcting a shift such as the addition of a mark to the template and the form as in the above-described conventional example and the printing of the mark are performed. Even without performing this, it is possible to determine the amount of deviation between the template and the form image. As a result, a predetermined area included in the form image in which character recognition and the like should be performed, including the area used for calculating the shift amount, can be accurately obtained, and the shift amount is corrected in a process after calculating the shift amount. Predetermined processing such as character recognition performed on an image can be accurately performed.

According to the present embodiment, even if all the regions corresponding to the region information stored in the template cannot be extracted from the form image, any one region of interest and the region of interest If a corresponding area can be detected, the amount of deviation between the template and the form image can be determined.

The reading (input) of the image is not limited to the image scanner 108, but may be an image stored in an external storage or the like in advance. Further, an image scanner, a storage device, or the like at a remote place may be used by using communication means via the network interface 109. Further, the processing for removing the inclination and the processing for eliminating the noise may be performed at the time of reading the image.

Further, the method of the region extraction processing and the configuration of the template are not limited to the above description as long as similar effects can be obtained.

The information used in the determination processing in step S303 is not limited to the upper left coordinates of each area, but may be information on the four corners and size of the area, the coordinates of the center, and the like.

In the present embodiment, step S204
When calculating the shift amount by using the coordinates of the upper left of the attention area,
Although the difference from the upper left coordinates of the corresponding region is used, for example, a difference between the center coordinates of the region and an average of the differences between the coordinates of the four corners of the region may be used. In addition, a configuration may be used in which a plurality of attention areas are used, and the average of the amounts of shift is used as the amount of shift between the input image and the template.

[Second Embodiment] Next, a second embodiment based on the above-described first embodiment will be described. In the following description, portions different from those of the first embodiment will be mainly described, and redundant description of the configuration of the image processing apparatus shown in FIG. 1 will be omitted.

In this embodiment, first, an area in which a corresponding area is to be searched is stored in a template in advance. That is, FIG.
In the case of the example shown in FIG. 5, an area 50 that will be stably extracted from most of the form images that will be input.
1, 503, 504, 505, and 506, or a part of each of these areas, is registered in the template in advance as an area to be searched for a corresponding area. Is determined.

FIG. 6 is a flowchart showing the processing for determining the corresponding area in the second embodiment, and shows the details of step S203 in FIG.

In the figure, step S601: It is determined whether or not the corresponding area has been searched for all the area information extracted from the form image. If NO, step S602
And the process ends when the result is YES.

Step S602: It is checked whether or not the attention area in the template that is currently focused on is an area in which a corresponding area is to be searched, based on registration information stored in advance.
When the determination is YES (when the corresponding region is a region to be searched), the process proceeds to step S603. When the determination is NO (when the corresponding region is not a region to be searched), the process proceeds to step S608.

Step S603: The coordinates of the upper left corner of the attention area of interest are acquired from among a plurality of areas included in the template.

Step S604: It is determined whether or not the corresponding area has been searched for all the area information extracted from the form image. If NO, the process proceeds to Step S605, and YES
If so, the process proceeds to step S608.

Step S605: The upper left coordinates of any one of the area information extracted from the form image are obtained, and the coordinates are compared with the upper left coordinates of the attention area obtained in step S603. It is determined whether or not the region is near the region of interest, as in the first embodiment.

Step S606: If the determination in step S605 is YES, that is, if it is determined that the area currently being determined from the form image is near the target area of the template, the area is determined as follows: It is set as a corresponding area to the current attention area, and step S60
Proceed to 8.

Step S607: If the determination in step S605 is NO, that is, if it is determined that the area currently being determined from the form image does not exist near the attention area of the template, the form image , A new area to be determined is selected, and the process returns to step S604.

Step S608: Another area included in the template is selected as a candidate for a new area of interest, and the process returns to step S601.

According to the above-described embodiment, the corresponding areas are individually detected for the areas to be searched for the corresponding areas registered in advance in the information of the template. For this reason, by applying the corresponding area determination processing in the second embodiment to step S203 of the form processing shown in FIG. 2, a shift such as adding a mark between the template and the form as in the above-described conventional example is performed. The amount of deviation between the template and the form image can be obtained more reliably than in the first embodiment without adding special information for correcting the error and printing the mark.

[0056]

[Other Embodiments] In each of the above-described embodiments, a plurality of devices (for example, a host computer, an interface device,
The present invention may be applied to a system including a scanner or the like, or may be applied to a device including one device (for example, a copying machine, a facsimile machine, or the like).

Further, an object of the present invention is to supply a storage medium (or a recording medium) in which program codes of software for realizing the functions of the above-described embodiments are recorded to a system or an apparatus, and to provide a computer (or a computer) of the system or the 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 is needless to say that a case in which the functions of the above-described embodiments are implemented by performing part or all of the actual processing.

Further, after the program code read from the storage medium is written into the memory provided in the function expansion card inserted into the computer or the 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 the program code corresponding to the flowchart described above (FIG. 2, FIG. 3, or FIG. 6).

[0060]

As described above, according to the present invention,
An image processing apparatus, an image processing method, and a computer-readable storage medium that recognize a position shift between a template and an input image without using a special mark for position shift detection are realized.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus to which the present invention can be applied.

FIG. 2 is a flowchart illustrating a form process of the image processing apparatus according to the first embodiment.

FIG. 3 is a flowchart illustrating a process of determining a corresponding area according to the first embodiment.

FIG. 4 is a diagram illustrating a plurality of areas included in a form image, which are used as an example in the first embodiment.

FIG. 5 is a diagram showing a template to be compared with the form (form image) shown in FIG. 4;

FIG. 6 is a flowchart illustrating a process of determining a corresponding area according to the second embodiment.

[Explanation of symbols]

 101: CPU, 102: ROM, 103: RAM, 104: external storage device, 105: display, 106: keyboard, 107: pointing device, 108: image scanner, 109: network interface,

Claims (14)

[Claims] 1. An area extracting means for extracting a plurality of areas included in an input image from an input image in a predetermined format, detecting position information of each of the extracted areas, and being included in the image as template information. Storage means for storing size and position information of the predetermined area in advance; and an area corresponding to size information selected at least one of the size information of the predetermined area stored as template information in the storage means. Searching means for searching among the areas extracted by the area extracting means; and when a corresponding area is detected by the searching means, the detected area and the area selected from the template information By detecting the amount of displacement based on the position information of those regions, the relative displacement between the input image and the template information is detected. An image processing apparatus comprising: a shift amount recognizing unit that recognizes a shift amount. 2. The storage unit has registered therein in advance, of the template information, information for specifying an area to be searched when performing a search by the search unit. 2. The image processing apparatus according to claim 1, wherein only an area registered in the storage unit is to be searched. 3. The search means searches for an area corresponding to one area selected from the template information from each area extracted by the area extraction means, and the shift amount recognition means comprises: 2. The image processing apparatus according to claim 1, wherein a relative shift amount between the input image and the template information is recognized based on position information of a set of areas detected by the search unit. 4. The apparatus according to claim 1, further comprising a document reading unit that obtains the input image by reading the document in the predetermined format.
The image processing device according to any one of the above. 5. The image processing apparatus according to claim 1, further comprising an image obtaining unit that obtains the input image from an external device. 6. The image processing apparatus according to claim 1, further comprising a character recognizing unit for recognizing a character of the input image in which the shift amount recognized by the shift amount recognizing unit is corrected. 7. The image processing apparatus according to claim 1, wherein the input image is an image representing a form. 8. An area extracting step of extracting a plurality of areas included in the input image from an input image of a predetermined format and detecting position information of each of the extracted areas, and including the area information as template information in the input image. From the storage device in which the size and position information of the predetermined area to be stored are stored in advance, at least one of the size information of the predetermined area is selected, and an area corresponding to the selected size information is selected in the area extraction step. A search step of searching from among the extracted areas, and when a corresponding area is detected in the search step, a shift amount between the detected area and the area selected from the template information is calculated. A shift amount recognizing step of recognizing a relative shift amount between the input image and the template information by detecting based on the position information of those areas. Image processing method, characterized in that. 9. In the template information, information for specifying an area to be searched when performing a search in the search step is registered in the storage device in advance, and in the search step, 9. The search method according to claim 8, wherein only areas registered in the storage device are searched.
The image processing method described in the above. 10. An area corresponding to an area selected from the template information in the search step,
A search is performed from among the respective regions extracted in the region extraction step, and in the shift amount recognition step, the input image and the template information are compared with each other based on the position information of the set of regions detected in the search step. 9. The image processing method according to claim 8, wherein a relative shift amount is recognized. 11. The image processing method according to claim 8, further comprising a character recognizing step of recognizing a character of the input image in which the shift amount recognized in the shift amount recognizing step is corrected. 12. The image processing method according to claim 8, wherein the input image is an image representing a form. 13. A computer-readable storage medium storing a program code for operating a computer as the image processing apparatus according to claim 1. Description: 14. A computer-readable storage medium storing a program code capable of realizing the image processing method according to claim 8 by a computer.