JP2004062272A - Medium picture processor, medium picture processing method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To simplify an operation of an operator and to improve work efficiency when a prescribed region (region to which seal, face photograph and the other picture are added, for example) is extracted in a medium picture processor. <P>SOLUTION: The medium picture processor 1 extracts the prescribed region from the medium picture and changes an extraction position of the prescribed region when the picture which is to exist in the prescribed region protrudes from the prescribed region or requests the operator to change the extraction position of the prescribed region. A specified value of picture luminance is set as a threshold. A plurality of binary pictures are generated from a multi-level picture by the different threshold and are sequentially displayed on a display means 19. Then, a selection instruction of the suitable binary picture inputted by the operator is received. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a medium image processing apparatus, and more particularly to a seal image processing apparatus that performs a predetermined process on an image of a medium on which a seal is stamped.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, there are various devices that acquire an image of a medium in which an image area and a character area are mixed (hereinafter, referred to as a medium image) and use image information and character information described in the medium. Such devices (hereinafter, referred to as a medium image processing device) include, for example, a seal stamp collation machine and a seal stamp registration machine used in financial institutions. In addition, there are, for example, a passport and a car license inquiry system, and the like.
[0003]
[Problems to be solved by the invention]
When extracting a predetermined area from a medium image, the medium image processing apparatus has a problem in that the operation of the operator is complicated and the efficiency of work is reduced. Here, the predetermined area means an area to be extracted according to the use, and is, for example, an area to which a seal image, a face photograph, and other images are attached. Hereinafter, the problem of the medium image processing apparatus will be described in detail by taking the seal stamp collation in the seal stamp collation machine as an example.
[0004]
The seal stamp verification device has a scanner and other various image acquisition means, thereby acquiring data of the medium image on which the seal is impressed, and outputting the acquired medium image data to a display means such as a display, thereby obtaining a medium. Display the image. The operator inputs various information and an instruction to start a predetermined process (for example, a seal stamp collation process) using information input means such as a keyboard and a mouse while viewing the medium image displayed on the display means.
[0005]
Thereafter, the seal verification device extracts a predetermined region (here, a seal frame which is a region where the seal is stamped).
[0006]
The extraction of the seal stamp frame is performed based on, for example, information that is set in advance by the seal stamp collator recognizing the format of the medium image. Alternatively, in extracting the seal frame, the seal verification machine detects a shape that matches a shape unique to the seal (that is, a shape having a round shape, an oval shape, a rounded square shape, and character information added thereto). This is done by extracting the surrounding rectangular area. The format can be recognized, for example, by a stamp collation machine identifying the number of ruled lines in the medium image and the length of each ruled line, or reading a form number attached to a predetermined position of the medium image and registering it in advance. This is done by comparing with the formatted format.
[0007]
However, in some cases, such as when the seal is stamped out of the seal frame, or when the seal is re-stamped outside the seal frame due to loss of press or improper seal, the seal imprint image may not fit within the seal frame. In such a case, since the seal verification cannot be performed correctly, the operator needs to manually specify the area to which the imprint image is attached by using the information input means such as a keyboard and a mouse, and execute the verification process again. Was. Therefore, in such a case, the operation of the operator is complicated and the operation efficiency is reduced.
[0008]
In addition, when the seal is stamped again outside the seal frame due to a loss of press or a difference in seal, a seal imprint image that is inappropriate for collation may be selected. Even in such a case, the seal verification cannot be performed correctly. Therefore, the operator manually specifies an area to which the imprint image is attached by information input means such as a keyboard and a mouse, and causes the verification processing to be executed again. Needed. Therefore, in such a case, the operation of the operator is complicated and the operation efficiency is reduced.
[0009]
Further, for example, when extracting a seal image by binarizing a multi-valued medium image of 256 gradations in order to perform seal verification, the luminance threshold for binarization may not be appropriate. For example, if the threshold is too high, the imprint image will be blurred and invisible. If the threshold value is too low, the pixels of the outline of the imprint image are connected, and the outline of the imprint image is crushed, making it difficult to determine the image. Even in such a case, the seal verification cannot be performed correctly. Therefore, the operator needs to sequentially specify the threshold values in various stages by manual operation using information input means such as a keyboard and a mouse, and execute the verification process again. there were. Therefore, even in such a case, the operation of the operator is complicated and the operation efficiency is reduced.
[0010]
[Means for Solving the Problems]
In order to solve the above-mentioned problem, a medium image processing apparatus according to a first aspect of the present invention includes a predetermined area extracting unit that extracts a predetermined area from a medium image, and a method that includes an image that should be present in the predetermined area. A protruding detecting means for detecting the protruding portion, and when the protruding portion is detected, changing the extraction position of the predetermined area or changing the extraction position of the predetermined area to the operator, and having a changing means. I do.
[0011]
Further, in the medium image processing apparatus according to a second aspect, in addition to the first aspect, the changing means includes a predetermined area corresponding to a protruding amount of an image to be present in the predetermined area detected by the protruding detecting means. Is characterized by changing the extraction position.
[0012]
A medium image processing apparatus according to a third aspect is characterized in that, in addition to the first or second aspect, the predetermined area extracting means extracts a predetermined area by detecting a specific shape. .
[0013]
A medium image processing apparatus according to a fourth aspect includes a threshold value setting unit that sets a specific value of image luminance as a threshold value, and an image binarization unit that converts a multi-tone image into a binary image by using the threshold value. Image output means for outputting a binary image to the outside, and timing measuring means for measuring output timing when a plurality of binary images generated by different threshold values are sequentially output. .
[0014]
According to a fifth aspect of the present invention, in the medium image processing apparatus according to the fourth aspect, the threshold value setting means includes a threshold luminance value at which the outline of the image is crushed and the image is hard to be distinguished, and a threshold value at which the image is blurred and invisible. The luminance value is set as an upper limit and a lower limit of a threshold.
[0015]
A medium image processing apparatus according to a sixth aspect is the medium image processing apparatus according to any one of the first to fifth aspects, wherein the medium image is an image of a medium on which a seal is stamped, and exists in the predetermined area. The image to be formed is a seal image.
[0016]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, the medium image processing apparatus according to the present invention will be described with reference to a seal stamp collation in a seal stamp collation machine. It should be noted that the drawings are only schematically shown to the extent that the present invention can be understood. In addition, in each of the drawings, common elements are denoted by the same reference numerals, and description thereof is omitted.
[0017]
FIG. 1 is a diagram showing a configuration of a medium image processing apparatus according to the present invention.
[0018]
In FIG. 1, 1 is a computer which is a medium image processing device, 11 is an arithmetic unit, 13 is a storage unit, 15 is an installation unit, 17 is an image acquisition unit such as a scanner, 19 is a display unit such as a display, 21 is a keyboard or the like. A mouse and other information input means, 31 denotes a form medium on which a seal is stamped (hereinafter referred to as a seal form), 33 denotes a floppy (registered trademark) disk, a digital versatile disk (DVD), and other storage media.
[0019]
Various programs are stored in the storage medium 33, and the computer 1 functions as a medium image processing apparatus by installing various programs from the storage medium 33.
[0020]
<First embodiment>
In the present embodiment, the protruding portion of the imprint image is detected, and the coordinate position of a region to be cut out as the imprint image (hereinafter, referred to as an imprint region) is shifted in the protruding direction. As a result, in the present embodiment, an appropriate imprint image can always be presented to the operator, and the work efficiency can be improved.
[0021]
FIG. 2 is a diagram illustrating a configuration of the medium image processing apparatus according to the first embodiment.
[0022]
FIG. 2 shows that the computer 1 installs the “imprint area extraction function” program, the “protruding detection function” program, and the “extraction position change function” program from the storage medium 33 of FIG. This shows a state in which the means 41, the protruding detection means 43, and the extraction position changing means 45 are constructed.
[0023]
The operation of the present embodiment will be described below with reference to FIG. FIG. 3 is a flowchart showing the operation of the first embodiment.
[0024]
In step (hereinafter, referred to as S) 11, the computer 1 executes form reading.
[0025]
Specifically, first, the operator places the seal stamp form 31 on the image reading unit of the image obtaining unit 17 and inputs a start instruction of the seal verification process from the information input unit 21.
Then, the computer 1 drives the image acquisition unit 17 to read the image of the seal stamp form 31. At this time, the image acquiring unit 17 irradiates the seal stamp form 31 with light, receives the reflected light or the transmitted light by a sensor (not shown), and outputs a digital signal obtained thereby to the computer 1. The computer 1 temporarily stores the digital signal (that is, the medium image of the seal stamp 31) received from the image acquisition unit 17 in a buffer unit (not shown).
[0026]
In S13, the computer 1 extracts the seal stamp frame and the seal stamp area from the medium image of the seal stamp form 31 by the seal stamp area extracting means 41.
[0027]
Specifically, the imprint area extracting unit 41 first identifies the number of ruled lines and the length of each ruled line from the medium image of the seal stamp form 31, or determines whether the form attached to a predetermined position of the medium image Read the number. Then, the type of the medium is specified by comparing it with the format registered in advance, and a rectangular area formed by ruled lines is detected from the medium image, and a seal stamp defined in advance for each type of medium is detected. A seal stamp frame is extracted as a seal stamp frame that is close to the coordinate position of the frame. Alternatively, a shape matching a shape unique to a seal (that is, a shape having a round shape, an oval shape, a rounded square shape, and character information added thereto) is detected, and a rectangular region around the shape is extracted. . Thus, the seal frame is extracted.
[0028]
Further, the imprint area extracting unit 41 detects an area where pixels are connected in and around the specified seal stamp frame based on the luminance of the pre-defined imprint image, or detects an edge where the luminance is changing. To detect an area having a shape that matches a shape unique to a seal (that is, a shape having a round shape, an oval shape, a rounded square shape, and character information added thereto). When there are a plurality of areas detected in this way, a number is assigned, and a high-priority area is regarded as an imprint area, and an imprint area is extracted. In addition, the one with the higher priority order has a high degree of suitability as a seal image used for the seal stamp collation. For example, the distance of the seal image from the seal frame, the sharpness of the outline of the seal image, the size of the seal image, The degree of satisfying a predetermined condition, such as the presence or absence of a peripheral line, is high.
[0029]
The computer 1 stores the information of the imprint area thus extracted in the storage unit 13. At this time, for example, the extracted area is set to 1 and the rest is set to 0 to generate a mask binary image and store its coordinate position, or generate a rectangle circumscribing the imprint image and store the coordinate position. Or the parameters of the shape of the imprint image (center coordinates, radius, inclination, etc.) are stored.
[0030]
In step S <b> 15, the computer 1 uses the protrusion detection unit 43 to detect whether the seal imprint area does not protrude from the seal seal frame based on the relationship between the end of the seal seal area and the seal seal frame.
[0031]
More specifically, the protruding detection means 43 determines whether or not a predetermined number or more of pixels of the binary image masking the imprint area exist on or outside the frame of the seal stamp frame, or the coordinate position of a rectangle circumscribing the imprint area is determined. If the coordinates of the circumscribing rectangle calculated from the parameters of the shape of the seal image (center coordinates, radius, and inclination) are outside the frame of the seal stamp frame, Yes "is determined. Then, from the relationship between the end of the imprint area and the seal frame, the directions and amounts of the upper, lower, left, and right imprint areas protruding from the seal frame are detected.
[0032]
If there is no protruding part, the processing of the present embodiment is terminated, and the processing of the seal verification is performed.
[0033]
In S17, the computer 1 causes the extraction position changing unit 45 to change the extraction position of the imprint area. This is executed by the extraction position changing unit 45 shifting the coordinate position of the imprint area in the direction of the protrusion by the amount of protrusion (hereinafter, referred to as the amount of protrusion). At this time, the ratio of the imprint area protruding from the seal stamp frame may be processed as the protruding amount.
[0034]
After that, the computer 1 repeatedly executes the steps S15 to S17 until there is no protrusion. Then, when there is no overhang, the processing of the present embodiment is terminated, and the processing of the seal verification is performed.
[0035]
To change the extraction position of the imprint area, in S17, first, the extraction position changing means 45 causes the display means 19 to display a screen requesting the change of the extraction position of the predetermined area. May be executed when an instruction to change the extraction position of the predetermined area is input from the. The amount of change may be shifted not by the amount of protrusion detected by the protrusion detection means 43 but by the number of pixels set in advance.
[0036]
Further, when the extraction position is changed, the result may be displayed on the display means 19 so that the operator can confirm it.
[0037]
As described above, in the present embodiment, when the seal imprint area protrudes from the seal frame, the coordinate position of the seal imprint area is changed and the extraction is performed again so that the seal imprint does not protrude. Therefore, the operation of the operator can be simplified, and the imprint can be prevented from being partially missing, so that the work efficiency can be improved.
[0038]
<Second embodiment>
In the present embodiment, when a multi-valued medium image is binarized to extract a seal image, a plurality of binarized images are extracted by sequentially changing the luminance threshold, and a plurality of extracted binarized images are extracted. Images are displayed on the display means 19 continuously. Then, the operator is caused to select when a binarized image that is considered suitable is displayed, and a suitable binarized image is extracted. As a result, in the present embodiment, an appropriate imprint image can always be presented to the operator, and the work efficiency can be improved.
[0039]
FIG. 4 is a diagram illustrating a configuration of a medium image processing apparatus according to the second embodiment.
[0040]
FIG. 4 shows that the computer 1 installs a “threshold setting function” program, an “image binarization function” program, a “timing measurement function” program, and an “image output function” program from the storage medium 33 of FIG. The state in which a threshold setting unit 51, an image binarization unit 53, a timing measurement unit 55, and an image output unit 57 are constructed inside the unit 11 is shown.
[0041]
The operation of the present embodiment will be described below with reference to FIGS. FIG. 5 is a flowchart showing the operation of the second embodiment, and FIG. 6 is a diagram showing a binarized animation display.
[0042]
In S31, the computer 1 executes form reading. This step is the same as S11 described above.
[0043]
In S33, the computer 1 sets a threshold using the threshold setting unit 51.
[0044]
In this case, the threshold setting means 51, first sets an initial value Th ₀ as the threshold value T. Then, according to step is returned to S33 from S41 in later, from the initial value Th ₀ at constant luminance interval [Delta] T, repeatedly set so as to increase or decrease between the upper limit value _{Th Max} and the lower limit value _{Th Min.}
[0045]
For example, if the initial value Th ₀ is 128, the upper limit value Th _Max is 255, the lower limit value Th _Min is 0, and the constant luminance interval ΔT is 1, when the process returns from S41 to S33, the next threshold value T becomes 129. It becomes. Further, when the process returns from S41 to S33, the next threshold value T becomes 130. This is repeated until the threshold value T becomes 255. When the threshold value T becomes 255, thereafter, the constant brightness interval ΔT is set to −1, and the brightness interval is decreased by 254, 253,. Then, when the threshold value T becomes 0, the constant luminance interval ΔT is set to 1 again, and is increased one by one, such as 1, 2,. Repeat this.
[0046]
However, in the above description, the upper limit value Th _Max is 255 and the lower limit value Th _Min is 0, but the luminance range of the imprint image exists in a band narrower than this. Therefore, in a binarized image with a threshold value exceeding a certain value on the upper limit side, pixels around the outline of the imprint image are connected, and the outline of the imprint image is lost. As a result, it becomes difficult to determine the imprint image. Conversely, in the case of a binarized image with a threshold value below a certain value on the lower limit side, the imprint image is blurred and disappears. As a result, similarly, it becomes difficult to determine the imprint image. The image shown at the right end of FIG. 6 is a binarized image with a threshold value exceeding a certain value on the upper limit side, the image shown at the center of FIG. 6 is a binarized image considered to be preferable, and the image shown at the left end of FIG. The image shown is a binarized image with a threshold value below a certain value on the lower limit side.
[0047]
Therefore, in the present embodiment, the limit luminance value at which the outline of the image is crushed and the image is hard to be distinguished is set as the upper limit value Th _Max, and the limit luminance value at which the image is blurred and cannot be seen is set as the lower limit value Th _Min. . The upper limit value Th _Max and the lower limit value Th _Min are obtained in advance by collecting data indicating the relationship between faintness or crushing of an image to be extracted and edge intensity or luminance distribution according to the use of the medium image processing apparatus. It is desirable to determine based on this data. The edge strength means a difference in contrast between the inside and the outside of the imprint image.
[0048]
In S35, the computer 1 binarizes the medium image using the threshold T set by the threshold setting unit 51 by the image binarization unit 53.
[0049]
In S37, the computer 1 causes the timing measurement unit 55 to measure the elapsed time from when the image output unit 57 last output the medium image to the display unit 19 to the present. If the elapsed time exceeds the predetermined value, the process proceeds to S39. If the elapsed time does not exceed the predetermined value, the elapsed time is measured at regular time intervals until the elapsed time exceeds the predetermined value. Thereby, the computer 1 can cause the display unit 19 to continuously display the binarized medium image at regular time intervals. Thereby, for example, as shown in FIG. 6, a binarized medium image can be displayed as an animation. That is, a binary image based on the lower threshold value to the upper threshold value is continuously displayed from time t1 to t5, and a binary image based on the upper threshold value to the lower threshold value is continuously displayed from time t6 to t10. Can be performed repeatedly. The display speed of the animation can be adjusted by changing the length of the certain time interval at this time.
[0050]
In S39, the computer 1 causes the image output unit 57 to output the binarized medium image to the display unit 19 by the image binarization unit 53.
[0051]
Thereafter, the display means 19 displays the binarized medium image. When the operator sees this, if the medium image is suitable, the information input means 21 inputs the determination of the medium image. If the medium image is inappropriate, the information input unit 21 inputs a command to display the next medium image, or leaves the image without any input.
[0052]
In S41, the computer 1 detects whether a decision has been input by the operator. If there is an input of determination, the processing of the present embodiment ends, and the processing of seal verification is performed. If there is no decision input, the process returns to S33, and the processes of S33 to S41 are repeatedly executed until the decision is input by the operator. Then, when the operator inputs a decision, the processing of the present embodiment ends, and the processing of seal verification is performed.
[0053]
As described above, in the present embodiment, the threshold value is changed stepwise, a binarized medium image is extracted based on the threshold value, and the binarized medium image can be displayed on the display unit 19 as an animation. For this reason, when a binarized medium image considered to be suitable is displayed by visual confirmation, the operator only has to input a decision, so that an effect similar to that of setting an optimal threshold is obtained. As a result, the operation of the operator can be simplified, and it is possible to improve the work efficiency by eliminating the possibility that the imprint is partially missing or the pixels of the outline of the imprint are not connected.
[0054]
The present invention is not limited to the above embodiment, and various applications and modifications can be considered without departing from the gist of the present invention.
[0055]
For example, in the above-described first and second embodiments, the medium image processing apparatus has been described using the seal verification machine as an example. However, a seal registration machine, a passport or a car license inquiry system, and other medium image processing apparatuses That is, the medium image processing apparatus is applicable to a device that acquires a medium image in which an image area and a character area are mixed and uses image information and character information described on a medium.
[0056]
Further, for example, in the above-described first and second embodiments, the imprint area is described as the predetermined area. However, the predetermined area is not limited to this, and a face photograph or other image to be extracted may be used depending on the application. Can be changed to the area marked with.
[0057]
Further, for example, in the above-described first and second embodiments, the computer 1 is described as installing various programs from the storage medium 33. However, the computer 1 installs various programs from an external computer via a communication line network. You may make it.
[0058]
The present invention includes such various applications and modifications.
[0059]
【The invention's effect】
As described above, the medium image processing apparatus according to the present invention performs the operation of the operator when extracting a predetermined area (for example, an area with a seal, a face photograph, or another image) from the medium image. The operation efficiency can be improved with simplification.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating a configuration of a medium image processing apparatus.
FIG. 2 is a diagram illustrating a configuration of a medium image processing apparatus according to the first embodiment.
FIG. 3 is a flowchart showing an operation of the first embodiment.
FIG. 4 is a diagram illustrating a configuration of a medium image processing apparatus according to a second embodiment.
FIG. 5 is a flowchart showing an operation of the second embodiment.
FIG. 6 is a diagram showing a binarized animation display.
[Explanation of symbols]
REFERENCE SIGNS LIST 1 computer 11 arithmetic unit 13 storage unit 15 installation unit 17 image acquisition unit 19 display unit 21 information input unit 31 seal form 33 storage medium

Claims (9)

A predetermined region extracting means for extracting a predetermined region from the medium image, and a protruding detecting means for detecting the protruding when an image to be present in the predetermined region protrudes from the predetermined region,
Changing means for requesting the operator to change the extraction position of the predetermined area or to change the extraction position of the predetermined area when the overhang is detected;
A medium image processing apparatus comprising: 2. The medium image processing apparatus according to claim 1, wherein the changing unit changes an extraction position of the predetermined region according to an amount of an image that should be present in the predetermined region detected by the protrusion detection unit. . The medium image processing apparatus according to claim 1, wherein the predetermined area extracting unit extracts a predetermined area by detecting a specific shape. Threshold setting means for setting a specific value of image brightness as a threshold,
Image binarization means for converting a multi-tone image into a binary image according to a threshold,
Image output means for outputting a binary image to the outside;
When sequentially outputting a plurality of binary images generated by different threshold values, a timing measurement unit that measures output timing;
A medium image processing apparatus comprising: 5. The threshold setting unit according to claim 4, wherein the threshold setting unit sets a limit luminance value at which an outline of the image is collapsed and the image is hard to be distinguished and a limit luminance value at which the image is blurred to be invisible as an upper limit and a lower limit of the threshold. 14. The medium image processing device according to claim 1. The medium image processing according to claim 1, wherein the medium image is an image of a medium on which a seal is stamped, and an image to be present in the predetermined area is a seal image. apparatus. In a medium image processing method for performing arbitrary processing on a medium image by a medium image processing device,
Extracting a predetermined area from the medium image, and changing an extraction position of the predetermined area or requesting an operator to change the extraction position of the predetermined area when an image to be present in the predetermined area is out of the predetermined area. A medium image processing method. In a medium image processing method for performing arbitrary processing on a medium image by a medium image processing device,
A medium image processing method comprising: generating a plurality of binary images from a multi-tone image with different thresholds; sequentially displaying the binary images on a display unit; and accepting a selection command of a suitable binary image input by an operator. A program for realizing the medium image processing device according to claim 1 by a computer.

Images