JPH06109653A - Image inspecting apparatus - Google Patents

Abstract

PURPOSE:To inspect even a neutral color with higher reliability. CONSTITUTION:A color system conversion part 3 converts an image of an RGB color system into an image of an HVC color system. The color system conversion part 3 converts a color system in an orthogonal coordinate system into a color system in a polar coordinate system. A checking inspection part 60 checks an HVC color system image to be inspected against a reference image in the HVC color system and performs image inspection. Inspection of yellow for example, which is a neutral color in the RGB color system, can be improved in reliability by comparative inspection in the HVC color system.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image inspection apparatus for inspecting an RGB image, and more particularly, an image inspection capable of inspecting intermediate colors more reliably and improving the inspection reliability of an image to be inspected. Regarding the device.

[0002]

2. Description of the Related Art Defects in printed matter include stains on printing paper,
There are various things such as printing defects. Even if the defective portion is minute, it may cause a problem in the quality of the printed matter. Furthermore, when printed matter such as a rotary printing machine is continuously running at high speed, it is necessary to inspect each printed matter at high speed.

Conventionally, printed matter inspection has been performed manually by various methods. For example, depending on the printing machine and the type of printed matter, the printed matter after printing has been appropriately extracted and visually inspected. Alternatively, in the case of a printed matter that continuously travels at a constant speed, a strobe emits light in synchronization with the traveling speed to visually inspect the printed matter.

In recent years, various techniques for automatically inspecting printed matter have been disclosed.

For example, Japanese Examined Patent Publication No. 1-47823 includes a memory capable of storing image data read from a design of a traveling printed matter at a predetermined time, and the image data read from the memory is used as reference data, and the remaining portion of the traveling printed matter. There is disclosed a technique relating to a printed matter inspection apparatus of a system in which image data read from a pattern is used as inspection data, and whether the printing is good or bad is determined based on a comparison between the reference data and the inspection data. This technique uses a first feature extraction / comparison / determination means for performing a print quality determination by extracting and comparing the features of the reference data and the features of the inspection data for each corresponding pixel unit, and A second characteristic extraction / comparison / determination unit that determines the quality of printing by extracting and comparing the characteristic and the characteristic of the inspection data as the total sum of the pixels in a predetermined range within the same pattern is further used. Third characteristic extraction / comparison / determination means for performing a quality judgment of printing by extracting and comparing the characteristics and the characteristics of the inspection data as the total sum of the pixels arranged on the same straight line in the running direction of the printed matter in the same pattern. Is also used to make a comprehensive determination of the determination results of the first to third feature extraction comparison / determination means to make a final pass / fail determination of the printed matter. Further, in this technique, the comparison means for comparing the difference between the traveling speed of the traveling printed matter at a predetermined time point and the traveling speed of the traveling printed matter at the time of reading the inspection data with a predetermined value is used, and based on the result of the comparison, There is also provided means for newly rewriting the inspection data read from the pattern of the running printed matter at this time as the reference data. According to the technique disclosed in this Japanese Patent Publication No. 1-47823, the accuracy of the quality judgment in the case where the density change such as the pattern of the printed matter is wide range is improved, and the masking function is provided to change the state of the printed matter. It is possible to always obtain a stable operation.

Further, in Japanese Patent Publication No. 1-20477, sample data detected by decomposing a sample pattern of a printed matter into a pixel matrix is compared with sampled data preliminarily extracted from a sampled printed matter and recorded in a memory, pixel by pixel, A technique relating to a pattern inspection method for a printed matter, which determines whether a pattern is good or bad, is disclosed. In this technique, one of the sample data and the sample data is displaced by one pixel in the lateral direction of the printed matter and compared with the other of the two data, and when the two data are closest to each other This is a technique in which the sample data or the sample data is corrected in position in the lateral direction of the printed matter according to the amount of position deviation and then compared with the sample data. According to the technique disclosed in Japanese Patent Publication No. 1-20477, the pattern inspection can be performed with high accuracy by a relatively inexpensive device even if the printed material conveying system is misaligned.

Further, in Japanese Patent Laid-Open No. 62-11152, a detection means for extracting pixel data in a state where the visual fields overlap each other in the direction perpendicular to the running direction of the printed matter and the images overlap each other is used. Then, the data to be inspected is taken in and compared with the reference data. In this comparison, each pixel is compared and then the addition data are compared with each other. According to the technique disclosed in Japanese Patent Laid-Open No. 62-11152, accurate inspection can be performed without being affected by positional displacement, which is inevitable in a printed matter that is running.

Further, conventionally, a red component R (red) and a green component G are used.
When inspecting, for example, an RGB image output by a color camera by (green) and the blue component B (blue), the brightness L is obtained by the following formula, and a monochrome image such as the above Japanese Patent Publication No. 1-47823 is obtained. Inspection is performed by the inspection device.

L = 0.3R + 0.6G + 0.1B (1)

Alternatively, when inspecting such an RGB image, a total of three monochrome image inspection devices such as the above-mentioned Japanese Patent Publication No. 1-47823 are used and a red component R, a green component G and a blue component B are used. After inspecting each independently, the final image inspection is determined based on these inspection results.

[0011]

However, the RGB
The above-described image inspection apparatus using the luminance L for inspecting an image has a problem that it is difficult to identify a defective intermediate color other than red, green, and blue. For example, it was difficult to find a yellow defect. For this reason, it has been practiced to insert a blue optical correction filter into a color camera. The brightness L when the blue correction filter is inserted is as follows.

L = 0.1R + 0.2G + 0.1B (1a)

However, when such a correction filter is used, the amount of light of the image to the color camera is reduced, the amount of information used for the image inspection is reduced, and the reliability of the image inspection is rather lowered. There was an occasion.

Further, in the above-mentioned technique which uses a total of three monochrome image inspection devices for inspecting RGB images, it is similarly difficult to identify image defects of intermediate colors of red, green and blue. There was a problem. or,
There is a problem that the scale of the hardware used is increased or the processing speed is reduced to, for example, 1/3.

The present invention has been made in order to solve the above-mentioned conventional problems, and provides an image inspection apparatus capable of inspecting an intermediate color more reliably and improving the inspection reliability of an image to be inspected. The purpose is to provide.

[0016]

SUMMARY OF THE INVENTION The present invention is an image inspection apparatus for inspecting an RGB image, in which an RGB image to be inspected is
A color system conversion unit for converting into a VC inspection image, and the HV
C inspection image and HVC corresponding to the HVC inspection image
The above-mentioned problem is achieved by providing a collation inspection unit that collates with the reference image.

Further, in the image inspection apparatus, the color system conversion unit causes the resolution of components other than the lightness component V in the HVC inspected image obtained thereby to be lower than the resolution of the lightness component V. As a result, the above-mentioned problems are achieved, the image inspection efficiency is improved, and the hardware amount or inspection processing amount is reduced.

[0018]

A conventional image inspection apparatus for inspecting RGB images is
As described above, even if the red component R, the green component G, and the blue component B are independently inspected using a total of three monochrome image inspection devices, the reliability of the image inspection of the intermediate color is lowered. The inventor and others have confirmed the problem of the occurrence.
This is probably because the information amount of the intermediate color tends to decrease even if the red component R, the green component G, and the blue component B are inspected independently. Also, for example, R to be inspected
This is probably because, when the GB image is an inspection of a printed matter that is supposed to be visually observed, the degree of noticeability of the image defect visually differs depending on the color. Among the above-described intermediate colors, for example, yellow is a color in which an image defect is easily noticeable by visual observation. In order to improve the reliability of the image inspection of the intermediate color such as yellow, the image of the color coordinate system of the orthogonal coordinate system such as the RGB image as described above is temporarily changed to the color coordinate system of the polar coordinate system,
The present invention has been made by finding that the reliability of image inspection can be improved by converting the image into an HVC (hue-value-croma) color system image and inspecting the image, for example.

FIG. 1 is a block diagram showing the gist of the present invention.

As shown in FIG. 1, the main components of the image inspection apparatus of the present invention are a color system conversion unit 30 and a collation inspection unit 60. In addition, for example, a color camera 10 for obtaining an image to be inspected and a reference image memory 48 for obtaining a reference image are provided as needed.

In the present invention, the RGB image of the image to be inspected is input to the color system conversion unit 30 by a predetermined means such as the color camera 10. The color system conversion unit 30
Converts the input RGB inspection image into an HVC inspection image. The present invention does not limit the specific configuration of the color system conversion unit 30, and may be an analog circuit or a digital circuit. Good. Further, the color system conversion unit 30 of the present invention is not limited to the one for converting an RGB image to an HVC image, and it is possible to convert a color image of a rectangular coordinate system to a color system of a polar coordinate system. Any image can be converted as long as it can be converted into a system image.

The collation inspection unit 60 collates the HVC inspected image converted by the color system conversion unit 30 with the HVC reference image stored in the reference image memory 48, for example. Similarly to the color system conversion unit 30, the collation inspection unit 60 is not limited to the HVC color system, and collates an inspected image of the polar coordinate system color system with a reference image. May output any information for obtaining the image inspection result. For example, the collation inspection unit 60 sets the hue component H, the lightness component V, and the saturation component C of the HVC inspection image, and the hue component H, the lightness component V, and the saturation component C of the HVC inspection image, It is also possible to sequentially collate each pixel or each component. Further, in such collation of each component or each pixel, Japanese Patent Application No. 4-155 by the inventors of the present invention, which has not been published at the time of filing the present invention, is filed.
158 and Japanese Patent Application No. 4-223945 may be applied. In addition, the collation checking unit 60 is, for example, an HVC.
The hue component H indicating the hue of the color system, the lightness component V indicating the lightness, and the saturation component C indicating the saturation are not limited to those in which the same components are collated with each other. For example,
In order to inspect the intermediate color more reliably, it is necessary to perform matching with at least a component showing a hue, for example, a hue component H in the HVC color system. Further, as a practical image inspection apparatus, a hue component and a lightness component such as HV
In the C color system, it is desirable to use at least the hue component H and the lightness component V.

According to the configuration of the present invention as described above, the image to be inspected and the reference image can be collated and inspected in the color coordinate system of the polar coordinate system, and the image inspection of the intermediate color can be performed more reliably. be able to.

[0024]

Embodiments of the present invention will be described in detail below with reference to the drawings.

FIG. 2 is a block diagram showing the structure of an image inspection apparatus to which the present invention is applied.

As shown in FIG. 2, the image inspection apparatus of this embodiment mainly includes a color camera 10, a camera control unit 12, a color system conversion unit 30, a selector 40, and
The image memory 46 to be inspected, the reference image memory 48, the collation inspection unit 60, the reference input command input unit 42, and the parameter input unit 50.

The color camera 10 photographs the surface of a printed matter to be inspected in this embodiment and outputs an RGB analog image. In this embodiment, in the image inspection, first, the color camera 10 photographs a reference printed material having no defect to obtain a reference image. After that, in the actual image inspection, the printed matter to be inspected is sequentially photographed to obtain an image to be inspected.

The camera control section 12 converts the RGB analog image output by the color camera 10 into an A / D (analog) image.
to digital) conversion and output RGB digital image. The color system conversion unit 30 converts the RGB digital image output by the camera control unit 12 from the RGB color system to HV.
Convert to C color system and output HVC digital image.

The inspected image memory 46 and the reference image memory 48 each have a storage capacity capable of storing at least one screen image in a two-dimensional frame which is one unit for image inspection of the printed matter 1. is doing.

The reference input command input section 42 inputs whether to select the photographing of the reference image to be performed in the image inspection or the photographing of the inspected image of the actual image inspection. When the reference input command input section 42 receives an input for selecting the reference image shooting, the selector 40 is switched to the reference image memory 48. At this time, the collation checking unit 60 does not operate. On the other hand, if the reference input command input unit 42 receives an input to select the image of the inspection image,
The selector 40 is switched to the inspected image memory 46, and the collation inspection unit 60 performs the collation inspection between the inspected image and the reference image in the HVC color system.

The parameter input section 50 is used to set parameters used in the collation checking section 60. For example, the collation inspection unit 60 inputs an allowable threshold when the image to be inspected is compared with the reference image.

FIG. 3 is a perspective view showing an attached state of the color camera used in this embodiment.

As shown in FIG. 3, the color camera 10 is a color line sensor camera for photographing a print pattern on the surface of the printed matter 1 which is running in the direction of the arrow. The color camera 10 takes a line image of each of the red component R, the green component G, and the blue component B in the width direction of the printed matter 1.

A free roller 3 to which a rotary encoder 24 is attached is provided in the vicinity of a photographing position of the color camera 10. The free roller 3 rotates as the printed matter 1 travels. Further, the rotary encoder 24 generates a pulse signal for each predetermined traveling distance (minute distance) of the printed matter 1.

FIG. 4 is a block diagram showing the configuration of the camera control unit used in this embodiment.

As shown in FIG. 4, the camera control unit 12 mainly includes a total of three A / D conversion circuits 14.
a to 14c and a total of three image buffers 18a to 18c
And a synchronization circuit 18.

The A / D conversion circuit 14a A / D converts the red component R of the RGB analog image output by the color camera 10 and writes it into the R image buffer 18a. The A / D conversion circuit 14b A / D-converts the green component G of the RGB analog image output by the color camera 10 and writes it in the G image buffer 18b. The A / D conversion circuit 14c A / D converts the blue component B of the RGB analog image output by the color camera 10 and writes it in the B image buffer 18c. Each of the image buffers 18a to 18c can store 8-bit image data for one line in the width direction of the printed matter 1. In each of the image buffers 18a to 18c, a double port memory that stores an 8-bit digital value of the brightness of the red component R, the green component G, or the blue component B of each pixel for one line is used as a line buffer. There is.

The synchronization circuit 16 is a timing signal (horizontal synchronization) used when each of the A / D conversion circuits 14a to 14c performs A / D conversion in accordance with a pulse signal output from the rotary encoder 24 as the printed matter 1 travels. Signal) or a timing signal (horizontal synchronizing signal) for writing the A / D converted signal into each of the image buffers 18a to 18c.

FIG. 5 is a block diagram showing the configuration of the color system conversion unit used in this embodiment.

As shown in FIG. 5, the color system conversion unit 30 mainly includes a color system converter 32 and a total of three image buffers, that is, an H image buffer 34a and a V image buffer 34b. And a C image buffer 34c. The image buffer 18a of the camera controller 12
The RGB digital image output from 18c is converted into an HVC color system digital image by the color system converter 32. Also, the HVC converted by the color system converter 32
In the digital image, the hue component H is the H image buffer 34.
a, and the brightness component V is written into the V image buffer 3
4b and the saturation component C is written to the C image buffer 34c.

FIG. 6 shows the RGB used in this embodiment.
It is a diagram showing a color system. On the other hand, FIG. 7 is a diagram showing the HVC color system used in this embodiment.

First, as shown in FIG. 6, the RGB color system used in this embodiment is one of the coordinate system of the orthogonal coordinate system. The RGB color system represents hues, lightnesses, and saturations of various colors by arbitrarily combining three components of a red component R, a green component G, and a blue component B which are orthogonal to each other. . For example, for yellow, the red component R and the green component G can be represented as 1.0, and for example, for white, the red component R, the green component G, and the blue component B can all be represented as 1.0. In FIG. 6, reference numeral BK is black, reference numeral Y is yellow, reference numeral C is cyan, reference numeral M is magenta, and reference numeral W is white.

Next, as shown in FIG. 7, the HVC color system used in this embodiment is one of the polar coordinate system. The HVC color system uses various hues (H:
hue) component, lightness (V: value) component, and saturation (C: c)
It is expressed in a three-dimensional polar coordinate space with the (roma) component. The hue represents tint, the lightness represents lightness, and the saturation represents vividness. For example, for crimson, H = 0 °, V =
It is represented by 0.5 and C = 1. As H increases, it becomes a yellowish color, and conversely, when H decreases, it becomes a bluish color. Also, as V increases, it becomes brighter, and as V decreases, it becomes darker. When C is increased, it becomes vivid, and when C is decreased, it becomes a dark color. Such an HVC color system is closer to human color perception than the RGB color system, and has characteristics more suitable for color image inspection of printed matter and the like on the assumption of human color perception. Can be said.

In the image inspection apparatus of this embodiment, the red component R, the green component G, and the blue component B of the RGB digital image output by the camera control unit 12 and input by the color system conversion unit 30, and The hue component H, the lightness component V, and the saturation component C, which are converted by the color system converter 32 of the color system converter 30 and output from the color system converter 30, are all 8 bits. Is represented by an unsigned binary number, that is, a numerical value of 0-255. Further, the hue component H is represented by a numerical value of 0 to 254 corresponding to 0 to 2π. That is, when the hue component H has an angle of 2π, its value becomes 0. Further, in the hue component H, the value of 255 shows indefinite.

The conversion from the RGB color system to the HVC color system using the generally well-known HVC bihexagonal pyramid color model, which is performed by the color system converter 32 of the present embodiment, will be described below. To do.

First, regarding the red component R, the green component G, and the blue component B, the maximum component Imax, which is the maximum value of these components, and the minimum component of these components, as shown in the following equation, A minimum component Imin that is a value is defined.

Imax = max {R, G, B} (2a) Imin = min {R, G, B} (2b)

The function max {} takes the maximum value among the listed variables. Also, the function min
{} Is a function that takes the minimum value among the listed variables. When the maximum component Imax is obtained by the equation (2a) and the minimum component Imin is obtained by the equation (2b), the lightness component V is obtained by the maximum component Imax and the minimum component Imin as shown in the following equation. You can ask.

V = (Imax + Imin) / 2 (3)

Next, the hue component H and the saturation component C
Can be calculated in the following cases.

(1) First, when the value of the maximum component Imax is equal to the value of the minimum component Imin, the hue component H
And the saturation component C are as follows.

H = 255 (that is, the hue is undefined) (4a) C = 0 (that is, only the gray component) (4b)

(2) On the other hand, when the value of the maximum component Imax is not equal to the value of the minimum component Imin, the saturation component C is obtained by the following equation.

C = Imax-Imin (5)

Here, in obtaining the hue component H, a normalized red component r, a normalized green component g, and a normalized blue component b are defined by the following equation.

R = 255 × (Imax −R) / C (6a) g = 255 × (Imax −G) / C (6b) b = 255 × (Imax −B) / C (6c)

Here, under the condition that the value of the maximum component Imax and the value of the minimum component Imin are different as in the condition (2) above, the hue component H is divided into the following cases. Required.

(2a) When the value of the red component R and the value of the maximum component Imax are equal, the hue component H is obtained by the following equation.

H = (b-g) / 6 (7a)

(2b) When the value of the green component G is equal to the value of the maximum component Imax, the hue component H is obtained by the following equation.

H = (r −b +512) / 6 (7b)

(2c) When the value of the blue component B and the value of the maximum component Imax are equal, the hue component H is obtained by the following equation.

H = (g−r + 1024) / 6 (7c)

If the value of the hue component H obtained by the equations (7a) to (7c) is less than 0, 255 is added. On the other hand, the value of the hue component H is 255
In the above case, 255 is subtracted from the hue component H.
The range of the value of the hue component H thus obtained is set to the range of 0 to 254.

As described above, the color system converter 32
When the conversion from the RGB color system to the HVC color system is performed, the conversion result shows that the hue component H is the H image buffer 3
4a, the lightness component V is written to the V image buffer 34b, and the saturation component C is written to the C image buffer 34c.

FIG. 8 is a block diagram mainly showing the structure of the collation checking unit.

As shown in FIG. 8, the collation checking unit 60 used in this embodiment is mainly composed of an allowable threshold value calculation circuit 64, a threshold value memory 66, and a comparison circuit 70. . The allowable threshold calculation circuit 64 is
It is used in the comparison inspection of the inspection image and the reference image in the comparison circuit 70 according to the reference image written in the reference image memory 46 by using the parameter input by the parameter input unit 50. A threshold value is obtained and written in the threshold value memory 66. The allowable threshold calculation circuit 64
In this case, the technique proposed in Japanese Patent Laid-Open No. 4-155158 is used.

Further, the comparison circuit 70 compares the HVC digital image of the inspection image stored in the inspection image memory 46 and the HVC digital image of the reference image written in the reference image memory 48 with each other. The components are compared and inspected. That is, the hue component H of the image to be inspected and the hue component H of the reference image are compared and inspected. Further, the lightness component V of the inspection image and the lightness component V of the reference image
Compare and inspect. The saturation component C of the image to be inspected and the saturation component C of the reference image are compared and inspected. If there is even one defective inspection result among the comparison inspection results for each component as described above, the corresponding inspected image is regarded as a defective image in this embodiment.

FIG. 9 is a block diagram showing the configuration of the comparison circuit used in this embodiment.

As shown in FIG. 9, the comparison circuit 70 mainly includes an H image comparison inspection circuit 72a, a V image comparison inspection circuit 72b, and a C image comparison inspection circuit 72c.
And an OR circuit 74. The HVC digital image output from the inspected image memory 46 and the HVC digital image output from the reference image memory 48 for each component are input to the image comparison / inspection circuits 72a to 72c for each component. To be done. That is, the H image comparison / inspection circuit 72a includes the inspected image memory 46
And the hue component H from the reference image memory 48 are input. The V image comparison / inspection circuit 72
The brightness component V from the inspected image memory 46 and the brightness component V from the reference image memory 48 are input to b. The saturation component C from the inspected image memory 46 and the saturation component C from the reference image memory 48 are input to the C image comparison / inspection circuit 72c. These image comparison / inspection circuits 72a to 72c respectively compare the input components pixel by pixel using the threshold value stored in the threshold value memory 66 of FIG. 8 not shown in FIG. , Outputs the inspection result of the image to be inspected for the corresponding component.

Each of the comparison inspection circuits 72a to 72c obtains the absolute value of the difference between the pixel value of the reference image and the pixel value of the image to be inspected for each pixel, and the absolute value and the threshold value memory 6
6 is compared with the threshold value stored in 6. Pixels smaller than the threshold value have a value of “0”, pixels larger than the threshold value have a value of “1”, and the inspection result of the corresponding component in the corresponding inspection image is output depending on the number of pixels having the value of “1”. .

The OR circuit 74 outputs the final inspection result of the corresponding inspected image based on the inspection result of each component output from each of the image comparison inspection circuits 72a to 72c. The OR circuit 74 corresponds to the image comparison / inspection circuit 7
If at least one of the inspection results 2a to 72c is defective, the final inspection result of the image to be inspected is determined to be defective.

As described above, according to this embodiment, the RGB analog image of the image to be inspected of the printed matter 1 photographed by the color camera 10 is first converted into the RGB digital image, and further converted into the HVC digital image. Is converted to H
Each component of the VC digital image can be compared and inspected with the reference image. Therefore, according to the present embodiment, it is possible to more reliably inspect the intermediate color. Further, in this embodiment, the color camera 10, the camera control unit 12, and the color system conversion unit 30 include the selector 40.
Can also be used to obtain the HVC digital image of the reference image.

It should be noted that the HV from the RGB color system as described above in the color system converter 32 of the color system conversion unit 30.
At the time of conversion to the C color system, at least one of thinning out the number of pixels of the hue component H and thinning out the number of pixels of the saturation component C may be performed. In this way, it is confirmed that even if the resolution of the hue component H or the saturation component C in the comparative inspection is made lower than the resolution of the lightness component V, the deterioration of the inspection result is not so noticeable. ing. By thinning out the pixels of the hue component H and the number of pixels of the saturation component C, the H image buffer 34a, the C image buffer 34c, the inspected image memory 46, and the reference image memory. The storage capacity of 48 can be reduced. Also, the processing speed of the H image comparison inspection circuit 72a and the C image comparison inspection circuit 72c can be reduced. For example, if the respective processing speeds of the H image comparison inspection circuit 72a and the C image comparison inspection circuit 72c can be halved, for example, one comparison inspection circuit can be used to detect the hue component H. It is possible to alternately perform the comparison inspection and the saturation component C comparison inspection. That is, these H image comparison inspection circuit 72a or C
Either one of the image comparison / inspection circuits 72c can be omitted.

In the conventional image inspection apparatus for performing the comparative inspection in the RGB color system, it was necessary to perform the inspection with the resolution equal to or higher than that of each component. However, as in this embodiment,
The comparative inspection using the HVC color system is characterized in that even if only the lightness component V is inspected at a high resolution, a difference in inspection performance for each color hardly occurs. Further, in the present embodiment, it is easy to detect the change in the hue component H and the change in the saturation component C with the passage of time, and it is possible to better use it to investigate the change in color tone.

In the comparison circuit 70 of this embodiment, the hue component H, the lightness component V and the saturation component C are used.
In order to independently inspect and, the three image comparison / inspection circuits 72a to 72c are used in total. However, as a modified example of this embodiment, the image comparison / inspection circuit 7 is
You may make it 2a-72c one and carry out the comparison inspection of each component sequentially.

Alternatively, in the case of inspecting a large number of inspected images of continuous printed matter of the same pattern, only one of the image comparison / inspection circuits 72a to 72c is provided, and the comparison inspection of one inspected image is performed. First, only the comparison inspection of the hue component H is performed, the comparison inspection of only the lightness component V is performed at the time of the comparison inspection of the next image to be inspected, and the comparison inspection of the next image to be inspected is performed. Alternatively, the same image comparison / inspection circuits 72a to 72c may perform only the comparison inspection of the saturation component C. In this case, the OR circuit 74 is defective in the comparison inspection result of the hue component H, the comparison inspection result of the lightness component V, and the comparison inspection of the saturation component C over three consecutive images to be inspected. You may make it output the logical sum of the inspection result.

[0078]

As described above, according to the present invention, it is possible to obtain an excellent effect that the intermediate color can be inspected more reliably and the reliability of the image to be inspected can be improved. .

[Brief description of drawings]

FIG. 1 is a block diagram showing the gist of the present invention.

FIG. 2 is a block diagram showing an overall configuration of an embodiment of an image inspection apparatus to which the present invention is applied.

FIG. 3 is a perspective view showing a mounted state of the color camera used in the embodiment.

FIG. 4 is a block diagram showing a configuration of a camera control unit used in the embodiment.

FIG. 5 is a block diagram showing a configuration of a color system conversion unit used in the embodiment.

FIG. 6 is a diagram showing an RGB color system used in the embodiment.

FIG. 7 is a diagram showing an HVC color system used in the embodiment.

FIG. 8 is a block diagram showing a configuration of a collation checking unit used in the above embodiment.

FIG. 9 is a block diagram showing a configuration of a comparison circuit used in the embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Printed material 3 ... Free roller 10 ... Color camera 12 ... Camera control part 14a-14c ... A / D conversion circuit 16 ... Synchronous circuit 18a ... R image buffer 18b ... G image buffer 18c ... B image buffer 24 ... Rotary encoder 30 ... Color system converter 32 ... Color system converter 34a ... H image buffer 34b ... V image buffer 34c ... C image buffer 40 ... Selector 42 ... Reference input command input unit 46 ... Inspected image memory 48 ... Reference image memory 50 ... Parameter input unit 60 ... Collation inspection unit 64 ... Allowed threshold value calculation circuit 66 ... Threshold memory 70 ... Comparison circuit 72a ... H image comparison inspection circuit 72b ... V image comparison inspection circuit 72c ... C image comparison inspection circuit 74 ... OR circuit R ... Red Component G ... Green component B ... Blue component H ... Hue component V ... Lightness component C ... Saturation component

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁵ Identification code Internal reference number FI technical display location // B41J 29/46 C 9113-2C

Claims (2)

[Claims] 1. An image inspecting apparatus for inspecting an RGB image, comprising: a color system conversion unit for converting an RGB inspected image into an HVC inspected image; the HVC inspected image; and the HVC inspected image. An image inspection apparatus comprising: a collation inspection unit that collates with an HVC reference image. 2. The resolution of a component other than the lightness component V in the HVC inspected image obtained by the colorimetric system conversion unit is set lower than the resolution of the lightness component V in the colorimetric system conversion unit. An image inspection device characterized in that