JP2000329706A - Mask image automatic generation method and card- inspecting device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To highly maintain a defect detection capacity by detecting the position of a magnetic stripe in the position direction that orthogonally crosses the longitudinal direction of the magnetic stripe and generating a mask image for excluding an area near the position of the magnetic stripe from an inspection target region. SOLUTION: For example, the surface defect of a magnetic card is inspected by first picking up an image by a magnetic card in a step S1 to obtain digital image data. Then, in a step S2, projection data to an coordinates axis in a direction that orthogonally crosses the longitudinal direction of a magnetic stripe is generated and is differentiated to obtain differential projection data, thus detecting the position of the maximum and minimum values, for example, by a predetermined threshold. In a step S3, the pixel value of the magnetic stripe is compared with a pixel value around it, it is judged that a mask image is required if the difference exceeds a given value. Then, in a step S5, a specific mask image based on the position of the magnetic stripe obtained in the step S2 is generated. In a step S6, a defect is detected using the mask image.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention belongs to the technical field of inspecting the appearance of an article. In particular, the present invention relates to a method and an apparatus for inspecting a defect such as a flaw or a dent on the surface of a magnetic card.

[0002]

2. Description of the Related Art Magnetic cards are used in cash cards, credit cards, membership cards, and the like. The magnetic card has a configuration in which plastic sheets are stacked. For example, it consists of a two-layer core printed on the surface of a white plastic sheet (white PVC sheet), and a surface layer of a transparent plastic sheet (transparent PVC sheet) provided on both sides of the core. You. A magnetic stripe (magnetic recording portion) is formed on the surface. Defects such as scratches and dents may be present on the surface of the magnetic card. These defects include those that are originally present in the transparent plastic sheet,
Some are generated in the manufacturing process.

[0003]

It has been proposed to perform an automatic inspection based on a picked-up image so that a defective magnetic card having this defect is not mixed with a product and shipped. However, a magnetic stripe is formed on the surface of the magnetic card, and optical characteristics such as reflectance are different between the magnetic stripe portion and other surface portions of the magnetic card. For this reason, in the conventional automatic inspection, there is a problem that the probability of erroneously determining the boundary as a defect increases when the defect detection capability is increased, and the defect detection capability decreases when the probability of the erroneous determination is suppressed sufficiently low. .

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to maintain a high defect detection capability and prevent an erroneous determination in an automatic inspection.

[0005]

The above objects are achieved by the present invention described below. That is, a method of automatically generating a mask image according to claim 1 of the present invention is a method of automatically generating a mask image indicating an area to be excluded from an inspection target area in an inspection of a magnetic card having a magnetic stripe. Having a step and a mask image generating step, in the magnetic stripe position detecting step, detecting a position of the magnetic stripe in a direction orthogonal to a longitudinal direction of the magnetic stripe from a captured image obtained by imaging a magnetic card, In the mask image generation step, a mask image is generated that excludes the vicinity of the side of the magnetic stripe from the inspection target area of the magnetic card.

According to the present invention, in the magnetic stripe position detecting step, the position of the magnetic stripe in the direction orthogonal to the longitudinal direction of the magnetic stripe is detected from the picked-up image obtained by imaging the magnetic card. Then, a mask image that excludes the vicinity of the side of the magnetic stripe from the inspection target area of the magnetic card is automatically generated. That is, this mask image is a mask image of an area where an erroneous determination is made. Therefore, by using this mask image, in the automatic inspection, the defect detection ability is kept high,
Moreover, erroneous determination can be prevented.

According to a second aspect of the present invention, there is provided a method of automatically generating a mask image according to the first aspect of the present invention, further comprising the step of determining the necessity of a mask image. Determining whether a mask image is necessary or not from the pixel values of the magnetic stripe and the pixel values around the magnetic stripe, and executing the mask image generating process only when it is determined that the mask image is necessary; It is. According to the present invention, when optical characteristics such as reflectance are not so different between the magnetic stripe portion and the other surface portion of the magnetic card,
The mask image is not generated. That is, when the probability of erroneous determination is sufficiently small, the mask image is not used in the automatic inspection. Therefore, the region excluded from the inspection target region can be eliminated.

According to a third aspect of the present invention, there is provided an automatic mask image generating method according to the first or second aspect, wherein the magnetic stripe position detecting step includes a projection data generating step, a differential step, a local maximum and a local minimum. A position detection step, wherein in the projection data generation step, projection data is generated from the captured image to a coordinate axis in a direction orthogonal to a longitudinal direction of the magnetic stripe, and the projection data is differentiated in the differentiation step. Thus, differential projection data is generated, and the positions of the local maximum value and the local minimum value in the differential projection data are detected in the local maximum / minimum position detecting process. According to the present invention, the maximum value and the minimum value in the differential projection data of the captured image on the coordinate axis in the direction orthogonal to the longitudinal direction of the magnetic stripe indicate the positions of the two sides of the magnetic stripe. Therefore, the magnetic stripe position is detected from the positions of the maximum value and the minimum value of the differential projection data.

According to a fourth aspect of the present invention, there is provided an automatic mask image generating method according to the third aspect, wherein the mask image generating step includes a step of determining a position of a maximum value and a minimum value in the differential projection data. And generating a mask image for masking the entire width of the captured image in a direction parallel to the longitudinal direction of the magnetic stripe. According to the present invention, a mask image that excludes the vicinity of the side of the magnetic stripe from the inspection area of the magnetic card is automatically generated from the local maximum value and the local minimum value in the differential projection data.

According to a fifth aspect of the present invention, there is provided an automatic mask image generating method according to any one of the second to fourth aspects, wherein the mask image necessity determining step is performed by using a method for determining whether or not a pixel of the magnetic stripe is required. The value is compared with the pixel values around the magnetic stripe. If there is a difference equal to or more than a predetermined threshold, it is determined that a mask image is necessary. If there is no difference equal to or more than the predetermined threshold, a mask image is unnecessary. This is the process of determining According to the present invention,
When there is a difference between the pixel value of the magnetic stripe and the neighboring pixel values that is equal to or greater than a predetermined threshold value, it is determined that a mask image is necessary.

A card inspection apparatus according to a fifth aspect of the present invention is an inspection apparatus for a magnetic card having a magnetic stripe, comprising an image pickup means and a data processing means, wherein the image pickup means is provided on a surface of the magnetic card. To generate an image signal, and the data processing unit performs a process of excluding the vicinity of the side of the magnetic stripe from the inspection target area of the magnetic card based on the imaging signal, thereby detecting a defect in the inspection target area. Is detected and pass / fail judgment data of the magnetic card is generated.

According to the present invention, the surface of the magnetic card is imaged by the imaging means to generate an imaging signal, and the vicinity of the side of the magnetic stripe is excluded from the inspection target area of the magnetic card based on the imaging signal by the data processing means. The process is performed, a defect in the inspection target area is detected, and data for determining whether the magnetic card is good or bad is generated. In other words, the erroneously determined area is excluded from the inspection target area. Therefore, it is possible to maintain a high defect detection capability and prevent erroneous determination.

[0013]

Next, the present invention will be described with reference to embodiments. FIG. 1 shows an example of a data processing process according to the present invention. FIGS. 2A and 2B show an example of the configuration of an imaging system in the card inspection device of the present invention. 2 (A) and 2 (B), 1 is an area sensor camera, 2 is a resolution lens, 3 is an LED surface light source, 4 is a mirror, 5 is a half mirror, 6 is a power source, 7 is a light source, and 8 is An optical fiber, 9 is a condenser lens, and 11 is a magnetic card.
FIG. 3 shows an example of a magnetic card to be inspected according to the present invention. In FIG. 3, reference numeral 11 denotes a magnetic card, 12 denotes a magnetic stripe, and 13a and 13b denote surfaces of the magnetic card other than the magnetic stripe 12. FIG. 4 is a diagram illustrating a method of detecting the position of a magnetic stripe in the present invention.
Shown in In FIG. 4, reference numeral 21 denotes a captured image, 14 denotes a background of the captured image 21, 22 denotes projection data, and 23 denotes differential projection data. FIG. 5 is a diagram illustrating a method of generating a mask image according to the present invention. In FIG. 5, reference numeral 23 denotes projection data, and 24 denotes a mask image. Hereinafter, the present invention will be described with reference to FIGS.

The magnetic card 11 shown in FIG. 3 is a plastic card having a magnetic stripe (magnetic recording section).
Here, the magnetic card 11 is not limited to a card having only a magnetic stripe. If a contact type or non-contact type IC card also has a magnetic stripe (magnetic recording section), it can be considered that the inspection target is equivalent to the magnetic card 11. Such plastic cards are
For example, JIS-X6301, JIS-X6302,
This card has a standard such as ISO7813. Here, such a card will be described as an inspection target of the surface inspection apparatus.

First, the features of the present invention will be clarified by describing the data processing process in the present invention. Details of other configurations will be described later. First, in step S1 of FIG. 1, the magnetic card 11 (see FIG. 3) is imaged to obtain a captured image 21 (see FIG. 4). This imaging is performed in an imaging system (see FIG. 2), and a captured image 21 (see FIG. 4) is obtained by converting the obtained imaging signal into digital image data. The captured image 21 is stored in a storage device of a data processing unit (described later).

Next, in step S2, the position of the magnetic stripe is detected by the data processing means. The magnetic stripe position detection process includes a projection data generation process, a differentiation process, and a local maximum / minimum position detection process. First, the process of generating projection data in magnetic stripe position detection (S2) will be described. In the projection data generation process, projection data is generated from the captured image 21 to coordinate axes in a direction orthogonal to the longitudinal direction of the magnetic stripe 12 (see FIGS. 3 and 4). As shown in FIG. 4, the vertical direction of the captured image 21 is defined as a y-coordinate axis, and the horizontal direction is defined as an x-coordinate axis. Since the captured image 21 is a matrix having pixel values as elements, it can be expressed as A (i, j). For a specific position (0, j) on the y coordinate axis in the captured image 21, the sum S (j) of the pixel values of all the pixels in the direction of the x coordinate axis is calculated. That is,
S (j) = A (0, j) + A (1, j) + A (2, j)
+... + A (n, j) are calculated. And the sum S
Let (j) be the value (integrated pixel value) at that position on the y coordinate axis. When this calculation is performed for all positions on the y coordinate axis, an integrated pixel value with j as a variable is obtained. This integrated pixel value is the projection data 22.

In the example shown in FIG.
When the position in the y coordinate is increased from the side of the origin (0, 0) of the coordinates of i, that is, when j is increased (note that the direction of increasing j in the normal matrix is opposite), the magnetic field is shifted from the origin to the magnetic field. The projection data 22 is “0” up to the position of the lower boundary of the card 11. When the projection data 22 rises beyond the position of the boundary, the projection data 22 shows a large value Xa. Up to the position of the boundary on the lower side of the magnetic stripe 12, the projection data 22 shows almost the same large value Xa. When the projection data 22 rises beyond the position of the boundary, the projection data 22 shows a small value Xb, and up to the position of the boundary on the upper side of the magnetic stripe 12, the projection data 22 shows almost the same small value Xb.
Is shown. When the projection data 22 rises beyond the position of the boundary, the projection data 22 again shows a large value Xa, and the magnetic card 11
Up to the position of the upper side boundary, the projection data 22 shows almost the same large value. When the data goes up beyond the boundary, the projection data 22 is "0".

As apparent from the above description, in the captured image 21, the pixel value Xb of the magnetic stripe 12 is different from the portions 13 a and 1 of the magnetic card 11 other than the magnetic stripe 12.
3b is smaller than the pixel value Xa. That is, the magnetic stripe 12 is a portion 13 other than the magnetic stripe 12.
The image is captured darker than a and 13b. The pixel value of the background 14 is “0”.

After the description of the projection data generation process in the magnetic stripe position detection process (S2), the differentiation process will be described. In the differentiation process, the projection data 22
Is differentiated to generate differential projection data 23.
As shown in FIG. 4, a difference D (j) is calculated from the projection data S (j) for a specific position (0, j) on the y coordinate axis in the captured image 21. That is, D (j) = S
(J) −S (j + 1) is calculated. And the difference D
Let (j) be the value at that position on the y coordinate axis. This calculation is y
When the processing is performed for all positions on the coordinate axis, a difference in which j is a variable is obtained. This difference is differential projection data 23.

In the example shown in FIG. 4, when the position on the y coordinate is raised from the origin (0, 0) of the coordinates of the differential projection data 23, that is, when j is increased, the boundary of the lower side of the magnetic card 11 from the origin is increased. Up to the position, the differential projection data 23 is “0”. At the position of the boundary, the differential projection data 23 shows a negative value Xc. When the position exceeds the boundary, the projection data 22 is substantially "0" up to the position of the boundary on the lower side of the magnetic stripe 12. Then, at the position of the boundary, the differential projection data 23 shows a positive value Xd. When the position of the magnetic stripe 12 rises beyond the position of the boundary, the projection data 22 reaches the position of the boundary of the upper side of the magnetic stripe 12.
Is almost “0”. Then, at the position of the boundary, the differential projection data 23 again shows a negative value Xe. When the position rises beyond the boundary, the differential projection data 23 is almost “0” up to the position of the boundary on the upper side of the magnetic card 11. Then, at the position of the boundary, the differential projection data 23
Indicates a positive value Xf. When the position rises beyond the boundary position, the projection data 22 reaches the boundary position on the upper side of the captured image 21.
Is almost “0”.

As is apparent from the above description, the differential projection data 23 is clearly different from those around the lower side of the magnetic card 11, the lower side of the magnetic stripe 12, the upper side of the magnetic stripe 12, and the upper side of the magnetic card 11. It has a prominent value, a local maximum and a local minimum. In the example shown in FIG. 4, the protruding portion is shown as if it has a width of one pixel. However, a protruding portion is actually formed in a plurality of adjacent pixels, and the maximum value and the minimum value or similar values are formed. (A value protruding from the periphery) of the differential projection data.

After the description of the differentiation process in the magnetic stripe position detecting process (S2), the process of detecting the maximum and minimum positions will be described. In the process of detecting the maximum and minimum position,
The positions of the local maximum value and the local minimum value in the differential projection data 22 are detected. In the example shown in FIG. 4, the predetermined threshold T1,
The positions of the local maximum value and the local minimum value are detected by T2. That is, the position of the lower side of the magnetic card 11 and the position of the upper side of the magnetic stripe 12 on the y coordinate axis are detected by the value of j that satisfies D (j) <T1. Further, the position of the lower side of the magnetic stripe 12 and the position of the upper side of the magnetic card 11 on the y coordinate axis are detected based on the value of j that satisfies D (j)> T2. As described above, since a protruding portion is usually formed in a plurality of adjacent pixels, D (j) <T1
Alternatively, the value of j that satisfies D (j)> T2 is a plurality of adjacent pixels. Therefore, the detected position has a width. Detecting this maximum and minimum position
The position of the magnetic stripe 12 will be detected.

Returning to FIG. 1, the description will be continued. Next, in the mask image necessity determination process in step S3, the pixel value of the magnetic stripe
The necessity of the mask image is determined from the pixel values of a and 13b. Then, in step S4, the subsequent processing branches according to the determination result. That is, only when it is determined that a mask image is necessary, the mask image generation process of step S5 is executed.

In the mask image necessity determination step of step S3, the pixel value of the magnetic stripe 12 is compared with the pixel values of the periphery 13a and 13b of the magnetic stripe. If it is determined that the mask image is necessary, and if there is no difference equal to or greater than the predetermined threshold, the process may be such that the mask image is unnecessary. The predetermined threshold value in this case is substantially the same as the aforementioned predetermined threshold values T1 and T2. The differential projection data 23 is data having a difference between the projection data 22 as a value. Magnetic stripe 12 and portions 13a and 13b of magnetic card other than magnetic stripe 12
Is a difference value obtained by comparing these pixel values.

The magnitude of the difference between the pixel values is equal to the predetermined threshold T.
If it does not exceed 1, T2, no boundary is detected. Therefore, a mask image is not generated in the mask image generation process of step S5 described below, and the pass / fail judgment using no mask image is performed in the pass / fail judgment process of step S6. On the other hand, when the magnitude of the difference between the pixel values exceeds the above-described predetermined thresholds T1 and T2, a boundary is detected. Therefore, a mask image is generated in the mask image generation process of step S5 described below, and step S6
In the pass / fail judgment process, pass / fail judgment using the mask image is performed.

Next, in the mask image generation process of step S5, a mask image 24 is generated which excludes the vicinity of the side of the magnetic stripe 12 from the inspection target area of the magnetic card 11. This is performed based on the position of the magnetic stripe 12 obtained in step S2. As shown in FIG. 5, the mask image generation process includes, for example, masking the entire width of the captured image 21 in the direction parallel to the longitudinal direction of the magnetic stripe 12 including the positions of the local maximum value and the local minimum value in the differential projection data 23. A mask image 24 is generated.

As shown in FIG. 5, the position of the magnetic stripe 12 obtained in step S2 is determined by, for example, applying the threshold values T1 and T2 to the differential projection data 23 to determine the position of the maximum value and the position of the minimum value. It is what I asked for. The position of the maximum value and the position of the minimum value have a width as described above. This width can be used as it is in the mask image 24 for masking. Further, this width can be enlarged or reduced to be a width for performing masking. The masking width in the mask image 24 depends on the magnetic stripe 12 and the other surface 1 of the magnetic card.
The boundary is determined based on the implementation data and the like so that the boundary between 3a and 13b is not erroneously determined as a defect and has a minimum necessary width.

Next, in the pass / fail judgment process of step S6, the mask image 24
Then, a process of excluding a portion to be masked is performed to detect a defect in the inspection target area, and pass / fail judgment data of the magnetic card 11 is generated. A specific example of this pass / fail determination method will be described later. Next, in step S7, it is determined whether to continue or end the magnetic card inspection process. If it is determined that the process is to be ended, the magnetic card inspection is ended. If it is determined that the process is to be continued, the process returns to step S1 to repeat the above process.

This is the end of the description of the data processing steps in the present invention, which is shown in the flowchart in FIG. Next, other configurations not described in detail above will be described. In FIG. 2A, the area sensor camera 1 has a CC constituted by light receiving elements (pixels) arranged two-dimensionally.
This is an imaging unit having an area sensor such as a D (charge coupled device). The area sensor camera 1 receives a light beam passing through the half mirror 5 by the imaging lens 2 and images the magnetic card 11 which is a magnetic card. The optical image formed on the area sensor by the imaging lens 2 is converted into a time-series electric signal and output as an imaging signal.

As the imaging lens 2, a lens having a narrow viewing angle (that is, a long focal length) is used. Since the viewing angle of the imaging lens 2 is narrow, it is possible to perform imaging using light beams that have the same conditions in which the directions of reflection from the surface of the magnetic card 11 are almost the same. Moreover, the imaging range that satisfies the condition is wide. Therefore, under the condition almost uniform over the entire range of the surface of the magnetic card 11 and matching the defect detection,
For example, imaging can be performed under conditions that emphasize flaws and dents.

Light emitted from a halogen lamp, a metal halide lamp, a xenon lamp, or the like can be used as the light source 6. In the light source 7, the emitted light is condensed on one end face of the optical fiber 8 by a condenser lens, a reflecting mirror, or the like, enters the inside of the optical fiber 8, travels there, and radiates from the other end face of the optical fiber 8. Is done. The emitted light is condensed by the condenser lens 9 to form substantially parallel light. The parallel light is converted by a mirror 4 into a half mirror 5
Change direction towards. The parallel light changes its direction toward the magnetic card 11 by the half mirror 5 and irradiates the magnetic card 11.

As shown in FIG. 2A, the mirror 4 reflects the parallel light formed by the condenser lens 9 in the direction of the half mirror 5. The half mirror 5 is an optical axis conversion unit. The half mirror 5 makes the optical axis of the parallel light coincide with that of the area sensor camera 1 on the magnetic card 11 side and separates it on the opposite side. Due to the half mirror 5, there are few restrictions on the design and installation of an imaging system including the area sensor camera 1 and the light source 7, and the optical axis of illumination on the surface of the magnetic card 11 is the optical axis of imaging by the area sensor camera 1. Can be matched with

Next, the imaging system shown in FIG. 2B will be described. The area sensor camera 1 is a CCD (charge coupl) composed of light receiving elements (pixels) arranged two-dimensionally.
ed device). The area sensor camera 1 receives a light beam passing through the half mirror 5, and receives a light beam passing through the half mirror 5 so that the plastic card 1 is a flat article.
1 is imaged. The optical image formed on the area sensor by the imaging is converted into a time-series electrical signal and output as an imaging signal.

The power source 6 is a light emitting diode (LED)
(Emitting diode).
Normally, a DC stabilized power supply is used as the power supply 6 so that a stable predetermined luminance can be obtained.

The LED surface light source 3 is a surface light source having a plurality of light emitting diodes arranged two-dimensionally. As the light emitting diode, those having a light emission color such as red light emission, green light emission, and blue light emission are known. In the present invention,
There is no particular limitation on the emission color. The LED surface light source 3 can be constituted by a light-emitting diode of any one of these single emission colors or a combination of these emission colors. Some semiconductor area sensors have strong sensitivity in the red wavelength band. In general, by matching the sensitivity of the area sensor with the emission color, the utilization efficiency of the illumination light can be increased.

The LED surface light source 3 is provided with a plurality of light emitting diodes as point light sources, and emits light from a region having a two-dimensional spread. Therefore, the LED surface light source 3 has characteristics as a diffusion light source not only when a diffusion plate is provided on the front surface of the LED surface light source 3 but also when no diffusion plate is provided. In addition, a general light emitting diode has a light emitting surface that acts as a lens, and the intensity of light emission according to a direction has a designed predetermined directivity. The property of the LED surface light source 3 using the light emitting diode having strong directivity is weakened as a diffusion light source, and the property as a non-diffusion light source (light beam) having strong directivity is enhanced. By appropriately selecting the directivity of such a light emitting diode so as to conform to the configuration of the entire imaging system, it is possible to obtain an imaging signal in which flaws and dents are emphasized in the configuration of the imaging system shown in FIG. it can.

As shown in FIG. 2B, the mirror 4 is LE
The light emitted from the D-plane light source 3 is reflected in the direction of the half mirror 5. The half mirror 5 is an optical axis conversion unit. The half mirror 5 aligns the optical axes of the area sensor camera 1 and the LED surface light source 3 on the plastic card 11 side and separates them on the opposite side. This half mirror 5
Accordingly, there are few restrictions on the design and installation of the area sensor camera 1 and the LED surface light source 3, and the optical axis of illumination on the surface of the plastic card 11 can be made to coincide with the optical axis of imaging by the area sensor camera 1.

Next, an image pickup signal and data processing in the surface inspection apparatus of the present invention will be described. An optical image of the magnetic card 11 formed on the area sensor camera 1 is output from the area sensor camera 1 as an imaging signal. The optical image coupled to the area sensor is output as an image signal of one line sequentially scanned with respect to the outputs of the light receiving elements arranged in the horizontal direction, and further sequentially scans the outputs of the light receiving elements arranged in each row in the vertical direction, Output is performed as the imaging signals of all the rows. This imaging signal is converted into digital data by A / D conversion means. The scanning of the output of the light receiving element is performed in synchronization with the clock signal.
By performing the / D conversion in synchronization with the clock signal, digital data including pixel values corresponding to the light receiving elements can be obtained.

In the process of converting the image signal into digital data by the A / D converter, the relationship between the level of the image signal and the data is defined. For example, when the voltage value of the imaging signal is “0” volt, the data is “0”, and when the voltage value of the imaging signal is “1” volt, the data is “255”.
It is defined that the conversion is performed linearly during that time. This regulation includes imaging conditions such as illumination, an output amplifier of the imaging means,
The conversion characteristics of the / D conversion means and the like are comprehensively determined and determined so as to be suitable for the surface inspection. As a simple determination method, for example, 8-bit data is used so that the data of the background portion (see FIG. 4) of the captured image 21 becomes “0” and the card portion (see FIG. 4) becomes “255”. Stipulate.

Next, a process for detecting the presence or absence of a defect in a captured image as shown in FIG. 4 and a process for determining whether the magnetic card 11 is good (corresponding to step S6 in FIG. 1) will be described. As described above, the detection of the presence or absence of a defect is performed on an inspection target area that is not set as a mask target area by the mask image 24. All the processing steps of the magnetic card inspection shown in FIG. 1 including this processing step are performed by data processing means (not shown). The data processing means can be constituted by hardware and software of a data processing device such as a microcomputer and a personal computer. As a method of detecting a defect as described above, a method that does not use the data of the reference image,
The method using the data of the reference image can be applied in the present invention.

First, an example of a method not using reference image data (first detection method) will be described. First, in a first step S11 (not shown; the same applies hereinafter),
Differentiation processing is performed on the inspection target image to obtain a differential inspection target image. In this differentiation process, the edge portion of the defect,
A fine defect is emphasized, and a noise component (level change) in a relatively large range due to illumination unevenness, characteristics of an imaging lens, and the like is removed. That is, in the differential inspection target image, the edge portion of the defect and the small defect are emphasized, and the data has a finite value, and the data of the other portions is substantially “0”.

Next, in a second step S12, the differential inspection target image is binarized using a predetermined threshold value, and pixels exceeding the predetermined threshold value and pixels below the predetermined threshold value are classified. A pixel exceeding the predetermined threshold is a pixel at a defective portion, which has the same meaning as that of extracting a defect. Next, in a third step S13, the quality of the magnetic card 11 of the inspection target image is determined based on the number of pixels at the defective portion, or the size and number of defects calculated based on the pixels at the defective portion. Is determined.

Next, an example of a method using the data of the reference image (second detection method) will be described. First, in a first step S21 (not shown; the same applies hereinafter) before performing a normal inspection, a magnetic card 11 serving as a reference for a non-defective product having no defect is imaged to obtain a reference image. This reference image includes noise components (level changes) related to imaging conditions such as uneven illumination, characteristics of the imaging lens, and the like. In the case where the influence of a print pattern existing on the magnetic card 11 appears in the image data, the influence is a noise component and is included.

Next, in a second step S22, a difference or an absolute value of the difference is calculated for each corresponding pixel between the inspection object image and the reference image to obtain a difference image. This difference image is an image of a difference between the inspection target image and the reference image. That is, the image indicates a defect that exists in the inspection target image but does not exist in the reference image. Next, in a third step S23, the difference image is binarized using a predetermined threshold value, and pixels exceeding the predetermined threshold value and pixels below the predetermined threshold value are classified. A pixel exceeding the predetermined threshold is a pixel at a defective portion, which has the same meaning as that of extracting a defect. Next, in a fourth step S24, the quality of the magnetic card 11 in the inspection target image is determined based on the number of pixels at the defective portion, or the size and number of defects calculated based on the pixels at the defective portion. Is determined.

[0045]

As described above, according to the mask image automatic generation method according to the first aspect of the present invention, by using this mask image, in the automatic inspection, the defect detection ability can be maintained high and the erroneous judgment can be made. Can be prevented. Further, according to the mask image automatic generation method of the second aspect of the present invention, it is possible to eliminate a region excluded from the inspection target region. According to the mask image automatic generation method according to the third aspect of the present invention, the position of the magnetic stripe is detected from the positions of the maximum value and the minimum value of the differential projection data. Further, according to the mask image automatic generation method according to claim 4 of the present invention, a mask image for excluding the vicinity of the side of the magnetic stripe from the inspection target area of the magnetic card is automatically generated from the maximum value and the minimum value in the differential projection data. Is done. According to the mask image automatic generation method according to the fifth aspect of the present invention, it is determined that a mask image is necessary when there is a difference between the pixel value of the magnetic stripe and the peripheral pixel value that is equal to or greater than a predetermined threshold. Further, according to the card inspection apparatus of the sixth aspect of the present invention, it is possible to maintain a high defect detection ability and prevent erroneous determination.

[Brief description of the drawings]

FIG. 1 is a diagram showing an example of a data processing process according to the present invention.

FIG. 2 is a diagram illustrating an example of a configuration of an imaging system in the card inspection device of the present invention.

FIG. 3 is a diagram showing an example of a magnetic card to be inspected in the present invention.

FIG. 4 is an explanatory diagram showing a method for detecting the position of a magnetic stripe in the present invention.

FIG. 5 is an explanatory diagram showing a method of generating a mask image in the present invention.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 Area sensor camera 2 Resolution lens 3 LED surface light source 4 Mirror 5 Half mirror 6 Power supply 7 Light source 8 Optical fiber 9 Condensing lens 11 Magnetic card 12 Magnetic stripes 13a, 13b Surface of magnetic card other than magnetic stripe 12 21 Captured image 14 Background 22 of captured image 21 Projection data 23 Differential projection data 24 Mask image

 ────────────────────────────────────────────────── ─── Continuing from the front page (72) Inventor Yasutaka Fujii 1-1-1 Ichigaya-Kaga-cho, Shinjuku-ku, Tokyo F-term in Dai Nippon Printing Co., Ltd. (reference) 2F065 AA03 AA49 AA61 BB01 BB17 CC00 FF01 FF04 GG02 GG03 GG07 GG15 HH03 JJ03 JJ07 JJ26 LL02 LL49 QQ03 QQ04 QQ13 QQ24 QQ25 QQ27 QQ29 QQ37 RR06 RR09 SS04 2G051 AA73 AA90 AB02 BA01 BA20 BB17 CA03 CA04 EA08 EA11 EA12 EA14 EB01 DC02 EB01 DC02 ED02

Claims (6)

[Claims] 1. A method of automatically generating a mask image indicating an area to be excluded from an inspection target area in an inspection of a magnetic card having a magnetic stripe, comprising: a magnetic stripe position detecting step and a mask image generating step. In a magnetic stripe position detecting step, a position of the magnetic stripe in a direction orthogonal to a longitudinal direction of the magnetic stripe is detected from a captured image obtained by imaging the magnetic card, and a side of the magnetic stripe is detected in the mask image generating step. Generating a mask image that excludes the vicinity of the above from the inspection target area of the magnetic card. 2. The mask image automatic generation method according to claim 1, further comprising a mask image necessity judging step, wherein in the mask image necessity judging step, a pixel value of the magnetic stripe and a pixel around the magnetic stripe are determined. A mask image generation step, wherein the necessity / non-necessity of the mask image is determined from the value and the mask image generation step is executed only when the mask image is determined to be necessary. 3. The mask image automatic generation method according to claim 1, wherein the magnetic stripe position detecting step includes a projection data generating step, a differentiation step, and a local maximum / minimum position detecting step. Generating projection data on the coordinate axis in a direction orthogonal to the longitudinal direction of the magnetic stripe from the captured image; generating differential projection data by differentiating the projection data in the differentiation process; Detecting a position of a local maximum value and a local minimum value in differential projection data in a process. 4. The method of automatically generating a mask image according to claim 3, wherein the mask image generating step includes a position of a local maximum value and a local minimum value in the differential projection data, and is performed in a direction parallel to a longitudinal direction of the magnetic stripe. A method for automatically generating a mask image, comprising generating a mask image for performing a mask for the entire width of a captured image. 5. The mask image automatic generation method according to claim 2, wherein in the mask image necessity determining step, a pixel value of the magnetic stripe and a pixel value around the magnetic stripe are compared. A step of determining that a mask image is necessary when there is a difference equal to or more than a predetermined threshold, and determining that a mask image is unnecessary when there is no difference equal to or more than the predetermined threshold. Generation method. 6. An inspection apparatus for a magnetic card having a magnetic stripe, comprising: an image pickup means and a data processing means, wherein the image pickup means picks up an image of a surface of the magnetic card to generate an image pickup signal; The processing means performs a process of excluding the vicinity of the side of the magnetic stripe from the inspection target area of the magnetic card based on the imaging signal, detects a defect in the inspection target area, and outputs pass / fail judgment data of the magnetic card. Generating a card inspection device.