JPH0587738A - Device for inspecting internal surface of circular container - Google Patents

Abstract

PURPOSE:To eliminate such a trouble encountered in the course of the conventional internal surface inspection on beer tins that the inspection takes time, because the inspection only detects black and white contaminations by a differentiating method, etc., and respectively sets thresholds to numerous window areas into which an objective picture is divided. CONSTITUTION:Since, in order to inspect the depression, distortion, and contamination of the high luminance section of a beer tin, a picture edge detection circuit 6 and high luminance section discrimination circuit 11 which inspect the circularity of the outer and inner peripheries of a high luminance section on the internal surface of a beer tin are provided in addition to a defect detection circuit 7 and defect detection discriminating circuit 12 which inspect white contamination, the number of window areas is reduced. Prior to the circularity inspection, the position of the tin is specified by finding the mean value of mid-point coordinates between the fist rising point and last falling point on the binarized picture scanning line of the high luminance section at the mouth of the tin through the circuit 6 and connecting points are found by finding the vertical projection of the binarized picture of the high luminance section in the container connecting direction through a projection circuit 9 or 10 and searching the differential value of projection from the inside to the outside of the container through a processing area decision circuit 14.

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 on a conveyor or the like, and
The present invention relates to a circular container inner surface inspection device as an image processing device for detecting dust, scratches, and the like. In the following figures, the same reference numerals indicate the same or corresponding parts.

[0002]

2. Description of the Related Art FIG. 12 is an explanatory view of a high-intensity part when an aluminum can container for beer is observed from above, as an example. FIG. 12A is a top view (image) of the can container and FIG. ) Is a side sectional view. 102 is a container, 101 is this container 1
A ring-shaped illuminator that illuminates 02 from above, 103 is a high-intensity part at the mouth, and 104 is a high-intensity part at the bottom. By thus irradiating the inner surface of the container 102 with light rays by using the ring illuminator 101, the mouth and the bottom of the container are respectively separated by one.
High brightness areas such as 03 and 104 occur. This is particularly noticeable when the inside of the container has a metallic luster such as a can.

FIG. 13B shows changes in density on the scanning line Q-Q1 with respect to the top image of the container 102 (FIG. 13A).
It is divided into two areas. The first region W1 is the mouth high-intensity part 103, the second region W2 is the middle part on the side surface of the container where the concentration change is relatively small, and the third region W3 is the light beam from the illumination 101 described in FIG. Since it does not reach so much, it is a lower part of the side surface of the container that is darker than other areas, the fourth area W4 is the bottom high-intensity part 104, and the fifth area 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 spot) or white stain (white spot) is set according to the optical characteristics of the area. Was. As a method of detecting a defect, for example, an 8-bit multi-value grayscale image signal obtained by A / D conversion of an analog video signal (analog grayscale image signal) obtained by scanning a target image is set at a predetermined threshold value. A binarization method and a differentiation method of differentiating the video signal to extract a defect signal are known. For this differentiation method,
A differential signal is also generated in the contour portion of the outer shape of the object, but in the contour portion, either a positive direction pulse or a negative direction pulse is generated by differentiation, whereas a minute defect portion simultaneously generates a positive direction pulse and a negative direction pulse. It is possible to extract the defective portion by utilizing this.

That is, a value P (i, j) at a target point (coordinate value x = i, y = j) of a signal P (x, y) obtained by differentiating an analog grayscale image signal based on raster scanning,
The value P (i- at a point separated by a predetermined minute α pixel and β pixel from the point of interest on the x-direction scanning line, respectively.
between α, j) and P (i + β, j), P (i, j) −
P (i-α, j)> TH1 and P (i +
If there is a relation of β, j) -P (i, j)> TH1,
(However, TH1 is a predetermined threshold value (positive value)) Binarization function value PD (i, j) for defect detection at the point of interest
= 1, this point of interest is a black level defect point, and in other cases, PD (i, j) = 0 is set and this point of interest is a normal point.

[0006]

However, in the above-described defect discrimination method, the optimum value of the threshold value TH1 to be given changes depending on the optical characteristics of the inner surface of the container. Therefore, in the conventional method, many (five in this case) concentric windows like the windows W1 to W5 in FIG. 13 are required, and at the same time, a different threshold TH1 is set for each window.
(Furthermore, it is necessary to give the coordinate values α and β), and when raster scanning is used, a wasteful scanning time is long, which is an obstacle to speeding up defect inspection. Therefore, an object of the present invention is to provide a circular container inner surface inspection device that can solve this problem.

[0007]

In order to solve the above-mentioned problems, the circular container inner surface inspection apparatus according to claim 1 has an axisymmetric circular container (102) which can be connected to each other in a predetermined direction (horizontal direction or the like). Etc.) from the axial direction (ring illuminator 101
After illuminating the inner surface of this circular container,
The illumination surface of the circular container is imaged from this axial direction via a V camera, and the imaged image is analyzed through defect inspection means (defect detection circuit 7, defect detection determination circuit 12, etc.) to analyze the inner surface of the circular container. In a circular container inner surface inspection device for inspecting black stains and white stains, an image signal (multi-value grayscale image signal PO or the like) obtained by the screen scanning of the imaging is stored in the mouth high brightness portion (103 or the like) of the circular container. A unit (Y projection circuit 10 or the like) for binarizing so as to obtain a binary image and projecting the binarized image signal in a direction (Y direction or the like) perpendicular to the connecting direction, and a projection pixel amount based on this projection. To obtain a difference projection pixel amount, check the difference projection pixel amount from the inner side of the circular container toward the outer side (mouth side), and check that the pixel amount becomes negative first (decrease start point PD, etc.). ) This difference within the interval up to A point where the amount of shadow pixels exceeds a predetermined threshold value (maximum difference projection point ΔPM, etc.) is detected, and a coordinate value obtained by adding a predetermined correction value (β, etc.) to the coordinate value of this detection point is used for the connection. It is assumed that a means for separating the areas (processing area determining circuit 14 etc.) is provided.

[0008]

[Function] By cutting out the high-intensity part by binarization and inspecting the circularity of this cut-out pattern, it is possible to detect not only deformation of the container, dents, etc., but also black spots in the high-intensity part such as dust adhering to the container. To improve the accuracy of defect detection. Then, in the same window area, this circularity inspection and the inspection of black dots and white dots by the conventional defect inspection means are executed in parallel. This reduces the number of window areas and speeds up the processing. In addition, prior to this circularity inspection, the position of the circular container should be specified so that the first rising point on the same scanning line of the binarized image signal in the region of the high brightness portion of the mouth of the container which is not affected by the container connection. The average value of the midpoint coordinates of the last falling point is used. Further, in order to separate the inspection area from the area of the connected container, the projection amount of the binary image of the mouth high-intensity part in the direction perpendicular to the connecting direction of the container is obtained, and the difference value of the projection amount is calculated as the inside of the container. From outside to the outside to detect contact points.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT An embodiment of the present invention will be described below with reference to FIGS. FIG. 1 is a block diagram of hardware as an embodiment of the present invention. In the figure, PO is a multi-valued (e.g., 8-bit) grayscale image signal obtained by AD-converting a video signal obtained by raster-scanning the screen of a TV camera (not shown), and 1 is the multivalued grayscale image signal PO. The frame memory 3 for storing multi-valued screen data is an address generation circuit for this frame memory. Reference numeral 2 is a window memory in which a mask pattern for each window is stored, and 4 is an address generation circuit for this window memory. A window gate circuit 5 masks the multi-value grayscale 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 to obtain the image signal PO or 1a only in the designated window region. It is a circuit that passes.

Reference numeral 18 denotes an image input changeover switch for switching and selecting the multivalued grayscale image signal PO or the frame memory image signal 1a. This switch 18 operates the latest multivalued value in order to operate a position shift amount determination circuit 13 described later. It has a role of supplying the grayscale image signal PO to the image edge detection circuit 6 in parallel with the input of the signal PO to the frame memory 1. Reference numeral 17 denotes an image output changeover switch, which is a switch for giving the output image signal of the image input changeover switch 18 that has passed through the window gate circuit 5 to the image edge detection circuit 6 or the defect detection circuit 7. The image edge detection circuit 6 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. The binarized image signal is binarized with a predetermined threshold value for position detection and circularity inspection of the target image, and the coordinates of the rising and falling points of this binarized signal as image edges are calculated. Internal memory (6A described later in FIG. 8)
~ 6D). Reference numeral 11 denotes the image edge detection circuit 6
This is a circuit for inspecting the circularity of the coordinate value of the outer peripheral point or the inner peripheral point detected by the method as described later.

Numeral 13 is preset with the position of the center of the actual target image detected by the image edge detection circuit 6 by inputting the latest multi-valued image signal PO so that a window is generated at the correct position with respect to the target image. This is a circuit for detecting a deviation from the center position of the window being displayed. Reference numeral 7 is a defect detection circuit that detects defective points (black spots, white spots, etc.) by the differentiation method described in the prior art and counts the area, and 12 is this circuit 7.
Is a defect detection determination circuit that compares the detection result of 1 with the set value to determine acceptability. Reference numeral 9 is an X projection circuit that obtains the X-direction projection pattern of the target image using the multi-valued image signal PO that has passed through the window gate circuit 5. Reference numeral 10 is a Y projection circuit that similarly obtains the Y-direction projection pattern of the target image. This is a circuit that uses the output data of one projection circuit 9 and 10 to obtain only the region of the target container image that is not connected to another container image. Further, 15 is a circuit for inputting the judgment results of the high-luminance part judgment circuit 11 and the defect detection judgment circuit 12 to make a comprehensive judgment, and 16 is an output circuit for outputting a pass / fail according to the output judgment signal of the comprehensive judgment circuit 15. ..

First, the position detecting operation of the target image by the image edge detecting circuit 6 will be described. FIG. 14 is an image in which the high-luminance portion is binarized by the image edge detection circuit 6. In the figure, 201 is a mask pattern, and 102-2 is a container connected to the target container 102 (102-1). That is, in this case, it is assumed that the bottom high-intensity portion 104 is masked by the mask pattern 201 via the window gate circuit 5 in FIG. In such a binary image, if the first rising point such as A0 and B0 and the last falling point such as A1 and B1 are detected in the scanning direction, the result shown in FIG.
The coordinate points of the thick line portion 4 are obtained. However, when there are containers connected, the coordinate points in the area E become inaccurate. Therefore, of the line segments that connect the coordinate points of the thick line portion that are not included in this area E with the horizontal scanning line, the longest possible line segment A0-A
It is necessary to detect the position of the container by paying attention to the line segment near 1, B0-B1.

FIG. 15 shows the line segment A0-A1, described in FIG.
A similar line segment A01 not included in the area E near B0-B1
-A11, ..., A04-A14 from each midpoint MA
(MA1 ... MA4) is obtained, and the line segment B01-B1 is similarly obtained.
1, ..., B04-B14 from each midpoint MB (MB
1 ... MB4), and the midpoints MA1 ... MA4, MB1
... shows that the position (X coordinate) of the container center in the horizontal scanning direction is calculated by calculating the average value of MB4. In this case, the Y coordinate of the container center is, for example, the X coordinate of FIG.
It is obtained by calculating the average value of the coordinates of both ends (upper and lower) of the X-direction projection pattern obtained by the projection circuit 9.

FIG. 16 shows an example in which, as a process after the image is input to the frame memory 1a, the scanning direction is changed to the vertical (Y) direction and the position is detected by the same method as described above. That is, if the transport direction of the container is the left-right (X) direction, the vertical direction (Y)
The containers do not connect to each other in the direction scanning, and
It is not necessary to consider the area corresponding to E of 4. Note that in FIG. 15, the multi-value grayscale image signal PO can be directly used, whereas in the case of FIG. 16, the processing time is delayed because the image signal 1a from the frame memory 1 needs to be used, and the target image There is a possibility that the position detection of
If the scanning area in FIG. 16 is limited to a local area, this delay time can be minimized.

FIG. 17 is an explanatory view of another example of the container position detecting method focusing on the high brightness portion. In this example, as shown in FIG. 7B, the container 102 is imaged from the obliquely upper portion by the camera 203. In this case, the mouth high-intensity portion 103 is observed as a binary image as shown in FIG. It In this detected image, first rising coordinate points A01 ... A04 and last falling points A11 ... A on the same horizontal scanning line.
14 is obtained, and each line segment A01-A11, ..., A04-A1
The position of the container in the horizontal direction is determined by obtaining the average value MA of the midpoints of the four points, and further, the limit line L at which this line segment length is less than or equal to a set value is determined to determine the position (upper end) 20 of the container in the vertical direction.
4 is specified. Such a position detecting method can be applied when the upper end of the container is previously selected as a positioning point.

Next, the operation of determining the processing area when the containers are connected will be described. The processing area determination circuit 14 of FIG. 1 performs a calculation for determining the processing area based on the information of the X projection circuit 9 and the Y projection circuit 10. FIG. 18 shows a conventional method for determining the processing area. FIG. 18A shows a binary image with a threshold value such that the entire container is binarized. Here, 102-1 is a container to be inspected, and 102-2 is a container connected to the container 102-1. In this case, the containers are connected horizontally.

FIG. 18B shows the amount of pixels projected in the vertical direction of the image of FIG. 18A, and FIG.
Furthermore, the difference is the projection amount (projection pixel amount). In the relatively clear pattern as shown in FIG. 18, the right side contact PA and the left side contact PB are detected from the change point of FIG. 18C, and the connected containers are separated.

FIG. 19 is an explanatory view of a conventional method similar to FIG. 18, and shows a case where it is difficult to detect a connecting point. That is, in the actual inspection image, only a part of the containers connected as shown in FIG. 19A may be detected as a binary image, the projection pattern becomes as shown in FIG. 19B, and the difference projection pattern becomes It becomes difficult to separate the containers as shown in FIG.

FIG. 20 is an explanatory view of a processing area determining method based on the present invention when the containers are connected. That is, in this case, the Y projection circuit 10 first sets a threshold value for detecting the mouth high-intensity portion 103 as a ring-shaped inspection image, binarizes the multi-value grayscale image signal PO, and then, FIG. After obtaining the binary image as shown in FIG. 7, the projection in the Y direction perpendicular to the connecting direction (horizontal, X direction) of the dusty binary image is calculated to obtain the projection pattern as shown in FIG. .. Next, the processing area determination circuit 14 determines the difference between the projection amount (projection pixel amount) in FIG. 20B from the central portion of the target container 102-1 to the mouth portion as indicated by an arrow 301 in FIG. 20C. Is calculated to obtain a differential projection pattern as shown in FIG. Then, the contact points are obtained as follows.

That is, in order to obtain the right-side contact point PA, FIG.
In (C), a search is performed from a certain point P1 on the side surface of the container toward the mouth portion, and the differential projection in a section up to a point (referred to as a differential decrease start point) PD at which the graph of the differential projection pattern in FIG. The point where the amount becomes the maximum value (called the maximum difference projection point) ΔPM is obtained.

FIG. 21 is an enlarged view near the point ΔPM in FIG. 20 (C). In FIG. 21, PM is the high brightness portion 10 of the mouth.
3 is a point having the maximum projection amount in 3 (for convenience, it is referred to as a maximum projection point), and ΔPM is a point very close to PM obtained in the following manner in correlation with this maximum projection point PM. That is, the pixel number taken in the right (X) direction from the center of the target container 102-1 is k, and the projected pixel amount at the position of the pixel number k is Tk. This T _K and the pixel number value are separated by 4 pixels to the right. If a difference projection pattern is obtained by obtaining the difference ΔT _K = T _{K + 4} −T _K from the projected pixel amount T _{K + 4} of the other point, ΔT _K
The point ΔPM that is the peak of is determined as a point inside 4 pixels of the maximum projection point PM. In the present invention, this maximum difference projection point ΔP
A point obtained by adding a predetermined correction amount β to M is defined as a right side contact PA, which is a coordinate for separating the container connection and determining the processing area. The reason why the maximum difference projection point ΔPM is obtained in advance in this way is that the mouth high brightness is 10 depending on the brightness of the illumination on the container.
This is because the ring-shaped width of 3 fluctuates and the maximum projection point PM is easily affected by this fluctuation, whereas the maximum difference projection point ΔPM is detected as a stable coordinate point. As described above, according to the present invention, since the mouth high-intensity portion 103 is used to search for the connecting contact from the inside of the container toward the opening, the influence of the connecting of the container can be reduced.

FIG. 4 is a diagram showing the influence of defects appearing in the high-brightness part when a can container having a defect on the inner surface of the container is observed from the upper surface. FIG. 4A is a top view and FIG. FIG. When dust such as 111 adheres to the mouth of the container 102, the mouth high-luminance portion 103 is also detected as a circumferential chip as shown in FIG. Also, if there is a large dent 112 on the side surface, it may be detected as a distortion of the bottom high-intensity part 104. Generally, in the case of a dent, the contrast difference is small unlike dust adhesion etc. Therefore, the method for detecting the dent 112 is very effective.

FIG. 5 shows a concrete example of the high-luminance part judgment circuit 11.
It is an explanatory view of a roundness detection method. This figure shows a non-defective container
The rising side of the coordinates of the outer peripheral point of the high-intensity part is x0j, and the falling side
X1j (where j = 1, 2, ──, that is, j is each point
Corresponds to the relative y coordinate value of the horizontal scanning line to which
It is a parameter. ) Is expressed as. the first
Amount of coordinate change of non-defective container x_{k + 1}-X_kAnd calculate
Maximum value that gives the allowable range of (max (a, b) described later)
And the minimum value (min (a, b) described later) are allowable values, respectively.
Maximum value table T described later (FIG. 6) as table TB
B1 is stored in the minimum value table TB2. But here
Where k is 0j or 1j. At this time, the upper and lower ends
Exclude some lines because the image stability is low or
It is necessary to give a very large tolerance, but good product coordinates
X from the amount of change_{k + 1}-X _kThe allowable range of
It min (a, b) -α <x_{k + 1}-X_k<Max (a, b) + α Here, max (a, b) is one of the values of a and b shown below.
Means the maximum value, whichever is larger, min
(A, b) is also the smaller of the values of a and b
It means the minimum value of. a = x_k-X_k-1 b = x_{k + 2}-X_{k + 1} Also, consider the quantization error when converting to a digital image.
It is a fixed value to ease the detection sensitivity. Note that
As the method of giving a and b, a = x_k-1-X_k-2 b = x_{k + 3}-X_{k + 2} It is also possible to have an allowable width of 2 lines.
It

As described above, the high-luminance portion determination circuit 11 stores the allowable values in each line of the non-defective container as the maximum value table TB1 and the minimum value table TB2 shown in FIG. 6, and the coordinate change amount of the inspection image and this table TB1. , T
The circularity is inspected by comparing with the allowable value in B2.
As a measure against the number of scan lines of the non-defective container stored in advance and the number of scan lines of the inspection image, the above comparison is performed in order from the upper end and the lower end of the container to the center of the container. Perform near the center. That is, when the number of lines in the allowable value table at the time of learning good products is small, the allowable value of the center line is continuously used as it is for comparison (see FIG. 6). Note that, in FIG. 6, the same process is performed twice for the upper circle and the lower circle, and the allowable value table has a method of storing only a half circle.

The above is the method for inspecting the outer peripheral points, but next, the method for inspecting the inner peripheral points will be described. 7A and 7B are explanatory diagrams of a method of detecting coordinate points on the inner periphery of the high-intensity portion. FIG. 7A is a top view image of a can container, and FIG. 7B is a scanning line Q-Q1 in FIG.
The change of the signal which binarized the high brightness part of the above-mentioned grayscale image signal is shown. The first falling point 121 of the binarized signal in FIG.
Focusing on, the coordinates such as the thick line portion 121a in FIG. Since the coordinates of the inner circumference point are in the section D-D1, D and D1 are respectively obtained as lines in which the amount of change in the coordinates is inverted, and the coordinates of the left semicircle of the inner circumference are obtained. Similarly, the last rising point 122 is detected to obtain the right semicircle of the inner circumference, and the circularity is inspected in the same manner as for the outer circumference point.

FIG. 8 shows the configuration of the image edge detection circuit 6 of FIG. 1 in more detail. In FIG. 8, 6A is a memory for storing the first rising point, 6B is a memory for storing the first falling point, 6C is a memory for storing the last rising point, and 6D is a memory for storing the last falling point. .. The outer circumference can be detected from the data in the memories 6A and 6D, and the inner circumference can be detected from the data in the memories 6B and 6C.

According to the present invention, when the circularity inspection of the inside and the outside of the high-intensity part as described above is performed, deformation of the container, dents, dust adhesion to the high-intensity part, etc. can be detected, and the defect detection accuracy can be improved. It is possible to reduce the number of windows by performing the sexiness inspection and the black and white spot inspection by the conventional defect detection circuit in parallel. FIG. 3 shows an embodiment of a window according to the present invention, and this figure corresponds to FIG. 13 (B).
That is, in FIG. 3, the window W1 including the mouth high brightness portion 103 of FIG. 13 and the adjacent window W2 are combined into a new window WN1. Similarly, the window W4 including the bottom high brightness portion 104 of FIG. And a window W3 adjacent thereto to form another new window WN2, and a window WN3 having a new code corresponding to the window W5 in the center of the bottom surface of FIG.
The number of areas can be reduced by dividing the window areas WN1, WN2, and WN3.

FIG. 9 is a flow chart showing the operation procedure of FIG. Next, the operation of FIG. 1 will be described with reference to FIG. The symbols S1 to S13 below indicate the steps in FIG.
First, the image output changeover switch 17 is set to the image edge detection circuit 6
At the same time as switching to the side, the image input changeover switch 18 is switched to the through side, that is, the side where the image edge detection circuit 6 directly inputs the multi-valued image signal PO (S1), and the positional deviation of the target image is detected (S2). At the same time, the X projection circuit 9 and Y
The processing area is determined through the projection circuit 10 and the processing area determination circuit 14 (S3). That is, in step S2, the positional deviation amounts Δx and Δy of the container image are obtained through the positional deviation amount determining circuit 13 of FIG. 1, and the correction amount relating to the parallel positional deviation is sent to the image address generating circuit 3 so that the window can be generated at the correct position. give. In step S3, the processing area determining circuit 14 separates the container image when the container image is connected to another container image, and cuts the scanning range so that the scanning area does not include the connected container image.

Next, the image input changeover switch 18 is switched to the side of the frame memory 1 (S4), and the following quality determination processing is performed based on the grayscale image data 1a of the frame memory 1. First, the inspection target window region of the target can is set as the region of the window WN1 including the mouth high-intensity portion 103, and the other window regions WN2 and WN3 are masked (S5). Then, until the inspection for all windows is completed (S5A, branch N), the process proceeds to step S6. Step S
In 6, the image output changeover switch 17 is switched to the defect detection circuit 7 side, and the defect detection processing is performed via the defect detection circuit 7 and the defect detection determination circuit 12 (S7). Here, the defect detection circuit 7 detects black stains and white stains by a method such as a differential method to measure the number of defective pixels, and the defect detection determination circuit 12 compares the measured number of defective pixels with a predetermined value to determine whether it is acceptable or not. Is performed and output to the comprehensive determination circuit 15 in a step described later.

Next, the image output changeover switch 17 is switched to the image edge detecting circuit 6 side and the image edge detecting circuit 6 is operated again, and the high brightness portion is binarized as described above, and the outer circumference is obtained by the above-mentioned method. , The area of the inner circumference coordinate points, the outer circumference circle, and the inner circumference circle are measured (S9), and the high-luminance part determination circuit 11
A circularity inspection and comparison with a reference area value are performed to determine whether the quality is good, and the determination result is output to the comprehensive determination circuit 15 in a step described later. If the comprehensive judgment circuit 15 judges that either the high-luminance part judgment circuit 11 or the defect detection judgment circuit 12 is defective (S10 → S11, branch Y), the output circuit 16 is instructed to output a defective product (S12). On the other hand, the step S
If it is a non-defective product in step 11, the process returns to step S5 again, and the next inspection target region is the window region W including the bottom high-intensity portion 104.
N2 is set, the other regions WN1 and WN3 are masked, and the procedure up to step S12 is repeated. In this way, when the inspection of all windows up to the window WN3 is completed (S5A, branch Y), the output circuit 16 is instructed to output a non-defective product via the comprehensive determination circuit 15 (S13).

FIG. 2 is a block circuit diagram for speeding up the processing of FIG. In FIG. 2, the image input changeover switch 18 of FIG. 1 is omitted, the window circuit 5 is replaced by a new circuit 5A, and two circuits 6-1 and 6-2 corresponding to the image edge detection circuit 6 are provided. The one image edge detection circuit 6-2 directly inputs the multi-valued image signal PO (via the window gate circuit 5A) to give the detection result to the position shift amount determination circuit 13, and further outputs the image shown in FIG. The changeover switch 17 is omitted, and the output image signal 1a of the frame memory (via the window gate circuit 5A) is supplied to the other image edge detection circuit 6-1 and the defect detection circuit 7.
And the processing of the high-brightness determination circuit 11 and the processing of the defect detection circuit 11 are simultaneously executed in parallel.

FIG. 10 is a flow chart showing the operation procedure of FIG. 2, which is a switching procedure S of the switches 17 and 18 from the procedure of FIG.
1, S4, S6, S8 are omitted, and the defect detection process of step S7 and the high-luminance part process of step S9 are parallelized.

FIG. 11 is an explanatory view of the bottom high-intensity portion when the bottom shape of the can container is different, and FIG. 11 (A) shows the top surface (image).
FIG. 1B is a side sectional view. In this example, two bottom high brightness portions 104-1 and 104-2 are generated. As described above, depending on the shape of the bottom of the can, the high-intensity bottom part may occur in several concentric circles. In such a case, the bottom area is appropriately divided and the number of windows is increased. Step S5 in FIGS. 9 and 10 is a conditional branch for that purpose. Since the bottom area is small as a scanning area, the processing speed can be maintained even if the number of windows is increased.

[0034]

According to the present invention, the position of the container is specified from the midpoint coordinates of the first rising point and the last falling point on the scanning line for the binary image of the high brightness portion of the mouth of the container. Furthermore, the projection amount of the binary image of the mouth high-intensity part in the direction perpendicular to the connecting direction of the container is obtained, the difference value of this projection amount is searched from the inside of the container to the outside, and the predetermined value is satisfied. After detecting the contact point and separating the detection area from the area of the connecting container,
Since it has been decided to inspect the circularity of the high-intensity part on the inner surface of the container, this inspection can detect deformation of the can container, dents, and dust adhesion to the high-intensity part, thus improving the inspection accuracy. Therefore, the size of the window area scanned at one time is enlarged by executing this circularity inspection and the inspection of the black and white dots by the conventional defect inspection means in parallel (in other words, the number of windows is reduced). The processing can be speeded up.

[Brief description of drawings]

FIG. 1 is a block diagram showing a hardware configuration as a first embodiment of the present invention.

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

FIG. 3 is a diagram showing a relationship between a change in concentration on the inner surface of a circular container and window division according to the present invention.

FIG. 4 is a diagram showing an influence on a high-intensity part due to a defect on the inner surface of the container.

FIG. 5 is a diagram showing outer peripheral points of a high-luminance portion for a circularity inspection.

FIG. 6 is an explanatory diagram of circularity determination.

FIG. 7 is an explanatory diagram of a method of detecting an inner peripheral point of a high brightness portion.

FIG. 8 is a block diagram showing a detailed configuration of an image edge detection circuit.

9 is a flowchart showing the operation procedure of FIG.

FIG. 10 is a flowchart showing the operation procedure of FIG.

FIG. 11 is a view showing a high-intensity part on the inner surface of the container when the bottom shape of the circular container is different.

FIG. 12 is a diagram showing a high-intensity part on the inner surface of a circular container.

FIG. 13 is a diagram showing a relationship between a change in concentration on the inner surface of a circular container and conventional window division.

FIG. 14 is an explanatory diagram of a target image position detection method according to the first embodiment of the present invention.

15 is a detailed explanatory diagram supplementing FIG.

FIG. 16 is an explanatory diagram of a target image position detection method as a second embodiment of the present invention.

FIG. 17 is an explanatory diagram of a target image position detection method as the third embodiment of the present invention.

FIG. 18 is an explanatory view of a conventional method for detecting a container contact point.

FIG. 19 is a diagram showing an example in which a contact cannot be detected by the detection method of FIG.

FIG. 20 is an explanatory diagram of a method for detecting a contact point based on the present invention.

21 is a partially enlarged view of FIG.

[Explanation of symbols]

 PO multi-value 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 5 window gate circuit 5A window gate circuit 6 image edge detection circuit 6-1 image edge Detection circuit 6-2 Image edge detection circuit 6A First rising point memory 6B First falling point memory 6C Last rising point memory 6D Last falling point memory 7 Fault detection circuit 9 X projection circuit 10 Y projection circuit 11 High brightness Part determination circuit 12 Defect detection determination circuit 13 Position shift amount determination circuit 14 Processing area determination circuit 15 Overall determination circuit 16 Output circuit 17 Image output changeover switch 18 Image input changeover switch WN1 window WN2 window WN3 window 101 Ring Illuminator 102 (102-1, 102-2) Container 102-1 Target Container 102-2 Connection Container 103 Mouth High Brightness Section 104 Bottom High Brightness Section 104-1 Bottom High Brightness Section 104-2 Bottom High Brightness x01- x0j Outer peripheral point x11 to x1j Outer peripheral point TB (TB1, TB2) Allowable value table TB1 Maximum value table TB2 Minimum value table 201 Mask pattern A0 First rising point B0 First rising point A1 Last falling point B1 Last falling point MA (MA1 to MA4) Mid point MB (MB1 to MB4) Mid point 203 Camera 204 Upper end position L Limit line PA Right side contact point PB Left side contact point PD Difference reduction start point ΔPM Maximum difference projection point PM Maximum projection point β Correction amount

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁵ Identification code Office reference number FI technical display location H04N 7/18 B 8626-5C

Claims (1)

[Claims] 1. An inner surface side of an axially symmetric circular container which can be connected to each other in a predetermined direction is illuminated from the axial direction, and an illumination surface of the circular container is illuminated from the axial direction via a TV camera. In a circular container inner surface inspection device for inspecting black stains and white stains on the inner surface of the circular container by imaging and analyzing the imaged image through a defect inspection means, the image signal obtained by the screen scanning of the imaging is Binarization is performed so as to obtain a binary image of the mouth high-intensity portion of the circular container, and means for projecting the binarized image signal in a direction perpendicular to the connecting direction and a projection pixel amount based on this projection Then, the differential projection pixel amount is obtained by examining the differential projection pixel amount from the inner side to the outer side of the circular container, and the difference projection pixel amount is set to a predetermined value within a section up to the point where the pixel amount first becomes negative. Detects points that exceed the threshold An apparatus for inspecting an inner surface of a circular container, comprising means for separating the connecting region by using a coordinate value obtained by adding a predetermined correction value to the coordinate value of the detection point.