JP2016015668A - Image processing device, image processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing device which synthesizes a surface image of a medium on which visible rays are irradiated and a surface image of a medium on which ultraviolet rays are irradiated in a state of allowing easy discrimination of a printed part by a UV ink.SOLUTION: A control device 7 (image processing device) comprises: an image reading part 35 for acquiring a first surface image G1 obtained by reading a check 2 on which first light (visible rays) are irradiated and a second surface image G2 obtained by reading the check 2 on which second light including ultraviolet rays are irradiated by driving an image sensor 16; a first corrected image creation part 51 for creating a first corrected image H1 where brightness of the first surface image G1 is decreased; a second corrected image creation part 52 for creating a second corrected image H2 where a contrast of the second surface image G2 is increased; and a synthetic image creation part 47 for creating a synthetic image where the first corrected image H1 and the second corrected image H2 are synthesized.

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program for reading a surface of a medium including a printed portion printed with ink that emits fluorescence when irradiated with ultraviolet rays.

  In a financial institution where a check is brought in, the check is put on a check processing device, magnetic ink characters printed on the check are magnetically read, and settlement processing is performed based on the acquired magnetic information. In addition, in parallel with reading of magnetic ink characters, a financial institution reads the surface of a check irradiated with visible light by a check processing device, and stores the acquired surface image as evidence of settlement. Furthermore, in a financial institution, when an anti-counterfeit image printed with ink that emits fluorescence when irradiated with ultraviolet rays (hereinafter referred to as UV ink) is used as a check, The surface of the check irradiated with ultraviolet rays is read, and the acquired surface image is used to determine the authenticity of the check. In addition, financial institutions store the surface images of checks irradiated with ultraviolet rays as proof of payment.

  A check processing apparatus that can be used for such check settlement processing is described in Patent Document 1. The check processing apparatus of this document is equipped with a magnetic sensor that magnetically reads magnetic ink characters and an image sensor that irradiates the surface of the check with reading light to acquire a surface image. The image sensor emits visible light and ultraviolet light as reading light.

JP2013-70225A

  As evidence of payment by check, when storing the surface image of a check irradiated with visible light and the surface image of a check irradiated with ultraviolet light, there is a problem that the data capacity of the image to be stored increases. Here, in order to reduce the data capacity of the image to be saved as payment evidence, the surface image of the check irradiated with visible light and the surface image of the check irradiated with ultraviolet light are combined to save one composite image. It is possible to do. However, when these two surface images are simply combined, there arises a problem that it becomes difficult to recognize the forgery prevention image in the combined image.

  An object of the present invention is to provide an image processing apparatus that synthesizes a surface image of a medium irradiated with visible light and a surface image of a medium irradiated with ultraviolet light in a state in which it is easy to distinguish a printed portion using UV ink. An image processing method and a program are provided.

  In order to solve the above problems, an image processing apparatus according to the present invention drives an image sensor to acquire a first image obtained by reading the surface of a medium irradiated with first light, and includes an ultraviolet ray. An image acquisition unit that acquires a second image obtained by reading the surface of the medium irradiated with the second light; and a first correction image generation unit that generates a first correction image with reduced brightness of the first image; A second corrected image generating unit that generates a second corrected image in which the contrast of the second image is increased, and a combined image generating unit that generates a combined image obtained by combining the first corrected image and the second corrected image. It is characterized by having.

  In the present invention, when combining the first image of the medium irradiated with the first light such as visible light and the second image of the medium irradiated with the second light including ultraviolet light, the first image is bright. A first corrected image with reduced brightness (for example, brightness) is generated, a second corrected image with increased contrast is generated for the second image, and the first corrected image and the second corrected image are combined. . Here, in the second image acquired when the surface of the check irradiated with ultraviolet rays is read by the image sensor, a portion obtained by imaging the reflected light of the reading light reflected on the surface of the check is dark (the luminance is low). The portion obtained by imaging fluorescence from the printed portion with UV ink becomes a bright (high luminance) gray scale image. Therefore, the second corrected image in which the contrast of the second image is increased is easier to discriminate the printed portion with the UV ink than the second image. Further, if the second corrected image and the first corrected image with reduced brightness are synthesized with respect to the first image, the contrast between the printed portion of the second corrected image by the UV ink and the first corrected image can be increased. it can. Therefore, the surface image of the medium irradiated with visible light and the surface image of the medium irradiated with ultraviolet light can be combined in a state where it is easy to discriminate a printed portion with UV ink.

  In the present invention, the first corrected image generation unit may generate the first corrected image by reducing luminance values of pixels of the first image at a constant rate. In this way, it is easy to generate the first corrected image.

  In the present invention, the second corrected image generation unit extracts, as the edge region, an area including an image portion in which the difference in luminance value between adjacent pixels is larger than a preset luminance difference in the second image. And a plurality of pixels included in the edge region are divided into a first pixel group and a second pixel group having a lower luminance value than the first pixel group based on a luminance value, and the first pixel group A correction function generating unit that generates a correction function for correcting a luminance value of a pixel so that a contrast is increased between the pixel included and the pixel included in the second pixel group; and a pixel constituting the second image A luminance value corrected image generation unit that generates the second corrected image obtained by correcting the luminance value of the pixel with the correction function. According to this configuration, the edge region extraction unit extracts, as an edge region, an image portion including a printed portion using UV ink and a surface portion of the medium not printed with UV ink from an image of the medium irradiated with ultraviolet rays. Then, the correction function generation unit generates a correction function that increases the contrast between the bright part (first pixel group) and the dark part (second pixel group) in the edge region. Thereafter, the corrected image generation unit generates a second corrected image obtained by correcting the entire image based on the correction function. Thereby, in the 2nd correction image, the contrast between the printing part by UV ink and the surface of the medium which has not been printed by UV ink increases. Therefore, it becomes easy to distinguish the printed portion by the UV ink.

  In the present invention, in the synthesized image, a luminance value of a synthesized pixel obtained by synthesizing the pixel of the first corrected image and the pixel of the second corrected image is equal to or higher than the luminance value of the pixel of the first corrected image. And it is desirable that it is more than the luminance value of the pixel of the 2nd amendment picture. In this way, the luminance of the pixel corresponding to the printed portion of UV ink in the composite image does not decrease, and this printed portion can be easily identified.

  In the present invention, the first image may include an image based on visible light, and the second image may include an image based on fluorescence from UV ink. In this way, for example, the surface of a check on which an image for preventing forgery is printed with UV ink can be read, and a composite image obtained by combining the image on the surface of the check and the image for preventing forgery can be generated.

  Next, the image processing method of the present invention acquires a first image obtained by reading the surface of the medium irradiated with the first light by the image sensor, and the second medium including the ultraviolet light is irradiated with the second light. A second image obtained by reading the surface is acquired, a first corrected image in which the luminance of the first image is reduced is generated, a second corrected image in which the contrast of the second image is increased is generated, and the first image is generated. A synthesized image obtained by synthesizing one corrected image and the second corrected image is generated.

  In the present invention, when the first image of the medium irradiated with the first light such as visible light and the second image of the medium irradiated with the second light including ultraviolet light are combined, the luminance of the first image is determined. A first corrected image with reduced contrast is generated, a second corrected image with increased contrast is generated for the second image, and the first corrected image and the second corrected image are combined. Here, the second corrected image in which the contrast of the second image is increased is easier to discriminate the printed portion by the UV ink than the second image. Further, if the second corrected image and the first corrected image with reduced brightness are synthesized with respect to the first image, the contrast between the printed portion of the second corrected image by the UV ink and the first corrected image can be increased. it can. Therefore, the surface image of the medium irradiated with visible light and the surface image of the medium irradiated with ultraviolet light can be combined in a state where it is easy to discriminate a printed portion with UV ink.

  In the present invention, the first corrected image can be generated by reducing the luminance value of the pixel of the first image at a constant rate. In this way, it is easy to generate the first corrected image.

  In the present invention, in order to increase the contrast between the printed portion with the UV ink and the surface of the medium not printed with the UV ink, a difference in luminance value between adjacent pixels in the second image is determined in advance. An area including an image part larger than the set luminance difference is extracted as an edge area, and a plurality of pixels included in the edge area are lower in luminance than the first pixel group and the first pixel group based on the luminance. A correction function for correcting the luminance value of the pixels so as to increase the contrast between the pixels included in the first pixel group and the pixels included in the second pixel group by allocating to the second pixel group; The second correction image may be generated by correcting the luminance value of the pixel constituting the second image with the correction function.

  In the present invention, the luminance value of the synthesized pixel of the synthesized image obtained by synthesizing the pixel of the first corrected image and the pixel of the second corrected image is equal to or higher than the luminance value of the pixel of the first corrected image, and The luminance value of the pixel of the second corrected image may be greater than or equal to the luminance value. In this way, the luminance of the pixel corresponding to the printed portion of UV ink in the composite image does not decrease, and this printed portion can be easily identified.

  In the present invention, the first image may include an image based on visible light, and the second image may include an image based on fluorescence from UV ink. In this way, for example, the surface of a check on which an image for preventing forgery is printed with UV ink can be read, and a composite image obtained by combining the image on the surface of the check and the image for preventing forgery can be generated.

  According to the present invention, in a program that operates in a control device that controls an image sensor, the control device drives the image sensor to read a first image read from the surface of the medium irradiated with the first light. An image acquisition unit that acquires the second image obtained by reading the surface of the medium irradiated with the second light including ultraviolet light and a first correction image in which the luminance of the first image is reduced are generated. A first corrected image generating unit; a second corrected image generating unit that generates a second corrected image in which the contrast of the second image is increased; and a composite image obtained by combining the first corrected image and the second corrected image. And a composite image generation unit that generates the function.

  According to the present invention, when combining the first image of the medium irradiated with the first light such as visible light and the second image of the medium irradiated with the ultraviolet light, the luminance of the first image is reduced. A first corrected image is generated, a second corrected image with increased contrast is generated for the second image, and the first corrected image and the second corrected image are combined. Here, the second corrected image in which the contrast of the second image is increased is easier to discriminate the printed portion by the UV ink than the second image. Further, if the second corrected image and the first corrected image with reduced brightness are synthesized with respect to the first image, the contrast between the printed portion of the second corrected image by the UV ink and the first corrected image can be increased. it can. Therefore, the surface image of the medium irradiated with visible light and the surface image of the medium irradiated with ultraviolet light can be combined in a state where it is easy to discriminate a printed portion with UV ink.

It is explanatory drawing of the check processing system to which this invention is applied. It is a block diagram which shows the control system of a check processing system. It is explanatory drawing of the 1st surface image of a check, and a 1st correction image. It is explanatory drawing of the 2nd surface image of a check, and a 2nd correction image. It is a graph of the luminance value in the image part of the surface image of a check. It is explanatory drawing of the histogram of the brightness place in an edge area | region, and a correction function. It is explanatory drawing of a synthesized image.

  A check processing apparatus as an embodiment of an image processing apparatus to which the present invention is applied will be described below with reference to the drawings.

(Check processing system)
FIG. 1A is an explanatory diagram of a check processing system, and FIG. 1B is an explanatory diagram of a check. A check processing system (image processing system) 1 performs a settlement process using a check 2. As shown in FIG. 1A, the check processing system 1 includes a check processing device 5 and a control device (image processing device) 7 connected to the check processing device 5 via a cable 6 or the like so as to be able to communicate. The control device 7 includes a device body 8, an input device 9 and a display 10 connected to the device body 8. The apparatus main body 8 is a computer.

  On the surface 2a of the check 2 brought into the financial institution, as shown in FIG. 1B, magnetic ink characters 11 representing a customer account number or the like are printed with magnetic ink. An anti-counterfeiting image 12 is printed on the surface 2a of the check 2 with UV ink that emits fluorescence when irradiated with ultraviolet rays.

  As shown in FIG. 1A, the check processing device 5 includes a magnetic sensor 15, an image sensor 16, a conveyance path extending through a magnetic reading position A by the magnetic sensor 15 and an image reading position B by the image sensor 16. 17. Further, the check processing device 5 includes a transport mechanism 18 that transports the check 2 inserted in the transport path 17 along the transport path 17 and passes the magnetic reading position A and the image reading position B. The transport mechanism 18 includes a transport roller pair 19 that feeds the check 2 inserted in the transport path 17 and a transport motor 20 (see FIG. 2) that drives the transport roller pair 19.

  The magnetic sensor 15 is arranged with the magnetic reading surface 21 facing the conveyance path 17. The magnetic sensor 15 reads the magnetic ink character 11 from the check 2 that passes through the magnetic reading position A.

  The image sensor 16 is a CIS (Contact Image Sensor) module. The image sensor 16 irradiates the check 2 passing through the image reading position B with light, and reads the reflected light or light emission from the check 2. The image sensor 16 is arranged with the irradiation unit 25 and the reading unit (imaging device) 26 facing the conveyance path 17.

  The irradiation unit 25 is linearly provided in the vertical direction perpendicular to the conveyance direction C of the check 2. The irradiation unit 25 includes a plurality of red light emitting elements 25R that emit red reading light, a plurality of green light emitting elements 25G that emit green reading light, a plurality of blue light emitting elements 25B that emit blue reading light, and a light emitting element. A plurality of ultraviolet light emitting elements 25UV for irradiating ultraviolet reading light composed of ultraviolet rays are provided. The plurality of light emitting elements 25R, 25G, 25B, and 25UV that irradiate each reading light are arranged in a line extending in the vertical direction.

  The reading unit 26 is linearly provided in the vertical direction along the irradiation unit 25. The reading unit 26 includes an image sensor such as a CMOS sensor. The reading unit 26 (imaging device) sequentially reads the check 2 passing through the image reading position B for each line extending in the vertical direction at the timing when each reading light is irradiated to the check 2.

  The check processing device 5 transports the check 2 along the transport path 17 by the transport mechanism 18. Then, the check processing device 5 reads the magnetic ink characters 11 from the check 2 passing through the magnetic reading position A by the magnetic sensor 15 and acquires magnetic information. Further, the check processing device 5 transmits the read magnetic information to the control device 7. Further, the check processing device 5 reads the surface 2a of the check 2 from the check 2 passing through the image reading position B by the image sensor 16, and sequentially transmits the read information to the control device 7.

  The control device 7 receives the magnetic information acquired by the check processing device 5 and performs a settlement process based on the magnetic information and the input information input from the input device 9.

  In addition, the control device 7 performs the first surface image (first image) and the second surface image (second image) based on the read information (output from the image sensor 16) sequentially transmitted from the check processing device 5. ) To get. The first surface image is a gray scale (composite gray) image when the check 2 is irradiated with visible light reading light (red reading light, blue reading light, and green reading light), and the second surface image is obtained with ultraviolet reading light. It is a gray scale image when the check 2 is irradiated. The first surface image and the second surface image are configured by pixels corresponding to the resolution of the image sensor 16.

  Further, the control device 7 corrects and combines the acquired first surface image and second surface image, and generates a combined image by combining the first surface image and the second surface image. Then, the control device 7 stores and holds the composite image as evidence of the settlement process.

(Control system)
FIG. 2 is a schematic block diagram showing a control system of the check processing system 1. FIG. 3 is an explanatory diagram of the first surface image and the first corrected image. FIG. 4 is an explanatory diagram of the second surface image and the second corrected image.

  As shown in FIG. 2, the control system of the check processing device 5 is configured around a control unit 31 on which a CPU and the like are mounted. A communication unit 32 including a communication interface for communicating with the control device 7 is connected to the control unit 31. Further, the transport motor 20, the magnetic sensor 15, and the image sensor 16 are connected to the control unit 31 via a driver (not shown).

  In the control unit 31, a control program is operating. The control program causes the control unit 31 to function as a conveyance control unit 33, a magnetic information acquisition unit 34, and an image reading unit 35. Therefore, the control unit 31 includes a conveyance control unit 33, a magnetic information acquisition unit 34, and an image reading unit 35.

  The conveyance control unit 33 drives and controls the conveyance motor 20 to convey the check 2 along the conveyance path 17.

  The magnetic information acquisition unit 34 drives the magnetic sensor 15 to read magnetic reading information (detection signal) from the magnetic ink character 11 of the check 2 that passes the magnetic reading position A. Further, the magnetic information acquisition unit 34 recognizes the magnetic ink character 11 based on the magnetic reading information. The magnetic ink character 11 is recognized by collating the magnetic reading information output from the magnetic sensor 15 with the signal waveform pattern of the magnetic ink character 11 stored and held in advance. The magnetic information acquisition unit 34 acquires the recognition result of the magnetic ink character 11 as magnetic information. When the magnetic information is acquired, the magnetic information acquisition unit 34 transmits this magnetic information to the control device 7.

  The image reading unit 35 drives the image sensor 16 to read the surface 2 a of the check 2 from the check 2 that passes through the image reading position B.

  When reading the surface 2 a of the check 2 by the image sensor 16, the image reading unit 35 transfers the check 2 from the irradiation unit 25 to the check 2 while conveying the check 2 by an amount corresponding to one line corresponding to the reading resolution at the image reading position B. The surface 2a is irradiated with red reading light, green reading light, blue reading light, and ultraviolet reading light in this order. Further, every time the check 2 is conveyed by the conveyance amount for one line, the image reading unit 35 receives the surface portion for one line of the check 2 irradiated with red reading light and the blue reading light to the reading unit 26. The surface portion of one line of the irradiated check 2, the surface portion of one line of the check 2 irradiated with the green reading light, and the surface portion of one line of the check 2 irradiated with the ultraviolet reading light are sequentially read. Let me take it. Further, the image reading unit 35 reads the reading information output from the reading unit 26 while the red reading light is irradiated, the reading information output from the reading unit 26 while the green reading light is irradiated, and the blue reading. The reading information output from the reading unit 26 while the light is irradiated and the reading information output from the reading unit 26 while the ultraviolet reading light is applied are sequentially transmitted to the control device 7.

  Next, as shown in FIG. 2, the control device 7 includes a check processing device control unit 41, an image processing unit 42, and a settlement processing unit 43. The control device 7 functions as a check processing device control unit 41, an image processing unit 42, and a payment processing unit 43 when a program operates on the device main body 8.

  The check processing device control unit 41 transmits a processing operation start command for starting the check processing operation to the check processing device 5.

  The image processing unit 42 acquires the first surface image G1 based on the read information output from the reading unit 26 while the visible light (red reading light, green reading light, and blue reading light) is irradiated. Further, the image reading unit 35 acquires the second surface image G2 based on the reading information output from the reading unit 26 while the ultraviolet reading light is irradiated. Furthermore, the image processing unit 42 generates a composite image I obtained by combining the first surface image G1 and the second surface image G2.

  The settlement processing unit 43 performs settlement processing based on magnetic information such as an account number received from the check processing device 5 and input information such as an amount input to the control device 7 via the input device 9. Further, the settlement processing unit 43 displays the composite image I generated by the image processing unit 42 on the display 10. Further, the settlement processing unit 43 stores and holds the composite image I in association with settlement information including a settlement date, magnetic information, input information, and the like.

  Here, the image processing unit 42 includes an image acquisition unit 45, a corrected image generation unit 46, and a composite image generation unit 47.

  The image acquisition unit 45 receives reading information output from the reading unit 26 while the red reading light is emitted, reading information output from the reading unit 26 while the green reading light is emitted, and blue reading light. Based on the read information output from the reading unit 26 during irradiation, the first surface image G1 is acquired. The first surface image G1 acquired by the image acquisition unit 45 is as shown in the upper diagram of FIG. The lower diagram in FIG. 3A is a histogram of the distribution of brightness (luminance values) in the first surface image G1. In order to display an image on the display 10, brightness is represented by luminance, the horizontal axis of the histogram is a luminance value, and the vertical axis is frequency (number of pixels). As described above, since the first surface image G1 is a grayscale image, the luminance value representing luminance is 256 gradations, the luminance value 0 is the darkest (black), and the luminance value 255 is the brightest (white). To do.

  The image acquisition unit 45 acquires the second surface image G2 based on the read information output from the reading unit 26 while the ultraviolet reading light is irradiated. The second surface image G2 acquired by the image acquisition unit 45 is shown on the upper side of FIG. The lower diagram in FIG. 4A is a histogram of the distribution of brightness (luminance values) in the second surface image G2. In the second surface image G2, the portion where the reflected light (ultraviolet light) of the reading light reflected by the surface of the check 2 is imaged is dark (the luminance is low), and the portion where the fluorescence emitted from the printed portion by the UV ink is imaged is bright. (High brightness).

  The correction image generation unit 46 includes a first correction image generation unit 51 that corrects the first surface image G1 and a second correction image generation unit 52 that corrects the second surface image.

  The first corrected image generation unit 51 generates a first corrected image by reducing the luminance value of each pixel of the first surface image G1 at a constant rate. In this example, the luminance value of each pixel of the first surface image G1 is reduced by 50%. The first corrected image H1 generated by the first corrected image generation unit 51 is as shown in the upper diagram of FIG. The lower diagram in FIG. 3B is a histogram of the distribution of brightness (luminance values) in the first corrected image H1. As shown in FIG. 3, the first corrected image H1 is an image that is darker (luminance is reduced) than the first surface image G1.

  The second corrected image generation unit 52 includes an edge region extraction unit 53, a correction function generation unit 54, and a brightness value correction image generation unit 55.

  When the second surface image G2 is acquired, the edge region extraction unit 53 extracts the image portion of the second surface image G2 as an edge region. The edge region is extracted with reference to the luminance value of each pixel constituting the second surface image G2. The edge region is a region including an image portion in which the difference between the luminance values of the adjacent first pixel and second pixel is larger than a preset luminance difference. Further, the edge region is a region including an image portion in which the luminance value of the first pixel having the higher luminance value among the first pixel and the second pixel is higher than the average Ave of the luminance values of all the pixels of the second surface image G2. is there.

  FIG. 5 is a graph showing the luminance of a part of a pixel row that passes through the anti-counterfeit image 12 in the longitudinal direction of the check 2 (direction corresponding to the transport direction C) in the second surface image G2. The horizontal axis represents the pixel position, and the vertical axis represents the luminance value (0 to 255) of the pixel at that position. The luminance value 0 is black and the luminance value 255 is white. In the example shown in FIG. 5, there are four image portions P1, P2, P3, and P4 as image portions in which the difference between the luminance values of the adjacent first and second pixels is larger than a predetermined luminance difference. In the image portions P1 and P2, the luminance value of the first pixel having high luminance is lower than the average Ave of the luminance values of all the pixels constituting the image. In the image portions P3 and P4, the luminance value of the first pixel having high luminance is higher than the average Ave of the luminance values of all the pixels constituting the image.

  Here, the luminance value of the image portion obtained by imaging the fluorescence emitted by the UV ink is higher than the average Ave of the luminance values of all the pixels constituting the image even when the concentration of the UV ink is not sufficient. Accordingly, the P3 and P4 image portions including pixels whose luminance values are higher than the average luminance value Ave are image portions obtained by photographing the printed portion using UV ink. Therefore, the edge region extraction unit 53 extracts the image portion P3 or the image portion P4 as an edge region. The extracted edge region 56 is, for example, a region shown in FIG. The image portions P1 and P2 are portions where the surface of the check 2 is patterned or printed with ordinary ink.

  The correction function generator 54 distributes the plurality of pixels included in the edge region 56 into a first pixel group and a second pixel group based on the luminance value. FIG. 6A is an example of a histogram of brightness (luminance value) distribution in a plurality of pixels included in the edge region 56. FIG. 6B is a graph of the correction function.

  As shown in FIG. 6A, the plurality of pixels included in the edge region 56 has a bimodal distribution in which two peaks are formed in a portion where the brightness (brightness value) distribution is high and low. It will be equipped with. Therefore, the correction function generation unit 54 uses an algorithm for finding a threshold value that divides a plurality of bimodal distribution values into two, and sets the plurality of pixels to a luminance higher than that of the first pixel group and the first pixel group. The second pixel group having a low value is assigned. As an algorithm for finding a threshold value for dividing a plurality of bimodal distribution values into two, Otsu's method is known.

  Further, the correction function generation unit 54 generates a correction function for correcting the luminance value of each pixel so that the contrast increases between each pixel included in the first pixel group and each pixel included in the second pixel group. To do. The correction function generation unit 54 averages the luminance value of each pixel included in the first pixel group, and the second average luminance value averaged the luminance value of each pixel included in the second pixel group. A correction function is generated based on L2 and a third average luminance value L3 obtained by averaging the first average luminance value L1 and the second average luminance value L2.

  Here, the generated correction function corrects the luminance value of the pixel having the first average luminance value L1 to the first target luminance value T1, and changes the luminance value of the pixel having the second average luminance value L2 to the second target luminance value T2. The luminance value of the pixel having the third average luminance value L3 is corrected to the third target luminance value T3. The first target luminance value T1 is higher than the second target luminance value T2 and the third target luminance value T3, and is lower than the highest luminance value (255 in this example). The second target luminance value T2 is a value lower than the third target luminance value T3, and is lower than the lowest luminance value (0 in this example).

  The correction function is such that the first difference between the first target luminance value T1 and the first average luminance value L1 is the second difference between the second target luminance value T2 and the second average luminance value L2, and the third target luminance value. The brightness value of each pixel is corrected so that the third difference between T3 and the third average brightness value L3 is larger than the third difference, and the second difference is smaller than the third difference. In this example, the first average luminance value L1 is 54.02, and the first target luminance value T1 is 200. The first difference is 145.98. The second average luminance value L2 is 41.64, and the second target luminance value T2 is 63. The second difference is 21.36. The third average luminance value L3 is 47.83, and the third target luminance value T3 is 127. The second difference is 97.17.

  The correction function generated by the correction function generation unit 54 is, for example, as shown in FIG. The horizontal axis in FIG. 6B is the luminance value (input luminance value) of the pixel before correction, and the vertical axis is the luminance value (corrected luminance value) of the pixel after correction. In this example, the correction function is represented by a Pezier curve, a sigmoid curve, or the like.

  The first target luminance value T1 is set to a value lower than the highest luminance value (255 in this example) because the luminance of the second corrected image obtained by correcting the second surface image G2 with the correction function is the highest. This is to prevent or suppress saturation with the value. Here, the correction function can be generated by setting the second target luminance value T2 to a value lower than the second average luminance value L2.

  The luminance value corrected image generation unit 55 generates a second corrected image H2 in which the luminance value of each pixel is corrected with a correction function for all the pixels constituting the second surface image G2. The second corrected image H2 is as shown in the upper diagram of FIG. The lower diagram in FIG. 4B is a histogram of the brightness (luminance value) distribution in the second corrected image H2. The second corrected image H2 illustrated in FIG. 4B is an image having an increased contrast compared to the second surface image G2 illustrated in FIG.

  The composite image generation unit 47 generates a composite image obtained by combining the first correction image H1 and the second correction image H2. FIG. 7A is an explanatory diagram of a composite image generated by the composite image generation unit 47, and FIG. 7B is a histogram of brightness (luminance value) distribution in the composite image.

  The synthesized image generation unit 47 synthesizes corresponding pixels in the first corrected image H1 and the second corrected image H2. The synthesized image generation unit 47 has a synthesized pixel obtained by synthesizing the pixel of the first corrected image H1 and the pixel of the second corrected image H2 in the synthesized image I equal to or higher than the luminance value of the pixel of the first corrected image H1, and The first corrected image H1 and the second corrected image H2 are combined by a combining method that is equal to or higher than the luminance value of the pixel of the second corrected image H2.

In this example, the pixels of the first corrected image H1 and the pixels of the second corrected image H2 are synthesized based on the following equation (1). In Expression (1), Im is the luminance of the combined pixel, I1 is a pixel of the first corrected image H1, and I2 is a pixel of the second corrected image H2.
Im = 255 * (1- (1-I1 / 255) * (1-I2 / 255)) (1)

  In the synthesis method based on the formula (1), the first correction image H1 is negative-positive-inverted, the second correction image H2 is negative-positive-inverted, and each pixel of the inverted first correction image H1 is inverted. The composite image I is generated by superimposing the pixels of H2 and further performing negative-positive inversion on the superimposed image.

  Here, the composite image I generated by the composite image generation unit 47 is as shown in FIG. The composite image I is a composite of the first corrected image H1 with reduced brightness for the first surface image G1 and the second corrected image H2 with increased contrast for the second surface image G2. Further, in the composition method by the composite image generation unit 47, the composite pixel obtained by combining the pixel of the first correction image H1 and the pixel of the second correction image H2 in the composite image I does not decrease. As a result, in the composite image I, the luminance of the pixels corresponding to the forgery prevention image 12 does not decrease, so that the forgery prevention image 12 can be easily identified.

Note that the composite image generation unit 47 may combine the pixels of the first correction image H1 and the pixels of the second correction image H2 based on the following equation (2).
Im = max (I1, I2) (2)

  In the synthesis method based on Expression (2), when the corresponding pixels in the first correction image H1 and the second correction image H2 are synthesized, the luminance value of the pixel having the higher luminance value of the two pixels is used as the luminance of the synthesis pixel. The composite image I is generated as a value.

(Check processing operation)
When payment processing is performed at the financial institution where the check 2 is brought in, the check 2 is inserted into the transport path 17 of the check processing device 5, and a processing operation start command is transmitted from the control device 7 to the check processing device 5.

  As a result, the check processing device 5 transports the check 2 along the transport path 17, reads the magnetic ink characters 11 printed on the check 2 with the magnetic sensor 15, and acquires magnetic information. Further, the check processing device 5 transmits the acquired magnetic information to the control device 7. Further, the check processing device 5 reads the surface 2 a of the check 2 with the image sensor 16 and sequentially transmits the read information to the control device 7.

  The control device 7 that has received the read information from the check processing device 5 acquires the first surface image G1 (see FIG. 3A) and the second surface image G2 (see FIG. 4A). And the control apparatus 7 produces | generates the 1st correction image H1 which correct | amended the luminance value of the 1st surface image G1 (refer FIG.3 (b)). Moreover, the control apparatus 7 produces | generates a correction function based on the 2nd surface image G2, and produces | generates the 2nd correction image H2 which correct | amended the 2nd surface image G2 with the correction function (refer FIG.4 (b)). Thereafter, the control device 7 generates a composite image I obtained by combining the first correction image H1 and the second correction image H2 (see FIG. 7A), and displays the composite image I on the display 10.

  Here, the operator confirms the authenticity of the check 2 based on the composite image I displayed on the display 10. That is, the operator checks on the display 10 the forgery prevention image 12 appearing in the composite image I. In addition, the operator confirms a front page and the like based on the composite image I and the check 2, and inputs information necessary for settlement to the apparatus main body 8 via the input apparatus 9. When information necessary for settlement is input, settlement processing is performed based on the input information and magnetic information. When the payment is completed, the control device 7 stores and holds the composite image I in association with the payment information including the date of payment, magnetic information, input information, and the like.

  According to this example, as a proof of settlement by the check 2, instead of separately storing the first surface image G1 of the check 2 irradiated with visible light and the second surface image G2 of the check 2 irradiated with ultraviolet light, A composite image I obtained by combining these is stored. Accordingly, it is possible to suppress the data capacity of the image stored as proof of settlement.

  Further, in this example, since the luminance of the pixel corresponding to the printed portion of the UV ink in the composite image I does not decrease compared to the second corrected image H2 before composition, the forgery prevention image 12 is determined in the composite image I. It's easy to do.

  Further, in this example, when the first corrected image H1 is generated, the luminance value of each pixel of the first surface image G1 is reduced at a uniform rate. Therefore, it is easy to generate the first corrected image H1. Further, in this example, the brightness value (brightness value) distribution histogram is compressed by reducing the luminance value of each pixel of the first surface image G1 at a uniform rate, as shown in FIG. The upper limit value of the luminance in the first corrected image H1 is lowered. Accordingly, in the histogram of the brightness (luminance value) distribution in the composite image I, it is possible to determine that the portion exceeding the upper limit value of the luminance in the first corrected image H1 is a portion that does not include information on the first corrected image H1. . That is, in this example, since the luminance value of each pixel of the first surface image G1 is uniformly reduced by 50% and then synthesized with the second corrected image H2, pixels having a luminance value of 128 or more in the synthesized image I are It is information added to the first surface image G1 by synthesizing the second correction image H2 with the first surface image G1, and can be classified as a portion not including the information of the first surface image G1.

(Other embodiments)
In the above example, the check processing device for processing a check is shown as an embodiment of the image processing device, but it can also be applied to an image processing device for processing an image read from a medium printed with UV ink other than a check. is there. In the above example, the first correction image H1 and the second correction image H2 are synthesized in the RGB color space. However, each pixel of the first correction image H1 and the second correction image H2 is set to a value in the HSB color space. You may convert and produce | generate the synthesized image which synthesize | combined these in HSB color space.

  In the check processing system 1, a configuration in which the image acquisition unit 45, the corrected image generation unit 46, and the composite image generation unit 47 in the control device 7 are mounted on the check processing device 5 side may be employed. In this case, the composite image generation unit 47 mounted on the check processing device 5 transmits the composite image I to the control device 7. In this case, the image processing program is operated on the control unit (control device) 31 of the check processing device 5, thereby causing the control unit 31 to change the image acquisition unit 45, the correction image generation unit 46, and the composite image generation unit. Function as 47.

  Note that the check processing device 5 may include a pair of image sensors 16 that face each other across the conveyance path 17 at the image reading position B, and acquire a front image and a back image of the check 2. Further, it is possible to mount an image recognition unit for recognizing characters and the like written on the surface 2a of the check 2 based on the first surface image G1. Further, the check processing system 1 may employ a configuration in which the magnetic information acquisition unit and the image acquisition unit 45 in the check processing device 5 are mounted on the control device 7 side. In this case, the magnetic reading information and the corrected reading information are transmitted from the check processing device 5 to the control device 7.

1. Check processing system 2. Check (medium) 2a Check surface 5. Check processing device 6. Cable 7. Control device (image processing device) 8. Device body , 9 .. Input device, 10 .. Display, 11 .. Magnetic ink character, 12 .. Anti-counterfeit image, 15 .. Magnetic sensor, 16 .. Image sensor, 17 .. Conveyance path, 18. , 19 ·· Conveying roller pair, 20 ·· Conveying motor, 21 ·· Magnetic reading surface, 25 ·· Irradiation part, 25B ·· Blue light emitting element, 25G ·· Green light emitting element, 25R ·· Red light emitting element, 25UV ·・ UV light emitting element 26 ..Reading unit 31 ..Control unit 32 ..Communication unit 33 ..Transport control unit 34 ..Magnetic information acquisition unit 35 ..Image reading unit 41. Device control unit, 42..Image processing unit 43 .. Settlement processing unit 45... Image acquisition unit 46.. Correction image generation unit 47.. Composite image generation unit 51.. First correction image generation unit 52. 53 .. Edge area extraction unit, 54... Correction function generation unit, 55 .. Brightness value corrected image generation unit, 56 .. Edge region, A .. Magnetic reading position, B .. Image reading position, C. Direction, G1 ··· first surface image (first image), G2 ··· second surface image (second image), H1 ··· first corrected image, H2 ··· second corrected image, I ··· composite image, L1 to L3 ・ ・ Average luminance value, T1 to T3 ・ ・ Target luminance value

Claims (11)

The image sensor is driven to obtain a first image obtained by reading the surface of the medium irradiated with the first light, and at the same time, a second image obtained by reading the surface of the medium irradiated with the second light including ultraviolet rays. An image acquisition unit for acquiring
A first corrected image generating unit that generates a first corrected image with reduced brightness of the first image;
A second corrected image generation unit for generating a second corrected image in which the contrast of the second image is increased;
An image processing apparatus comprising: a composite image generation unit configured to generate a composite image obtained by combining the first correction image and the second correction image. In claim 1,
The image processing apparatus according to claim 1, wherein the first corrected image generation unit generates the first corrected image by reducing luminance values of pixels of the first image at a constant rate. In claim 1,
The second corrected image generation unit extracts, as the edge region, an area including an image portion in which the difference in luminance value between adjacent pixels is larger than a preset luminance difference in the second image, A plurality of pixels included in the edge region are divided into a first pixel group and a second pixel group having a lower luminance value than the first pixel group based on the luminance value, and pixels included in the first pixel group A correction function generating unit that generates a correction function for correcting a luminance value of a pixel so that a contrast with a pixel included in the second pixel group is increased; and a luminance value of the pixel for the pixels constituting the second image A luminance value corrected image generation unit that generates the second corrected image obtained by correcting the image with the correction function. In claim 3,
In the synthesized image, a luminance value of a synthesized pixel obtained by synthesizing the pixel of the first corrected image and the pixel of the second corrected image is equal to or higher than the luminance value of the pixel of the first corrected image, and An image processing apparatus having a luminance value equal to or higher than the pixel of the two corrected images. In any one of Claims 1-4,
The image processing apparatus according to claim 1, wherein the first image includes an image based on visible light, and the second image includes an image based on fluorescence from UV ink. A first image obtained by reading the surface of the medium irradiated with the first light by the image sensor is obtained, and a second image obtained by reading the surface of the medium irradiated with the second light including ultraviolet light is obtained.
Generating a first corrected image with reduced brightness of the first image and generating a second corrected image with increased contrast of the second image;
An image processing method, comprising: generating a synthesized image obtained by synthesizing the first corrected image and the second corrected image. In claim 6,
An image processing method, wherein the first corrected image is generated by reducing luminance values of pixels of the first image at a constant rate. In claim 6,
In the second image, an area including an image portion in which a difference in luminance value between adjacent pixels is larger than a preset luminance difference is extracted as an edge area;
The plurality of pixels included in the edge region are divided into a first pixel group and a second pixel group having a lower luminance than the first pixel group based on luminance, and the pixels included in the first pixel group and the pixels Generating a correction function for correcting the luminance value of the pixel so that the contrast with the pixels included in the second pixel group is increased;
An image processing method, wherein the second corrected image is generated by correcting the luminance value of the pixel constituting the second image with the correction function. In claim 8,
The luminance value of the synthesized pixel of the synthesized image obtained by synthesizing the pixel of the first corrected image and the pixel of the second corrected image is equal to or higher than the luminance value of the pixel of the first corrected image, and the second corrected image An image processing method characterized by being equal to or greater than a luminance value of a pixel of an image. In one of claims 6 to 9,
The image processing method, wherein the first image includes an image based on visible light, and the second image includes an image based on fluorescence from UV ink. In a program that runs on the control device that controls the image sensor,
The control device;
The image sensor is driven to acquire a first image obtained by reading the surface of the medium irradiated with the first light, and a second image obtained by reading the surface of the medium irradiated with the second light including ultraviolet rays. An image acquisition unit for acquiring images;
A first corrected image generation unit for generating a first corrected image in which the luminance of the first image is reduced;
A second corrected image generation unit for generating a second corrected image in which the contrast of the second image is increased;
A composite image generation unit that generates a composite image by combining the first correction image and the second correction image;
A program characterized by making it function.