JPH0719291B2 - Appearance inspection device - Google Patents

Description

Detailed Description of the Invention [Industrial applications]

The present invention relates to a visual inspection apparatus that determines pass / fail of a shape of a target portion belonging to an object based on a captured image of the object.

[Prior art]

Conventionally, the following method has been used to image an object and inspect the shape of the object based on the image. For example, FIG. 5 shows an image of an object in the imaging field of view, and in this figure it is assumed that the image 30 of the object is circular. 31,32
Are all areas for measurement, and are for determining whether or not the shape of the object image 30 is acceptable. That is, the region 31 is a circular ring that is larger than the target image 30 by a predetermined amount, and the region 32 is a circular circle that is smaller than the target image 30 by a predetermined amount.
By measuring the area of the object image 30 at 1, 32, it is determined whether the shape of the object is acceptable or not. That is, if any one of the area values is equal to or larger than the predetermined value, it is determined to be rejected, and if any of the area values is less than the predetermined value, it is determined to be pass. By the way, in order to accurately determine the shape, the position of the object image 30 must be correctly associated with the positions of the regions 31 and 32, that is, concentric. Incidentally, in FIG. 5, the object image 30 is at the reference position, that is, the areas 31, 3
It is located concentrically with 2. However, in general, the object image 3
The position of 0 does not become concentric with the areas 31 and 32, and is usually slightly shifted. Therefore, at that time, as described below, a measure is taken to find the deviation of the object image 30 from the reference position and correct the positions of the regions 31 and 32 accordingly. FIG. 6 is an explanatory diagram for obtaining the positional deviation of the object image 30, that is, the deviation from the reference position. In FIG. 6, the rectangular regions 33 and 34 are located at the right end portion and the upper end portion of the object image 30. It is fixed so as to include. Based on the object image 30 in the regions 33 and 34, the positions X1 and Y1 of the right end portion and the upper end portion thereof are obtained. As is well known, how to obtain this position is based on the projection of the object image 30 on the X axis and the Y axis. In this way, the reference position Xo, Yo of each of these points in the X-axis and Y-axis directions
(See Fig. 5) Deviations Xd (= X1-Xo), Yd (= Y1-Y)
o) Next, according to this deviation Xd, Yd, the regions 31, 32
Is corrected to be concentric with the object image 30.

[Problems to be Solved by the Invention]

In the conventional technique as described above, the outline image of the target object is large from the X and Y directions, such as when the outer shape of the target object is large and the entire target object is not always completely included in the imaging visual field. It may not have a convex portion or a concave portion when viewed, and in such a case, the position of the object cannot be accurately obtained. The object of the present invention is to solve the above-mentioned problems of the conventional technique, and even when the contour of the object does not have a convex portion or a concave portion viewed from each of the X and Y directions, whether the shape of the target portion is accurate or not. An object is to provide an appearance inspection device capable of making a determination.

[Means for Solving the Problems]

In order to solve this problem, the present invention is a device for inspecting the pass / fail of a portion to be inspected of the object based on an object image obtained by imaging, and the portion to be inspected (hole 21) of the object Measuring area generating means (measuring area generating circuit 5) for generating a measuring area (W1, W2) having a predetermined shape corresponding to the shape of the object, and the amount of positional deviation from the reference position of the object image in the imaging visual field. Position correction means (position correction circuit 9) for correcting the position of the measurement area, feature quantity measurement means (area measurement circuit 10) for obtaining the feature quantity of the portion to be inspected in the measurement area, and the feature quantity measurement means. Discriminating means (discriminating circuit 1
1) and a first region (Wx) including at least an image of a contour portion of the object image, and a certain point (P) on the contour in the first region
Means (correction area generating circuit 6) for generating a second area (Wy) partially including the object image at a position away from the object in the X-axis or Y-axis direction by a predetermined distance; A means (projection detection circuit 7) for detecting the end point coordinates (X coordinate Xs of the point P in the embodiment) on the X axis or the Y axis by projecting the object image in the area onto the coordinate axes; Means (centroid detection circuit 8) for detecting the coordinates of the center of gravity (point G) (Y coordinate Ys of the point G in the embodiment) for a partial image of the object to be detected, and means for detecting the coordinates of the end points; On the basis of the output from the means for detecting the coordinates of the center of gravity, the amount of displacement (X
s, Ys), and outputs this as a correction amount to the measurement region generating means to generate the measurement region (W1, W2) in the portion to be inspected of the object. .

[Action]

The position of the measurement region is corrected by the position correction unit according to the deviation of the predetermined position of the object image from the reference position, which is obtained based on at least one of the projection detection unit and the center of gravity detection unit. Next, the feature amount measuring means obtains the feature amount of the image of the target portion in the measurement region, and based on this feature amount, the pass / fail of the shape of the target portion is determined.

【Example】

An embodiment of a visual inspection apparatus according to the present invention will be described below with reference to the drawings. By the way, the point of this embodiment is to provide a correction region corresponding to the target portion in order to correct the position of the measurement region corresponding to the image of the inspection target portion belonging to the object in accordance with the change in the position of the target portion. not,
The object is provided so as to correspond to a predetermined location of the object, and the detection of the predetermined location of the object is based on at least one of projection detection and gravity center detection. The configuration of this embodiment will be described with reference to the block diagram of FIG. In FIG. 1, 1 is a TV camera for image pickup, and 2 is an A / D for digitizing a video signal of the TV camera 1.
D converter, 3 is a binarization circuit for binarizing the output of the A / D converter 2 based on a predetermined threshold value, 4 is a binarization circuit 3
Is an image memory for storing the output data of. Reference numeral 5 denotes a measurement area generation circuit, which generates a measurement area corresponding to the target portion in order to measure the shape of the target portion. Reference numeral 6 denotes a correction area generation circuit, which generates first and second correction areas corresponding to a predetermined position in order to measure the change in the position of the predetermined position of the object, as will be described later in detail. Reference numeral 7 is a projection detection circuit, which detects the object image of the first correction area.
Obtain the projections in the X and Y directions. 8 is a center of gravity detection circuit, which is the second
The barycentric position of the object image is obtained with respect to the correction area. A position correction circuit 9 corrects the position of the measurement region according to the change in the position of the target portion obtained based on the first and second correction regions. An area measuring circuit 10 measures the area of the target portion in the measurement area. A determination circuit 11 determines whether or not the shape of the target portion is acceptable based on the area value output from the area measurement circuit 8. FIG. 2 is an explanatory diagram of an imaging visual field when the object image 20 is at the reference position in the embodiment, and FIG. 3 is an explanatory diagram of an imaging visual field when the object image 20 is deviated. In FIG. 2, Q is an imaging field of view, in other words, an image effective area, and the X and Y axes are provided in parallel with the mutually perpendicular sides. Reference numeral 21 is an image of the target portion belonging to the object, which in this case is a hole image. W1 and W2 are measurement regions corresponding to the target partial image 21, respectively, and correspond to regions 31 and 32 in the conventional example (see FIG. 5). The point P is the left end of the object image 20 and has a predetermined positional relationship with the target partial image 21, which is a predetermined position in the invention. Wx is an area including the point P with a margin,
In the first area of the invention, Wy partially includes the object image 20, has a predetermined positional relationship with the point P in the X direction, and corresponds to the second area of the invention. In FIG. 2, the X coordinate Xs of the point P is obtained by projecting the object image 20 on the region Wx onto the X axis. This projection detection is performed by the projection detection circuit 7 shown in FIG. By the way, since the Y coordinate of the point P is not obtained by projecting the object image 20 onto the Y axis, the Y of the center of gravity G of the object image 20 in the region Wy is calculated.
Coordinates are substituted. The center of gravity detection is performed by the center of gravity detection circuit 8 shown in FIG. Since FIG. 3 is based on FIG. 2, detailed description thereof is omitted, and the position of the region Wx is fixed, and the region Wy moves in parallel only in the X-axis direction corresponding to the point P. To do. Next, regarding the operation of this embodiment, mainly in FIG.
Description will be made with reference to FIG. 3 and FIG.
FIG. 4 is a flowchart showing the operation. In FIG. 4, a region Wx is generated in step S1 and a region Wy is generated in step S2. In step S3, the X coordinate Xs of the point P when the object image 20 is at the reference position is obtained. In step S4, the center of gravity G
Y coordinate Ys of the point P is obtained instead of the Y coordinate of the point P. In step S5, the X coordinate X1 of the point P when the object image 20 is slightly translated (shifted) from the reference position (see FIG. 3) is obtained, and in step S6, the Y coordinate Y1 of the center of gravity G is changed to the point P. Obtained as a substitute for the Y coordinate. In step S7, the deviations (X1-Xs) and (Y1-Ys) of the point P from the reference position are obtained. In step S8, the measurement areas W1 and W2 are set to the first
The position is corrected by the position correction circuit 9 shown. In steps S9 and S10, the area measurement value A1 for the measurement region W1,
The area measurement value A2 is obtained for the measurement region W2. In addition,
Each area measurement is performed by the area measurement circuit 10 shown in FIG. The following is a determination process based on the area measurement values A1 and A2, and the pass / fail of the shape of the target partial image 21 is determined in steps S11 to S14. Note that this determination processing is performed by the determination circuit 11 in FIG. 1, and a is a predetermined allowable value set for the area measurement value. Further, in the above description of the embodiments, the area value is shown as the characteristic amount, but it goes without saying that another characteristic amount, for example, a perimeter or the like may be used. As is apparent from the above description, the pass / fail of the shape of each target portion belonging to the object in FIGS. 2 and 3 is determined by the target portion being the object even if there is a slight change in the position or the object size of the object from the reference. As long as a predetermined positional relationship is maintained at a predetermined position of, the judgment is accurate. By the way, the above has described the apparatus as an appearance inspection apparatus for the shape of the target portion. However, in general, the device of the present invention is a defect inspection device based on the appearance of a target portion when it is chipped or scratched, and a target recognition device based on the shape of the target portion when it is a character or an unknown object.

【The invention's effect】

According to the present invention, the contour of the object is X,
Even when there are no convex or concave parts when viewed from each direction,
There is an excellent effect that the shape of each target portion is accurately inspected.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment according to the present invention, FIG. 2 is an explanatory view of an imaging visual field when an object is at a reference position in this embodiment, and FIG. 4 is a flow chart showing the operation of this embodiment, FIG. 5 is an explanatory view of the imaging field of view when the object is at the reference position in the conventional example, and FIG. 6 is this object. It is an explanatory view of how to obtain the deviation when the object is deviated. Code Description 1: TV camera, 2: A / D converter, 3: Binarization circuit, 4: Image memory, 5: Measurement area generation circuit, 6: Correction area generation circuit, 7: Projection detection circuit, 8: Center of gravity detection Circuit, 9: Position correction circuit, 10: Area measurement circuit, 11: Judgment circuit.

Claims (1)

[Claims] 1. An apparatus for inspecting the pass / fail of an inspected portion of an object based on an object image obtained by imaging,
A measurement area generating unit for generating a measurement area having a predetermined shape according to the shape of the object portion to be inspected of the object, and the measurement area of the measurement area according to the amount of displacement from the reference position of the object image in the imaging field Position correction means for correcting the position,
A feature amount measuring unit for determining a feature amount of a portion to be inspected in the measurement region, and a determining unit for performing a determination based on an output from the feature amount measuring unit, wherein at least a contour portion of the object image A first region including an image, and a second region partially including the object image at a position separated by a predetermined distance in the X-axis or Y-axis direction from a certain point on the contour in the first region Means for generating an object, a means for detecting end point coordinates on the X axis or the Y axis by projecting the object image in the first area onto the coordinate axes, and a partial image of the object included in the second area. And a reference position of the object image in the X-axis and Y-axis directions based on outputs from the means for detecting the coordinates of the end points and the means for detecting the coordinates of the center of gravity. The appearance inspection apparatus is characterized in that the measurement area is generated in a portion to be inspected of the object by detecting the amount of positional deviation with respect to, and outputting it as a correction amount to the measurement area generating means.