JP2988059B2 - Circular container inner surface inspection device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention inspects the inner surface of a circular container such as a beer can conveyed by a conveyor or the like, and detects foreign matter or foreign matter.
The present invention relates to a circular container inner surface inspection device as an image processing device for detecting dust and scratches. In the drawings, the same reference numerals indicate the same or corresponding parts.

[0002]

2. Description of the Related Art FIG. 8 is an explanatory view of a high-brightness portion when an aluminum can container for beer as an example is observed from above, and FIG. 8A is a top (image) view of the can container, and FIG. (B) is a side sectional view. And 102 is a container, 101 is this container 1
A ring-shaped illuminator illuminating 02 from above, 103 is a high-brightness portion at the mouth, and 104 is a high-brightness portion at the bottom. By irradiating the inner surface of the container 102 with a light beam using the ring illuminator 101 in this manner, the mouth and the bottom of the inner surface of the container 1
High luminance portions such as 03 and 104 occur. This is particularly noticeable when the inner surface of the container has a metallic luster such as a can.

FIG. 9B is a top view image of the container 102 (FIG. 1).
3A shows the density change on the scanning line Q-Q1 with respect to 3 (A), and is classified into five regions W1 to W5 according to the characteristic of the density change. The first region W1 is the high-brightness portion 1 of the mouth.
03, the second area W2 is the upper middle part of the side of the container where the density change is relatively small, and the third area W3 is a container darker than the other areas because the light beam by the illumination 101 described in FIG. The fourth region W4 is the bottom high brightness part 104, and the fifth region W5 is the bottom.

Conventionally, a window is provided in each of these areas W1 to W5, and a threshold value for detecting a defect of black stain (black point) or white stain (white point) is set according to the optical characteristics of the area. Was. As a method of detecting a defect, for example, a multi-valued grayscale image signal such as 8 bits obtained by A / D conversion of an analog video signal (analog grayscale image signal) obtained by scanning a target image is converted to a predetermined threshold value. There are known a binarizing method, a differentiating method for extracting the defective signal by differentiating the video signal through a differentiating circuit as shown in FIG. In the case of this differentiation method, a differential signal is also output at the contour of the outer shape of the object, but either one of a positive pulse or a negative pulse is generated by the differentiation at the contour, whereas a positive pulse is generated at a minute defect portion. A defect can be extracted by utilizing the simultaneous occurrence of negative pulses.

That is, a value P (i, j) at a point of interest (coordinate values x = i, y = j) for a signal P (x, y) obtained by differentiating an analog grayscale image signal based on raster scanning,
The value P (i−i) at a point separated from the point of interest by a predetermined minute α pixel and β pixel before and after the x-direction scanning line, respectively.
α, j) and P (i + β, j), P (i, j) −P (i−α, j)> TH1 and P (i + β, j) −P (i, j) )> TH1 (where TH1 is a predetermined threshold value (positive value)) Binarization function value PD for detecting a defect at a point of interest
If (i, j) = 1, this point of interest is regarded as a black level defect point; otherwise, PD (i, j) = 0 and this point of interest is regarded as a normal point.

[0006]

FIG. 11 is a diagram for explaining the problem of the conventional defect detection method based on the differentiation method.
5A shows an example of a density change (analog grayscale image signal) on the scanning line Q-Q1, FIG. 4B shows an analog differential signal corresponding to FIG. 4A, and FIG. 3) shows examples of digital differential signals corresponding to the above. In these figures (A) to (C), BD is a black dirt (valley) defective portion.
That is, in the conventional defect detection method, even if a black level defect such as a BD exists as a signal in a portion having a gradient of density change as shown in FIG. As shown in (1), only the differential signal of a small defective portion is superimposed on the gray-scale differential signal serving as the base due to the time constant of the filter circuit. According to the digital differentiation method, the signal is not stabilized as shown in FIG. In addition, the differential signal of the defective portion is buried in the noise component, and it is extremely difficult to detect the defective signal using a certain threshold value.

FIG. 12 shows an example of a top view of a container 102 having an angular projection 102a at the bottom. On the other hand, FIG.
As described above, the inner surface of the container has many high brightness portions as shown in FIGS. 104-1 and 104-2 due to the shape of the bottom portion and the degree of reflection of light rays on the side portions. Are often mirror-like, and this tendency is remarkable. It is difficult to remove such a high-brightness portion by contriving lighting or the like, and when inspecting the inner surface of the container, it is necessary to employ a defect detection method that essentially responds to uneven illuminance on the inner surface of the container due to the high-brightness portion. However, it has been difficult to detect this defect by a conventional method. Therefore, an object of the present invention is to provide a circular container inner surface inspection apparatus that can detect a defective portion stably and with high accuracy even when there is uneven illuminance on the inner surface of the container.

[0008]

In order to solve the above-mentioned problems, in the present invention, an axially symmetric circular container (such as 102) is formed from the axial direction (via a ring illuminator 101 or the like). After illuminating the inner surface side, image the illumination surface of this circular container from this axial direction via a TV camera,
A circular container inner surface inspection device that analyzes this captured image and inspects black dirt and white dirt on the inner surface of the circular container,
The value of the pixel of interest (such as PO (i, j)) on the same screen scanning line for the gray image signal (such as the inspection area gray image signal 23a) obtained by the image scanning screen scanning
Is the same number as the predetermined number (such as α) before and after the pixel of interest.
(Hereinafter referred to as a front background pixel and a rear background pixel, respectively) separated by a pixel (hereinafter referred to as an α pixel)
(I + α, j), PO (i−α, j), etc.) and the two differences are of the same polarity, and the absolute value of one of the predetermined two differences is a predetermined first value corresponding to the polarity. When the other absolute value of the difference is larger than a predetermined second threshold value (THD, etc.) corresponding to the polarity, the target pixel is determined to be defective. Valley failure determination means (AN in the valley / valley detection binarization circuit 24)
According to the optical characteristics of the inner surface of the circular container based on the illumination and the optical characteristics of the inner surface of the circular container based on the illumination, the inspection area of the image to be subjected to the peak / valley defect determination means is set to (Z1 to Z4, Za to
Zc) and means for varying at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. ,

In particular, the circular container inner surface inspection apparatus according to the first aspect is provided with means for changing the number of the α pixels for one of the inspection areas and repeatedly performing the processing of the peak / valley defect determination means. ,

According to a second aspect of the present invention, in the circular container inner surface inspection device according to the first aspect, the value of the grayscale image signal is a predetermined third threshold value determined for each inspection region. Black level failure determining means (comparator 37-3, etc.) for determining a pixel smaller than the black level threshold value (THB, etc.) as defective;

According to a third aspect of the present invention, in the circular container inner surface inspection device according to the first aspect, the value of the grayscale image signal is a predetermined fourth threshold value determined for each inspection region. It is provided with a white level failure judging means (comparator 37-4, etc.) for judging a pixel larger than the white level threshold value THW, etc.

According to a fourth aspect of the present invention, there is provided a circular container inner surface inspection apparatus which obtains an inverted grayscale image signal by obtaining a one or two's complement of the grayscale image signal, and replaces the signal with the grayscale image signal to obtain the peak / valley defect. Means for providing to the determination means, to detect the pixel of the peak and valley failure without inversion of the polarity,

According to a fifth aspect of the present invention, there is provided the circular container inner surface inspection apparatus, wherein a pixel whose value of the grayscale image signal is smaller than a predetermined third threshold value (eg, a black level threshold value THB) determined for each of the inspection areas. Black level failure determination means (comparator 37-3 or the like) for determining failure,
Or a means for obtaining an inverted gray level image signal by obtaining a two's complement, and providing the inverted gray level image signal to the black level defect determining means in place of the gray level image signal. Should also be detected,

According to a sixth aspect of the present invention, in the circular container inner surface inspection apparatus, the scanning direction of the image is set in a horizontal direction for each of the inspection areas.
Means for selecting a direction (AR or the like) in which a change in the grayscale image signal is the lowest frequency among a plurality of predetermined directions such as a vertical direction and an oblique direction;

According to a seventh aspect of the present invention, in the circular container inner surface inspection apparatus, the value of the pixel value in the section consisting of the first predetermined number of pixels (n or the like) including the pixel on the screen scanning line is determined as the value of the front background pixel. Means for outputting an average value (e.g., a smoothing circuit 41-1) and a section including a predetermined second number of pixels (e.g., n) including the pixel on the screen scanning line as the value of the rear background pixel. Means for outputting an average pixel value (e.g., a smoothing circuit 41-2);

According to an eighth aspect of the present invention, there is provided the circular container inner surface inspection apparatus according to the seventh aspect, wherein the two output means output a median of a pixel value of a corresponding section instead of the average value. It shall be output means.

[0017]

The multi-level grayscale image signal PO based on raster scanning
Point of interest for (x, y) (coordinate values x = i, y = j)
And the value (background pixel value) at two points (background point) separated by a predetermined minute α pixel before and after the point of interest on the x-direction scanning line, respectively, PO (i, j)
PO (i + α, j) and PO (i−α, j) are extracted,
The relationship between these three points becomes a valley in the black level detection, and a density relationship (that is, a density difference between the background pixel value and the pixel value of interest) to be a mountain shape in the white level detection, and the absolute value of the density difference is detected. Is more than a certain threshold value THD, the pixel value of interest PO (i, j) is regarded as a defective pixel.

FIG. 1 is a diagram for explaining the principle of a valley detection binarization method which is the core of the present invention. FIG. 1A shows a scanning line (y = j).
An example of a multi-valued grayscale image signal PO (x, y) on QQ1 is shown. Here, 51 is the point of interest in the non-defective part, and 52 and 53
Are the background part of the non-defective part and the background point of the non-defective part as background points separated by the number of pixels α on the scanning line with respect to the point of interest 51, respectively. Similarly, reference numeral 54 denotes a point of interest in the defective portion, and reference numerals 55 and 56 denote a background point in front of the defective portion and a background point behind the defective portion as background points separated from the point of interest 54 by a number of pixels α before and after the scanning line. .

In the present invention, the coordinates of the point of interest are x = i, y = j
Where PO (i−α, j) −PO (i, j)> THD (1), and PO (i + α, j) −PO (i, j)> THD (2) (Where THD is a predetermined threshold value (positive value)), a binarization function value (referred to as a peak / valley defect binarized image signal) POD ( i,
j) = 1, this point of interest is defined as a valley (defective). In the non-defective part in FIG. 1, the above equation (2) does not hold, and no defect is detected. The above conditions (1) and (2) are satisfied, and a valley defect can be detected. FIG. 1B shows the peak / valley binarized image signal POD (x, j) as a defect determination output corresponding to FIG.
Is shown.

In this manner, the waveform of FIG. 1A is divided into small areas, and the values of the number of pixels α and the threshold value THD in the equations (1) and (2) are appropriately given for each of the small areas. Optimum detection performance can be obtained. Further, in the present invention, in the case of detecting a mountain (defective), the position of the difference term in the equations (1) and (2) is reversed, and PO (i, j) −PO (i−α, j)> THD (1A) and PO (i, j) −PO (i + α, j)> THD (2A), the peak / valley binary image signal POD (i, j) = 1, and this point of interest is regarded as a mountain failure.

[0021]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to FIGS. FIG. 2 is a block diagram of hardware as one embodiment of the present invention. In the figure, PO denotes the above-mentioned multi-valued (for example, 8-bit) gray-scale image signal obtained by AD-converting a video signal obtained by raster-scanning the surface of a TV camera (not shown). , And an address generation circuit 3 for this frame memory. Reference numeral 2 denotes a window memory in which a mask pattern for each window is stored, and 4 denotes an address generation circuit for the window memory. Reference numeral 5E denotes a window gate circuit which masks the multi-valued gray-scale image signal PO or the image signal 1a read from the frame memory 1 with the mask pattern data 2a from the window memory 2, and outputs the image signal PO or 1a only for the designated window area. Is a window gate circuit that passes through.

Reference numerals 6-1 and 6-2 denote image edge detection circuits.
It has a function of detecting an edge of an image, specifically, an outer end (outer peripheral point) and an inner end (inner peripheral point) of a ring-shaped high-brightness portion. After binarization with a predetermined threshold value for circularity inspection, the coordinates of the rising point and the coordinates of the falling point of this binarized signal as an image edge are stored in its own memory. Reference numeral 11 denotes a circuit for performing a circularity test on the coordinate values of the outer peripheral point or the inner peripheral point detected by the image edge detection circuit 6-1. Reference numeral 13 denotes a center position of the actual target image detected by inputting the latest multi-valued gray image signal PO by the image edge detection circuit 6-2 and preset so that a window is generated at a correct position with respect to the target image. This is a circuit for detecting a deviation from the center position of the window being set.

Reference numeral 21 denotes a defect inspection target area for each horizontal scanning line (in other words, a target container) in order to input the multi-valued grayscale image signal 1a passed through the window gate circuit 5E from the frame memory 1 and detect defective pixels. An area detection circuit 22 outputs an area signal 21a as a signal for determining an area divided by an outer shape. The area detection circuit 22 receives the same image signal 1a for the same one horizontal scanning line in synchronization with the area detection circuit 21 and temporarily stores the same. 23 is a line memory which takes an AND condition between the area signal 21a and the corresponding grayscale image signal 22a output from the line memory 22 as an image signal for each horizontal scanning line, and An AND gate that outputs a gray image signal (referred to as an inspection region gray image signal) 23a of only the area. Numeral 24 denotes a peak / valley detection binarization circuit for detecting a defective pixel including the peak / trough defect described in FIG. 1 from the image signal 23a, and is a core part of the present invention.

Next, 9 is an X projection circuit for obtaining an X-direction projection pattern of the target image using the multi-valued image signal PO passed through the window gate circuit 5E.
A Y projection circuit 14 for obtaining a direction projection pattern is a circuit for obtaining only an area of a target container image which is not connected to another container image by using output data of the two projection circuits 9 and 10. Reference numeral 15 denotes a circuit for inputting the judgment results of the high-luminance portion judgment circuit 11 and the peak / valley detection binarization circuit 24 to make a comprehensive judgment. Reference numeral 16 denotes a pass / fail output based on the output judgment signal of the general judgment circuit 15. Output circuit.

FIG. 3 is a block diagram showing an embodiment of the detailed configuration of the peak / valley detection binarization circuit 24 of FIG. However, this configuration shows the case of valley (defective) detection, and in the case of ridge (defective) detection, the polarity of the subtraction of the subtraction circuits 36-1 and 36-2 described later is inverted or the ridge / valley detection is performed. The input image signal 23a to the binarization circuit 24 is inverted. In the latter case, the function of the comparator 37-3 (black level determination by fixed binarization) and the function of the comparator 37-4 (white level determination by fixed binarization) are interchanged.

Next, the function of FIG. 3 will be described. FIG. 3
Implements the principle of FIG. In FIG. 3, 32
-1, 32-2 are input image signals (that is, A
Inspection area grayscale image signal as output of ND gate 23)
This is a + α pixel delay circuit for sequentially adding a delay in the scanning direction by α pixels to 23a. Reference numerals 41-1 and 41-2 denote a smoothing circuit for smoothing the image signal as required to reduce the influence of noise, as will be described later. / Off switch. Here, the smoothing circuit 41-1 is provided corresponding to a front background point detection circuit 33 described later.
-2 is provided corresponding to a rear background point detection circuit 35 also described later. It should be noted that there is no smoothing circuit corresponding to the point of interest detection circuit 34 to be described later. Ability to do so).

The front background point detection circuit 33 receives the inspection area gray image signal 23a as the original input image signal or a circuit for inputting the smoothed signal to detect the front background point, and the point of interest detection circuit 34 detects the + α pixel. A circuit for inputting an output image signal of the delay circuit 32-1 to detect a point of interest, and a rear background point detection circuit 35 receives the output image signal of the + α pixel delay circuit 32-2 or a smoothed signal thereof to input a rear background point. In the delay circuits 32-1 and 32-3.
When the detection circuits 33, 34, and 35 do not use the smoothing circuits 41-1 and 41-2 due to the operation of 2-2 (that is, the smoothing circuits are short-circuited by the switch 42), the pixels described in FIG. Values PO (i + α, j), PO (i, j), P
O (i-α, j) are latched simultaneously.

However, when the smoothing circuits 41-1 and 41-2 are used, the pixel values PO (i + α, j) and PO (i−
α, j) are replaced by the values of the following equations (3) and (4), respectively. PO (i + α, j) = ｛ _{k = 0} Σ ⁿ⁻¹ PO (i + α + k, j)｝ / n (3) PO (i−α, j) = ｛ _{k = 0} Σ ⁿ⁻¹ PO (i-α −k, j)｝ / n (4) That is, the smoothing circuit 41-1 calculates the pixel value P of the front background point in question.
The average of n pixel values on the front side including O (i + α, j) is calculated and replaced with the pixel value of the front background point. Similarly, the smoothing circuit 41-2 performs the processing on the rear background point. The average value of a total of n pixel values on the rear side including the pixel value PO (i-α, j) is calculated and replaced with the pixel value of the rear background point. The reason why the average value centered on the pixel value is not determined here is to prevent the pixel value PO (i, j) at the point of interest from being involved in the calculation of the average value. Also, instead of calculating the average value as in the above equations (3) and (4), the median of the n pixel values (that is, the n
(A value in the center order when the values are arranged in the order of magnitude) may be extracted.

The image data latched by the detection circuits 33, 34 and 35 in FIG.
6-2, and are respectively described in FIG.
The difference is calculated according to the content of the equation (2). The difference is calculated by comparing the peak and valley threshold values T set in the threshold setting circuits 38-1 and 38-2 by the comparators 37-1 and 37-2, respectively.
HD and the comparators 37-1 and 37-2.
The output of the AND gate 39 for obtaining the D condition described above with reference to FIG.
D is obtained. On the other hand, the comparators 37-3 and 37-4 are for detecting a defective pixel having a relatively large area, and the comparator 37-3 outputs the image data of the pixel of interest from the point-of-interest detection circuit 34 which does not input the smoothed image signal. The output is compared with a black level threshold value THB set in the threshold value setting circuit 38-3, and a black level binarized image signal 37B indicating a black level defective pixel is detected and output. Similarly, the comparator 37-4 receives the pixel data output of the pixel of interest, and sets the threshold value setting circuit 3
Compare with the white level threshold value THW set at 8-4,
White level binarized image signal 37W indicating a white level defective pixel
Is detected and output.

The OR gate 40 outputs a peak / valley binarized image signal P as each defective pixel detection signal detected in this manner.
Means for determining the OR condition of the OD, the black level binarized image signal 37B, and the white level binarized image signal 37W, and detecting a black level defective pixel that outputs the defective binarized image signal 40a (comparator 37-3) 3) and means for detecting a white level defective pixel (such as the comparator 37-4) are processed in parallel with peak / valley detection binarization means (such as the AND gate 39) in the example of FIG. Of course, these means are also included in the scope of the present invention even if a method of individually inspecting an image, finally synthesizing each operation, and outputting a judgment is used.

Next, an image scanning method will be described. FIG.
(A) shows the density of the image at a certain cross section QQ1 of the inner surface of the container, and the number of pixels α in the formulas (1) and (2) or the formulas (1A) and (2A) is a defective portion. It is a parameter that gives the frequency of the image signal of the part (in other words, the width of the peak or valley). However, as shown in FIG. 1A, the density image signal at the time of a non-defective product on the inner surface of the container is complicated because it contains various kinds of frequency components. Need to give. However, by devising the scanning direction of the image, it is possible to further reduce the change in density of the background pixel and improve the detection accuracy.

FIG. 4 is an explanatory diagram of one embodiment of such an image scanning method. In FIG. 4A, WB denotes a window for selecting a defect detection target area, and Z1, Z2, Z3,
Z4 is an upper circle area, a lower circle area, a left circle area, and a right circle area, respectively. That is, in FIG. 4, the bottom high-brightness portion 104 where the shading of the container 102 changes a lot is selected in the window WB, and valley detection binarization is attempted. Here, for example, when examining the gray level change in the horizontal scanning direction in the area of the window WB, a portion where the gray level changes at a high frequency, such as HF in FIG. 4C, occurs in the left circular area Z3, which affects the detection sensitivity. Gives
By scanning the left circular area Z3 in FIG. 4A in the direction of the scanning direction arrow AR, a low-frequency shading change is obtained as a background as shown in FIG. Since the frequency is high, the accuracy of detection can be increased.

FIG. 5 is an explanatory view of an embodiment of a simple image scanning method. In the same figure, while the scanning direction is horizontal as indicated by the arrow AR, the scanning area is a window WB
Is divided into three regions of Za, Zb, and Zc. In this case, a threshold value is set for detecting the peaks and valleys of the regions of Za and Zc, and a threshold value is set for detecting the peaks and valleys of the region of Zb. The setting is performed separately, and the optimum detection is performed in accordance with the density of the background. In this case, the defect detection sensitivity in the region Zb is low, but the detection sensitivity in the regions Za and Zc can be increased.

FIG. 6 shows a modified embodiment of FIG. 4. In FIG. 4, the scanning area is equally divided into four fan-shaped areas around the center of the container. In FIG. 6, the scanning area is equally divided into eight fan-shaped areas. FIG. 4 shows an example in which an optimal scanning direction AR is given to an area.
The detection sensitivity can be increased as compared with the case of.

FIG. 7 is an explanatory diagram showing the relationship between the defect detection method according to the present invention and the shape of the defective portion. In FIG. 7A, reference numerals 71 to 73 indicate defective portions appearing in the image of the container 102. FIG. 6B shows the change in shading in the scanning section QA-QA1 of FIG.
The frequency of the shading change differs depending on the direction of the long (short) diameter. Therefore, in the same inspection area, the above-mentioned formula (1),
The defect detection capability can be improved by selecting several types of the amount corresponding to the pixel number α in (2) and repeating the inspection.

On the other hand, FIG. 7C shows the scanning section Q of FIG.
The change in density in B-QB1 is shown. It is assumed that the defective portion 73 on this cross section is large, and the change in the density image signal is low in frequency but sufficiently black with respect to the background. In this case, since the defective portion 73 has a low frequency, it cannot be detected in the valley detection binarization unless the value of the number of pixels α is extremely large, which is not practical. In such a case, the black level threshold value THB is set in the threshold value setting circuit 38-3 in FIG. 3 by using the fixed binarization method described in FIG.
As described above, the defective portion 73 is separated and detected as a black level to supplement the detection capability of valley detection binarization. As a method of determining the black level threshold THB, for example, FIG.
The average of the density data of the pixels on the circumference (illuminance measurement circle) such as 74 in (A) is obtained, and as shown in FIG. And so on.

[0037]

As is apparent from the above description, according to the invention of each claim, the inner side of the axisymmetric circular container is illuminated from the axial direction of the circular container, and then this axis is illuminated via the TV camera. Image the illumination surface of this circular container from the direction,
In a circular container inner surface inspection device that analyzes the captured image to inspect black and white stains on the inner surface of the circular container, there is a case where there is uneven illuminance on the inner surface of the circular container due to a high luminance portion or the like generated by illumination. However, a defective portion can be accurately detected.

[0038]

[0039]

[0040]

[0041]

[0042]

[0043]

[0044]

[0045]

[Brief description of the drawings]

FIG. 1 is a diagram illustrating the principle of a valley detection binarization method according to the present invention.

FIG. 2 is a block diagram showing a hardware configuration as one embodiment of the present invention;

FIG. 3 is a block diagram showing a detailed configuration of a peak / valley detection circuit as one embodiment of the present invention;

FIG. 4 is an explanatory diagram of a first embodiment of a screen scanning method according to the present invention.

FIG. 5 is an explanatory diagram of a second embodiment of the screen scanning method according to the present invention.

FIG. 6 is an explanatory diagram of a third embodiment of the screen scanning method according to the present invention.

FIG. 7 is an explanatory diagram of a relationship between a defect detection method according to the present invention and a shape of a defective portion.

FIG. 8 is a diagram showing a high-luminance portion on the inner surface of a circular container.

FIG. 9 is a diagram showing a relationship between a change in density on the inner surface of a circular container and a conventional window division.

FIG. 10 is a diagram illustrating an example of an analog differentiating circuit;

FIG. 11 is an explanatory diagram of a conventional failure detection method.

FIG. 12 is a diagram showing a high-luminance portion on the inner surface of the circular container when the bottom shape of the circular container is different.

[Explanation of symbols]

 PO Multi-level grayscale image signal 1 Frame memory 1a Frame memory output image signal 2 Window memory 2a Mask pattern data 3 Image address generation circuit 4 Window address generation circuit 5E Window gate circuit 6-1 Image edge detection circuit 6-2 Image edge detection circuit Reference Signs List 9 X projection circuit 10 Y projection circuit 11 High-brightness part determination circuit 13 Position shift amount determination circuit 14 Processing area determination circuit 15 Total determination circuit 16 Output circuit WB window 21 Area detection circuit 22 Line memory 23 AND gate 23a Inspection area grayscale image signal 24 Peak and valley detection binarization circuit 32-1 + α pixel delay circuit 32-2 + α pixel delay circuit 33 Front background point detection circuit 34 Point of interest detection circuit 35 Rear background point detection circuit 36-1 Subtraction circuit 36-2 Subtraction circuit 37-1 Comparator 37 2 Comparator 37-3 Comparator 37-4 Comparator 37B Black level binarized image signal 37W White level binarized image signal 38-1 Threshold setting circuit 38-2 Threshold setting circuit 38-3 Threshold Value setting circuit 38-4 threshold value setting circuit 39 AND gate 40 OR gate 40a defective binarized image signal 51 non-defective part attention point 52 non-defective part front background point 53 non-defective part rear background point 54 defective part notice point 55 defective part front Background point 56 Bad part rear background point Z1 Upper circle area Z2 Lower circle area Z3 Left circle area Z4 Right circle area Za area Zb area Zc area 101 Ring illuminator 102 Container 103 Mouth high brightness section 104 Bottom high brightness section 104-1 Bottom high-luminance part 104-2 Bottom high-luminance part PO (i-α, j) Pixel value PO (i, j) of the background point PO Pixel value PO (i + α, j) of the point of interest Front back Spectral pixel value POD Peak / valley binarized image signal THD Peak / valley threshold THB Black level threshold THW White level threshold

Claims (8)

(57) [Claims] 1. An inner surface side of an axially symmetric circular container is illuminated from the axial direction of the circular container, and an illumination surface of the circular container is imaged from the axial direction via a TV camera. In the circular container inner surface inspection device that analyzes and inspects black stains and white stains on the inner surface of the circular container, the value of the pixel of interest on the same screen scanning line for the grayscale image signal obtained by the screen scanning of the imaging is calculated as Two differences subtracted from the values of background pixels (hereinafter referred to as front background pixels and rear background pixels, respectively) separated by a predetermined same number of pixels (hereinafter referred to as α pixels) before and after the pixel of interest have the same polarity, The predetermined one absolute value of the two differences is larger than a predetermined first threshold value corresponding to the polarity, and the predetermined one absolute value of the difference is a predetermined first threshold value corresponding to the polarity. Than the threshold Peak and valley defect determining means for determining the pixel of interest as defective when the absolute value of the difference is greater than a second predetermined threshold value corresponding to the polarity; and a circular container based on the illumination. Depending on the optical properties of the inner surface,
Means for dividing an inspection area of an image to be subjected to the peak / valley defect determination means; and at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. A circular container inner surface inspection, comprising: means for changing one of the inspection areas; and means for changing the number of the α pixels for one of the inspection areas to repeat the processing of the peak / valley defect determination means. apparatus. 2. A circular container inner surface inspection apparatus according to claim 1, wherein a pixel whose value of the grayscale image signal is smaller than a third threshold value determined for each inspection area is determined to be defective. An inner surface inspection device for a circular container, comprising a level failure judging means. 3. The circular container inner surface inspection apparatus according to claim 1, wherein a pixel whose value of the grayscale image signal is larger than a predetermined fourth threshold value determined for each inspection area is determined to be defective. An inner surface inspection device for a circular container, comprising a level failure judging means. 4. An inner surface side of the circular container is illuminated from the axial direction of the axially symmetric circular container, and an illumination surface of the circular container is imaged from the axial direction via a TV camera. In the circular container inner surface inspection device that analyzes and inspects black stains and white stains on the inner surface of the circular container, the value of the pixel of interest on the same screen scanning line for the grayscale image signal obtained by the screen scanning of the imaging is calculated as Two differences subtracted from the values of background pixels (hereinafter referred to as front background pixels and rear background pixels, respectively) separated by a predetermined same number of pixels (hereinafter referred to as α pixels) before and after the pixel of interest have the same polarity, The predetermined one absolute value of the two differences is larger than a predetermined first threshold value corresponding to the polarity, and the predetermined one absolute value of the difference is a predetermined first threshold value corresponding to the polarity. Than the threshold Peak and valley defect determining means for determining the pixel of interest as defective when the absolute value of the difference is greater than a second predetermined threshold value corresponding to the polarity; and a circular container based on the illumination. Depending on the optical properties of the inner surface,
Means for dividing an inspection area of an image to be subjected to the peak / valley defect determination means; and at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. Means for changing one, means for obtaining a 1 or 2's complement of the grayscale image signal to obtain an inverted grayscale image signal, and providing the signal to the peak / valley defect determining means in place of the grayscale image signal Wherein a pixel having a peak / trough defect is detected without reversing the polarity. 5. An inner surface side of the circular container is illuminated from the axial direction of the axially symmetric circular container, and an illumination surface of the circular container is imaged from the axial direction via a TV camera. In the circular container inner surface inspection device that analyzes and inspects black stains and white stains on the inner surface of the circular container, the value of the pixel of interest on the same screen scanning line for the grayscale image signal obtained by the screen scanning of the imaging is calculated as Two differences subtracted from the values of background pixels (hereinafter referred to as front background pixels and rear background pixels, respectively) separated by a predetermined same number of pixels (hereinafter referred to as α pixels) before and after the pixel of interest have the same polarity, The predetermined one absolute value of the two differences is larger than a predetermined first threshold value corresponding to the polarity, and the predetermined one absolute value of the difference is a predetermined first threshold value corresponding to the polarity. Than the threshold Peak and valley defect determining means for determining the pixel of interest as defective when the absolute value of the difference is greater than a second predetermined threshold value corresponding to the polarity; and a circular container based on the illumination. Depending on the optical properties of the inner surface,
Means for dividing an inspection area of an image to be subjected to the peak / valley defect determination means; and at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. Means for varying one of them; black level failure determination means for determining a pixel whose value of the grayscale image signal is smaller than a predetermined third threshold value determined for each inspection area as defective; Means for obtaining an inverted grayscale image signal by obtaining a 1's or 2's complement of the above, and providing the signal to the black level defect determining means in place of the grayscale image signal. An inner surface inspection device for a circular container, wherein a pixel having a level defect is also detected. 6. An inner surface of the circular container is illuminated from the axial direction of the axially symmetric circular container, and an illumination surface of the circular container is imaged from the axial direction via a TV camera. In the circular container inner surface inspection device that analyzes and inspects black stains and white stains on the inner surface of the circular container, the value of the pixel of interest on the same screen scanning line for the grayscale image signal obtained by the screen scanning of the imaging is calculated as Two differences subtracted from the values of background pixels (hereinafter referred to as front background pixels and rear background pixels, respectively) separated by a predetermined same number of pixels (hereinafter referred to as α pixels) before and after the pixel of interest have the same polarity, The predetermined one absolute value of the two differences is larger than a predetermined first threshold value corresponding to the polarity, and the predetermined one absolute value of the difference is a predetermined first threshold value corresponding to the polarity. Than the threshold Peak and valley defect determining means for determining the pixel of interest as defective when the absolute value of the difference is greater than a second predetermined threshold value corresponding to the polarity; and a circular container based on the illumination. Depending on the optical properties of the inner surface,
Means for dividing an inspection area of an image to be subjected to the peak / valley defect determination means; and at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. A means for changing one of the plurality of predetermined directions such as a horizontal direction, a vertical direction, and an oblique direction as a scanning direction of the image, for each of the inspection areas, a direction in which a change in the grayscale image signal is the lowest frequency. Means for selecting the inner surface of the circular container. 7. An inner surface side of the circular container is illuminated from the axial direction of the axially symmetric circular container, and an illuminated surface of the circular container is imaged from the axial direction via a TV camera. In the circular container inner surface inspection device that analyzes and inspects black stains and white stains on the inner surface of the circular container, the value of the pixel of interest on the same screen scanning line for the grayscale image signal obtained by the screen scanning of the imaging is calculated as Two differences subtracted from the values of background pixels (hereinafter referred to as front background pixels and rear background pixels, respectively) separated by a predetermined same number of pixels (hereinafter referred to as α pixels) before and after the pixel of interest have the same polarity, The predetermined one absolute value of the two differences is larger than a predetermined first threshold value corresponding to the polarity, and the predetermined one absolute value of the difference is a predetermined first threshold value corresponding to the polarity. Than the threshold Peak and valley defect determining means for determining the pixel of interest as defective when the absolute value of the difference is greater than a second predetermined threshold value corresponding to the polarity; and a circular container based on the illumination. Depending on the optical properties of the inner surface,
Means for dividing an inspection area of an image to be subjected to the peak / valley defect determination means; and at least one of the number of α pixels, a first threshold value, and a second threshold value for each of the divided inspection areas. Means for varying one, means for outputting, as the value of the front background pixel, an average value of pixel values in a section having a predetermined first number of pixels including the pixel on the screen scanning line, and Means for outputting, as the value of the background pixel, an average value of the pixel values in a section consisting of the predetermined second number of pixels including the pixel on the screen scanning line. . 8. A circular container inner surface inspection apparatus according to claim 7, wherein said two output means are means for outputting a median of a pixel value of a corresponding section instead of said average value. To inspect the inner surface of a circular container.