JP3456096B2 - Shape inspection method - Google Patents

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a shape inspection method using image input means.

[0002]

2. Description of the Related Art As a shape inspection method using an image input means, a shape inspection by pattern matching is generally used. In this case, the reference image registered in advance and the image of the inspection object are compared to determine pass / fail.

[0003]

In this case, the reference image must be registered in advance, and it takes time for the pattern matching to reach the quality judgment stage. The present invention has been made in view of these points,
It is an object of the invention to provide a shape inspection method capable of determining pass / fail without having to register a reference image if the shape of the inspection object is known.

[0004]

The invention according to claim 1 of the present invention is a shape inspection method for an object to be inspected whose shape is already known. The contour line is extracted, the coordinates of a plurality of points on the contour line are obtained, a known shape is expressed from the coordinates, and an equation that should match the contour line is derived, and a predetermined offset value is added to the equation.
In this way, an inspection reference line similar to the known shape and different in size from the contour line is obtained, and the quality of the shape of the inspection object is determined based on the area of the gap between the inspection reference line and the contour line. It has features.

According to a second aspect of the present invention, there is provided a shape inspection method of an object whose shape is already known, wherein a contour line is extracted from an image of the object to be inspected obtained by the image input means, and the contour line is extracted. The coordinates of a plurality of points are obtained, the known shape is expressed from the coordinates, and the formula that should match the contour line is derived .
By adding a predetermined offset value, an inspection reference line that is similar to the known shape and slightly different in size from the contour line is obtained, and the quality of the shape of the inspection object is judged based on the shade of the image on this inspection reference line. It is characterized by

According to a third aspect of the present invention, there is provided a shape inspection method for an object whose shape is known, wherein a contour line is extracted from an image of the object to be inspected obtained by the image input means, and the contour line is extracted. The coordinates of a plurality of points are obtained, the known shape is expressed from the coordinates, and the formula that should match the contour line is derived .
By adding a predetermined offset value, an inspection reference line that is similar to the known shape and has a different size from the contour line is obtained, and an edge search is performed from multiple points of this inspection reference line toward the contour line to obtain the contour from each point. The feature is that each distance to the line is obtained and whether the shape of the inspection object is good or bad is determined based on the distance.

[0007]

In each of the above inventions, when the known shape is a rectangle, two points from the top and bottom of the obtained image,
A total of 8 points are searched from the left and right to find the coordinates of 8 points on the contour line, and the equations that represent the known shape and should match the contour line are straight lines of 4 sides from the coordinates of the 8 points. It is advisable to find the coordinates of the four points where the equation and these straight lines intersect, and if the known shape is a perfect circle, search the edges of the obtained image to find the coordinates of the three points on the contour line. As a formula that represents a known shape and that should match the contour line, a formula of a virtual circle that passes through the coordinates of the three points may be obtained.

The inspection object may be divided into a plurality of images, and the contour line may be extracted from each image. In any case, in the present invention, it is possible to determine the quality of the shape without performing pattern matching by utilizing the fact that the shape and size are known.

[0010]

BEST MODE FOR CARRYING OUT THE INVENTION First, a case where it is known that the object 1 to be inspected is a rectangle in which all four corners are at right angles will be described. As shown in FIG.
An image of the inspection object 1 illuminated by the illumination 11 is captured by the image capturing means 10 such as a CD camera. FIG. 3A shows the obtained image. In the figure, 21 is the inspection region and 22 is the image of the inspection object.

With respect to the image thus obtained, first, as shown in FIG. 3B, the edges of the image 22 of the object to be inspected from the upper two points and the lower two points of the inspection region 21 toward the center in the vertical direction. To search. At this time, if the four edges cannot be searched, the search is performed by changing the interval between the two points or the left and right positions. The search scan uses an edge image thresholded with a differential absolute value corresponding to the density change rate, scans the search line to find an edge flag, and if the differential value exceeds a predetermined value, The address is the point.

In this way, if the upper two points a and b and the lower two points c and d of the contour line of the inspection object image 22 are searched, then, based on the coordinates of these four points, FIG.
The search start points on the left and right sides of the inspection area 21 are determined, and the edges of the inspection object image 22 are searched from the two points on each of the left and right sides toward the center in the left-right direction, and the outline of the inspection object image 22 is determined. 2 points e and f on the left side of the line and 2 points g on the right side,
Find the coordinates of h.

In this way, if the coordinates of 2 points on one side, that is, 8 points in total, are obtained, the image of the object to be inspected 22
The linear equation of each side of the contour line is obtained from the coordinates of the above points, and further the intersections of the straight lines, that is, the coordinates of the four corners are obtained from the four linear equations. An equation that represents a known shape and that conforms to the contour line is derived. Next, based on this equation, as shown in FIG. 3D, an inspection reference line S that is similar to the known shape and different in size from the contour line is set. Since it is known that the example shown in the figure has a rectangular shape, by adding an offset of a predetermined value to each of the four linear equations, a line parallel to the line represented by the above four linear equations is formed. The rectangular inspection reference line S is set.

By thus setting the inspection reference line S, the area of the gap between the inspection reference line S and the contour line of the image 22 of the object to be inspected is obtained. At this time, if the contour line draws an accurate rectangle, the value thus obtained matches the area value calculated from the known size of the inspection reference line S and the offset value, but the accurate rectangle Otherwise, the values will be different, so that the quality of the inspection object 1 can be determined from the area value. Although the inspection reference line S is located outside the contour line in FIG. 3D, it may be located inside the contour line. In this case, the area of the portion inside the contour line and outside the inspection reference line S is obtained.

When the offset value is set small when setting the inspection reference line S, that is, when the offset value for setting the inspection reference line S is set within the non-defective range of the inspection object 1. As shown in FIG. 4, the quality can be determined by determining the density of the pixel on the inspection reference line S. This is because if there is shading of pixels due to the unevenness of the contour line on the inspection reference line S, it means that the inspected object 1 has unevenness outside the non-defective range. Of course, the inspection reference line S is set outside the contour line to detect a convex defect, and inside the contour line to detect a concave defect. However, in order to eliminate the effect of image density due to noise, as shown in FIG. 4B, the average density of a plurality of pixels is obtained for each address that is shifted by one pixel or several pixels, and the average density of adjacent portions is calculated. It is preferable to determine that there is a defect if the cumulative value of the differences exceeds the threshold value.

As shown in FIG. 5, when the contour lines are not rectangular, the four straight lines represented by the four straight line equations are not two parallel lines, and thus form a pair. The quality can be determined from the degree of inclination of one of the two lines with respect to the other. If the length of each side is also known, the straight line distance between the coordinates of the four corners, that is, the length of each side is obtained, and it is judged whether the length exceeds a preset limit value. You may.

Next, an example in which the inspection object 1 is a perfect circle will be shown. Also in this case, as shown in FIG. 6, the image of the inspection object 1 illuminated by the illumination 11 is taken by the image pickup means 10 such as a CCD camera. The image obtained is shown in FIG. In the figure, reference numeral 21 is an inspection area, and 22 is an image of the inspection object. With respect to the image thus obtained, an edge search for three points is performed to obtain coordinates of three points on the contour line. In the illustrated example, first, the edge of the object image 22 to be inspected is searched from the midpoint in the horizontal direction on the upper and lower sides of the inspection area 21 toward the center in the vertical direction, and as shown in FIG. Find the coordinates of the edge of. The search scan in this case may also use the edge image obtained by thresholding the differential absolute value corresponding to the rate of change in density.

Next, the midpoints of the two points a and b are calculated, the edges existing on the midpoint are searched from the left and right sides of the inspection area 21, and the two points c and d shown in FIG. Get the coordinates of. Based on the coordinates of 3 points of the 4 points a, b, c and d thus obtained, the center coordinates and the radius r of the contour line which should be a perfect circle of the image of the inspection object 1 are obtained. An expression that represents a known shape and that matches the contour line is obtained.

Then, an inspection reference line S which is similar to the known shape and different in size from the contour line is set based on the equation. Here, since the known shape is a perfect circle, as shown in FIG. 7D, the perfect circle having the same center coordinates and an offset value added to the radius value r is used as the inspection reference line S. By setting the inspection reference line S in this manner, the area of the gap between the inspection reference line S and the contour line of the inspection object image 22 is obtained. At this time, if the contour line draws an accurate perfect circle, the value thus obtained is the inspection reference line S.
The value of the area that is calculated from the known size of the above and the value of the offset is different, but if it is not an exact circle, the value will be different. You can Here again, the inspection reference line S is located outside the contour line in the case shown in FIG. 7, but it may be located inside the contour line.

When the offset value is set small when setting the inspection reference line S, that is, when the offset value for setting the inspection reference line S is set within the non-defective range of the inspection object 1. As shown in FIG. 8, the quality can be determined by determining the shading of the pixel on the inspection reference line S. This is because if there is shading of pixels due to the unevenness of the contour line on the inspection reference line S, it means that the inspected object 1 has unevenness outside the non-defective range. Of course, the inspection reference line S is set outside the contour line to detect a convex defect, and inside the contour line to detect a concave defect. In order to eliminate the effect of noise on the image density, as shown in FIG. 8B, the average density of a plurality of pixels is calculated for each address that is shifted by one pixel or several pixels, and the difference in the average density of adjacent portions is calculated. It is the same as the above-mentioned case that it is preferable to judge that there is a defect if the cumulative value of exceeds the threshold value.

If the radius value R of the object to be inspected 1 is also known, it is advisable to set the inspection reference line S to a perfect circle having a known radius R centered on the center point obtained from the image 22 to be inspected. If the radius r obtained from the inspection object image 22 is within the range of good products from the known radius R, that is, if the range of good products is R ± d, R−d <
When r <R + d, it is determined as a non-defective product. If the three points for obtaining the radius r and the center coordinates include the deformation points as shown in FIG. 9, the value of the radius r is the original radius R.
This is because the value is different from.

However, even if the above-mentioned 3 points include the deformation points, the calculated value of the radius r may fall within the non-defective range. Therefore, as shown in FIG. 10, a radius obtained by adding an offset value to the radius r. A plurality of points, eight edge search start points in the illustrated example, are provided on the inspection reference circle S at equal intervals, and edge search is performed by differential values from each point toward the center of the circle, and the object image 22 The respective distances to the contour line are obtained, and the total sum DF of the differences between the respective distances at these eight locations and the offset value of the radius of the inspection reference circle S is calculated, and the non-defective product is judged by comparing the value of the total sum DF with a threshold Shall be performed. D for each distance
1, d2 ... d8,

[0023]

[Formula 1]

Then, the sum DF is used as a value indicating the degree of deformation. When the inspection object 1 is an annular one, the above-described non-defective product determination may be performed on the outer peripheral side contour line and the inner peripheral side contour line, respectively. When the inspection object 1 is large and the resolution required for inspection is high, as shown in FIG. 11, one inspection object 1 is imaged by a plurality of image pickup means to show different parts of the inspection object 1. It is preferable to generate a plurality of inspected object images 22 and 22 and set an inspection reference line S for each inspected object image 22 to perform the shape inspection as described above.

FIG. 1 shows a flow chart when the pass / fail judgment is performed by performing the steps shown in FIG. 11, FIG. 12 and FIG. 10 in this order. The noise component removal in the edge search in FIG. 1 is performed as follows. That is, as shown in FIG. 12, when there is a portion with different density in the inspection object image 22 or there is a noise image 27 due to dirt or dust on the outside of the inspection object image 22, the density of pixels on the edge search line. The density value having the maximum frequency (usually the background density) is obtained as the distribution, and the reference density L0 is set, and the binarization processing is performed with the threshold value L obtained by adding a predetermined offset to the reference density L0. To label black pixels. For example, if the reference density value is 200 and the offset is 30, the threshold L for binarization is set to 170 and the portions of the inspection object image 22 having different densities are absorbed.

The obtained labeling result LL is shown in FIG.
If there is one as shown in (1), the coordinates at which the color changes from white to black from the outside to the inside of the edge search line are detected as the primary edge. To further improve the accuracy of the edge detection point, locally obtain the differential absolute value in the vicinity of the primary edge, and perform threshold processing of the differential absolute value to obtain an edge image showing the boundary line of the density change. It may be used to obtain the secondary edge.

The obtained labeling result LL is shown in FIG. 12 (b).
When there are two due to the noise image 27 as shown in, by adopting the labeling result LL having a large width,
The noise image 27 can be removed.

[0028]

As described above, in the present invention, the contour line is extracted from the image of the object to be inspected obtained by the image input means, the coordinates of a plurality of points on the contour line are obtained, and the known shape is represented from the coordinates. A formula to be matched with the contour line is derived, and a predetermined offset value is added to the formula to obtain an inspection reference line that is similar to the known shape and has a size different from that of the contour line. or to determine the acceptability of the shape of the object to be inspected area of the gap based on, given by the formula offsets
By adding a dot value, an inspection reference line similar to the known shape and slightly different in size from the contour line is obtained, and the quality of the shape of the inspection object is judged based on the contrast of the image on the inspection reference line. Alternatively, by adding a predetermined offset value to the above equation , an inspection reference line similar to the known shape and different in size from the contour line is obtained, and the inspection reference line is directed to the contour line from a plurality of points. calculated respectively the distances from each point performs edge search to contour Te, the distance from <br/> it is to acceptability of the shape of the object to be inspected based on, without requiring a pattern matching process, also It is not necessary to capture the reference image in advance, and the quality can be determined accurately and quickly.

When the known shape is a rectangle, a total of 8 points are searched for the obtained image, two points each from the upper and lower sides and two points from the left and right sides, and the coordinates of the eight points on the contour line are determined. If the straight line equation of four sides and the coordinates of the four points where these straight lines intersect are obtained from the coordinates of these eight points, it is possible to easily obtain an equation that represents the known shape and that should match the contour line. When the known shape is a perfect circle, the edge of the obtained image is searched for three points to obtain the coordinates of three points on the contour line, and the formula of the virtual circle passing through the coordinates of the three points is calculated as the known shape. , And a formula that should match the contour line, the formula that also matches the contour line can be easily obtained.

When the inspection object is divided into a plurality of images and the contour line is extracted from each image, a result satisfying the size of the inspection object and the required accuracy can be obtained.

[Brief description of drawings]

FIG. 1 is a flowchart of the operation of the present invention.

FIG. 2 is a perspective view showing an example of an embodiment.

FIG. 3 shows the same operation as above, and (a) to (d) are explanatory views.

FIG. 4 shows another operation, and FIGS. 4 (a) and 4 (b) are explanatory diagrams.

FIG. 5 is an explanatory diagram of another operation.

FIG. 6 is a perspective view showing an example of another mode.

FIG. 7 shows the same operation as above, and (a) to (d) are explanatory views.

FIG. 8 illustrates another operation, and FIGS. 8A and 8B are explanatory diagrams.

FIG. 9 is an explanatory diagram of another operation.

FIG. 10 is an explanatory diagram of still another operation.

FIG. 11 is an explanatory diagram of a different operation.

FIG. 12 shows a noise removing operation, and FIGS. 12 (a) and 12 (b) are explanatory views.

[Explanation of symbols]

1 Inspected 22 Inspection object image S inspection reference line

Claims (6)

(57) [Claims] 1. A method of inspecting an object whose shape is known, wherein a contour line is extracted from an image of the object to be inspected obtained by an image inputting means, and coordinates of a plurality of points on the contour line are obtained. From the coordinates, derive a formula that should represent the known shape and match the contour line, and add a predetermined offset value to the formula.
Therefore, an inspection reference line similar to the known shape and different in size from the contour line is obtained, and the quality of the shape of the inspection object is determined based on the area of the gap between the inspection reference line and the contour line. Shape inspection method. 2. A method of inspecting an object whose shape is known, wherein a contour line is extracted from an image of the object to be inspected obtained by the image inputting means, and coordinates of a plurality of points on the contour line are obtained. From the coordinates, derive a formula that should represent the known shape and match the contour line, and add a predetermined offset value to the formula.
It is characterized in that an inspection reference line which is similar to the known shape and whose size is slightly different from the contour line is obtained, and whether the shape of the inspection object is good or bad is determined based on the contrast of the image on the inspection reference line. Shape inspection method. 3. A method of inspecting a shape of an object whose shape is known, wherein a contour line is extracted from an image of the object to be inspected obtained by the image inputting means, and coordinates of a plurality of points on the contour line are obtained. From the coordinates, derive a formula that should represent the known shape and match the contour line, and add a predetermined offset value to the formula.
Thus, an inspection reference line similar to the known shape and different in size from the contour line is obtained, and an edge search is performed from a plurality of points on the inspection reference line toward the contour line to determine the distance from each point to the contour line. A shape inspecting method, which is characterized in that the quality of a shape of an object to be inspected is determined based on the obtained distance. 4. The image obtained when the known shape is a rectangle.
2 points from the top and 2 points from the top and bottom of the image
8 point edge search is performed and 8 point coordinates on the contour line
To obtain the known shape and match the contour line
As a straight line of four sides from the coordinates of the above 8 points
Characterized by finding the coordinates of the four points where these straight lines intersect with the formula
The shape inspection method according to any one of claims 1 to 3 . 5. The image obtained when the known shape is a perfect circle.
The image is searched for 3 points and 3 points on the contour line are searched.
The coordinates of the object are obtained, the known shape is displayed, and the contour is
As a formula to be met, a virtual circle that passes through the coordinates of the above 3 points
4. The method according to claim 1, wherein the equation is calculated.
The shape inspection method described in the section . 6. An inspection object is divided into a plurality of images, and each image is divided into a plurality of images.
6. A contour line is extracted for the contour line.
The shape inspection method according to any one of 1 .