JP3126634B2 - Appearance 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 defect such as a flaw or dirt on the appearance of an inspected object or a defect of the inspected object based on a grayscale image obtained by imaging a spatial region including the inspected object by an imaging means. The present invention relates to a visual inspection method for inspecting a shape and the like.

[0002]

2. Description of the Related Art In general, in this type of appearance inspection method, a spatial region including an object to be inspected is imaged by an imaging device such as an ITV camera, and the density of each pixel in the captured image (that is, the imaging device). The normal part of the object to be inspected and the defect and the background of the object to be inspected are identified based on the amount of received light. That is, a threshold value is set for the pixel density, and binarization is performed using the threshold value, thereby separating the inspection object into a normal part and another part. In order to facilitate this separation, it is common practice to irradiate the object to be inspected with light from an appropriate direction so as to cause an illuminance difference between a normal part of the object and other parts. ing.

[0003]

Conventionally, the threshold value for binarization has been fixedly set, so that the reflectance of the object to be inspected is different, If the amount of irradiated light changes, there is a problem that it is not possible to perform binarization to correctly separate a normal portion and another portion of the inspection object. In other words, there has been a problem that when the appearance of a different object to be inspected is inspected, or when the amount of light applied to the object to be inspected changes, the threshold value must be manually adjusted .

Further, when inspecting the appearance of an object to be inspected, it is better to remove as much as possible an area that does not need to be inspected from the image because the number of pixels to be processed is reduced and the processing efficiency is increased, so that the object is inspected. A mask including only an area is set, and the presence or absence and shape of a defect are recognized only in the mask. However, for a test object having a complicated contour including a bent portion, a mask may be set to include only the test object, or a portion corresponding to a hole, a groove, a projecting portion, or the like formed in the test object. It is difficult to set a mask that removes only the inspection target from the inspection target and leaves the scratches and dirt as the inspection target, and there is a problem that the processing efficiency cannot be sufficiently improved.

The present invention has been made in view of the above circumstances, and an object of the present invention is to automatically set a threshold value for binarization in accordance with an object to be inspected and to set a normal value of the object to be inspected. such portion and the If can <br/> have value if the density difference is relatively small with other parts to be set, yet the appearance inspection method with enhanced sufficiently exclude the processing efficiency region not be inspected To provide.

[0006]

According to the first aspect of the present invention, an inspection window including at least a partial area of an object to be inspected is set in a grayscale image obtained by imaging a spatial area including the object to be inspected by an imaging means. In the method of inspecting the appearance of the inspection object in the inspection window, a plurality of inspection lines that do not intersect each other are set in the inspection window, and a plurality of density measurement points are set on each inspection line. ,
Calculate the mode of the density at the density measurement point for each inspection line,
In addition to setting a density threshold shifted by a specified offset value to at least one of the high density side and the low density side with respect to the mode, each inspection is performed using the density threshold for each inspection line. After extracting exclusion candidate pixels from the inspection window by binarizing the pixels for each line, the number of density measurement points in the non-inspection candidate region, which is a group of adjacent exclusion candidate pixels, is determined. A non-inspection candidate area that is equal to or more than a predetermined number is set as a non-inspection area, and the appearance of the inspection object is inspected only in an inspection target area excluding the non-inspection area from the inspection window.

In this method, an inspection line is set in an inspection window including at least a partial area of the inspection object, a density measurement point is set on the inspection line, and the density of the density measurement point for each inspection line is determined. Since the density measurement points are binarized for each inspection line using the density threshold set based on the mode, the density threshold used for binarization is automatically set according to each inspection object. Is set. In addition , the number of density measurement points in the non-inspection candidate area, which is a group of exclusion candidate pixels obtained by binarization, is determined, and it is determined whether each non-inspection candidate area should be excluded from the inspection window. Since the target area is determined, it is possible to remove a non-inspection area such as a hole or a projection of the inspection object or a conveyor for transporting the inspection object from the exclusion candidate pixels, and as a result, does not become an inspection object. Regions can be sufficiently excluded, leading to an improvement in processing efficiency.

According to the second aspect of the present invention, an inspection window including at least a part of the inspection object is set in a grayscale image obtained by imaging a spatial region including the inspection object by the imaging means. In the method of inspecting the appearance of the object to be inspected, an edge passing through the peak of the density difference between pixels is obtained based on the grayscale image, and a plurality of inspection lines that do not intersect each other are set in the inspection window. Set multiple concentration measurement points on the inspection line,
Calculate the mode of the density at the density measurement point for each inspection line,
In addition to setting a density threshold shifted by a specified offset value to at least one of the high density side and the low density side with respect to the mode, each inspection is performed using the density threshold for each inspection line. After extracting exclusion candidate pixels from the inspection window by binarizing the pixels for each line, the number of density measurement points in the non-inspection candidate region, which is a group of adjacent exclusion candidate pixels, is determined. The above edge is searched outward from each density measurement point on the outer peripheral edge of the non-inspection candidate region that is equal to or more than a predetermined number, and when the edge is detected, the edge surrounding the outer periphery of the non-inspection candidate region is traced by tracing the edge. The number of pixels of the determined edge and the sum of the differential values of the pixels are determined.If the calculated number of pixels and the total of the differential values are each equal to or larger than a predetermined value, the inside of the edge is determined as a non-inspection area, and the inspection is performed. For inspection areas excluding the non-examination region from the window only to inspect the appearance of the object to be inspected.

This method is a further extension of the method according to the first aspect of the present invention. The non-inspection candidate area obtained in the first aspect of the present invention has an error of about the interval between the density measurement points. Since the non-inspection area is often slightly smaller than the area to be excluded from the inspection window, the non-inspection candidate area is corrected so as to be enlarged and the non-inspection area is accurately set.

According to the third aspect of the present invention, each test line is a straight line parallel to each other, and the interval between each pair of adjacent test lines and the interval between each pair of adjacent density measurement points on each test line are fixed. In addition, the positions of the density measurement points on each pair of adjacent test lines are matched in the extension direction of the test line. In the invention according to claim 4, each test line is a straight line parallel to each other, the interval between each pair of adjacent test lines is appropriately set, and the interval between each pair of adjacent density measurement points on each test line is constant. In addition, the positions of the density measurement points on each pair of adjacent test lines are matched in the extension direction of the test line.

According to the fifth aspect of the present invention, each test line is a straight line parallel to each other, and the interval between each pair of adjacent test lines and the interval between each pair of adjacent density measurement points on each test line are fixed. In each pair of adjacent inspection lines, the density measurement points on the other inspection line are positioned at the center of each pair of adjacent density measurement points in the extension direction of the inspection line.

According to the present invention, each inspection line is a straight line parallel to each other, the interval between each pair of adjacent inspection lines is appropriately set, and the interval between each pair of adjacent density measurement points on each inspection line is determined. Is constant, and in each pair of adjacent inspection lines, the density measurement point on the other inspection line is positioned at the center of each pair of adjacent density measurement points in the extension direction of the inspection line.

According to the present invention, each test line is a straight line parallel to each other, the interval between each pair of adjacent test lines is constant, and the interval between each pair of adjacent density measurement points on each test line is determined. It is set appropriately. In the invention of claim 8,
Each test line is a straight line parallel to each other, and the interval between each pair of adjacent test lines and the interval between each pair of adjacent density measurement points on each test line are appropriately set.

According to a third aspect of the present invention, there is provided a method of setting an inspection line and a density measuring point. If the density of the surface of the object to be inspected is substantially uniform, the density measuring point is made uniform. In the case where some distribution occurs in the density of the surface of the object to be inspected, the intervals between the inspection lines and the density measurement points are determined according to the distribution. May be set appropriately. Furthermore, if the density measurement points are arranged in a staggered manner as in the inventions of claims 5 and 6, a non-inspection area can be accurately extracted using a relatively small number of density measurement points.

[0015]

BEST MODE FOR CARRYING OUT THE INVENTION

(Embodiment 1) In this embodiment, an inspection target area is determined according to the procedure shown in FIG. When inspecting the appearance of the inspection object,
The object to be inspected is positioned at a predetermined position, and a spatial region including the object to be inspected is imaged by an imaging device such as an ITV camera. The output of the imaging device is subjected to A / D conversion, and a monochrome grayscale image having a density value corresponding to the amount of received light for each pixel is stored in the frame memory. Here, when imaging the spatial region including the object to be inspected by the imaging device, the object to be inspected is angled such that a difference occurs between the density of a defect such as a scratch or dirt of the object to be inspected and another portion. Light is applied to the light. In the following description, it is assumed that the higher the brightness (ie, the closer to white), the higher the density. Subsequent processing is performed on the grayscale image stored in the frame memory.

[0016] The object to be inspected Q ₁ groove R ₂ is formed, an image of only the object to be inspected Q ₁ is assumed to be as shown in Figure 2.
First, an inspection window D as shown in FIG.
₁ is set (S101). The inspection window D ₁ is
The shape may be a shape that can be easily set, and is set to a rectangular shape here. The inspection window D ₁ is
₁ may be set to include at least a portion, except when performing a visual inspection for the entire region of the object Q _1, need not necessarily include the entire object to be inspected Q _1,
Usually desirable to sufficiently larger than other areas the proportion of the area occupied by the object to be inspected Q ₁ in in the examining window D _1. Here, the object to be inspected Q ₁ is positioned at a predetermined position, the imaging device from being locked in place, the examining window D ₁ is capable of fixedly set regardless of the object to be inspected Q ₁ some, but it may be changed inspection window D ₁ of the shape according to the object to be inspected Q _1. In the image, as shown in FIG. 3, and conveyer R ₁ to be a part of the background against the contours of the object to be inspected Q _1, and the like groove R ₂ formed in the object to be inspected Q ₁ .

[0017] spirit of the present invention, as a region to be inspected, because there to set the excluded areas such as conveyor R ₁ and groove R ₂ from the inspection window D _1, from the inspection window D ₁ by the following steps conveyor R ₁ and groove R exclude ₂ or the like as the non-examination region. However, as shown in FIG. 4, when a defect R ₀ such as a scratch or dirt exists, the defect R ₀ must not be included in the non-inspection area.

Therefore, as shown in FIG. 5, a plurality of inspection lines L _{1 to} L ₁ are arranged at appropriate intervals in an inspection window D _1.
Set _n, to set the density measurement point P _{(x, y)} at appropriate intervals on each inspection line L ₁ ~L _n. Inspection line L ₁ ~L _n
Are set to be the simplest straight lines in the illustrated example and are set parallel to each other, but need not be straight lines, and need not be parallel if they do not cross each other. Further, the distance between adjacent inspection lines L _{1 to} L _n and each inspection line L ₁ to L _n
The interval between the density measurement points P _{(x, y)} on L _n may be set arbitrarily. Here, as these intervals are larger, the number of density measurement points P _{(x, y)} is smaller and processing can be performed at high speed in a shorter time. However, when the interval is too large, the accuracy of determining the non-inspection area decreases. , it is necessary to determine empirically an appropriate size depending on the object to be inspected Q _1. After the density measurement points P _{(x, y)} are set in this way, the density of each density measurement point P _{(x, y)} is determined (S102).

By the way, A / D conversion is performed as described above.
Concentration is a discrete value instead of a continuous value.
For example, it has 256 values. Therefore, the concentration measurement
Point P _{(x, y)}Is set properly, one check
Inspection line L₁~ L_nThe density measurement results in the same value on the
Fixed point P_{(x, y)}Exist (the inspection object Q₁Is a plane
Sometimes, inspection window D is ideal₁Defect R in₀,
Conveyor R₁, Groove R _TwoDensity values except for
). Therefore, the inspection line L₁~ L_nConcentration measurement value for each
P_{(x, y)}Mode (mode) M of the density obtained in step₁~ M_nTo
Ask.

The mode values M _{1 to} M _n obtained in this way should be close to the density values of the normal area of the inspection object Q ₁ . On the other hand, when the background is a shadow, the density of the background area is lower than the mode values M _{1 to} M _n , and the groove portion R ₂ and the recessed defect R ₀ are also the mode _values M _{1 to} M _n. It is considered that the concentration becomes lower than that of the above. In addition, a protruding portion or the like may have a portion where the specular reflection condition is satisfied and the density becomes higher than the mode _values M _{1 to} M _n, and the background may be different depending on the illumination method of the inspection object Q _1. The density may be higher than the mode _values M _{1 to} M _n . Therefore, if the mode M _{1 to} M _n is binarized as a threshold value for the density, it is considered that an exclusion candidate pixel to be excluded from the inspection target area can be extracted.
However, in practice, an area to be inspected may be included in the exclusion candidate pixels due to uneven illuminance or the like. To avoid such inconvenience,
In the present invention, the offset values WO and BO are set on the high density side and the low density side with respect to the mode values M _{1 to} M _n , respectively, and the mode values M _{1 to} M _n are set by the offset values WO and BO. By shifting the light-side density threshold value WS _k (= M
_k + WO) and the dark side density threshold value BS _k = (M _k −B
O) is set (S103). Where the subscript k
Takes a value of 1 to n.

As described above, the proportion of the inspection window D ₁ occupied by the inspection object Q ₁ is set to be sufficiently large, so that the density of the pixels included in the inspection target area of the inspection object Q ₁ is becomes a value closer to the most frequent value M ₁ ~M _n. Therefore, for each density measurement point P _{(x, y)} , the density threshold WS _k , set for each inspection line L _{1 to} L _n ,
The density is binarized by using BS _k , and when the density of the density measurement point P _{(x, y)} is larger than the density threshold value WS _k, it is determined as a bright area candidate point, and the density measurement point P _{(x, y)} and dark region candidate points when the concentration is smaller than the concentration threshold BS _k. However, the concentration threshold WS _k, since BS _k is set for each inspection line L _k, concentration threshold WS _k different for each inspection line L _k, will be used BS _k.

[0022] Thus the concentration threshold WS _k different for each inspection line L _k, by using a BS _k, tends to remove the unevenness of the density distribution by lighting method of the light source. The reason will be described below. Now, it is assumed that the concentration distribution as shown in FIG. 6 is inclined in a specific direction of the object to be inspected Q _1. Such a density distribution is represented by a point A in FIG.
Occurs when the point is closer to the light source than the point B. In FIG. 6, a portion where a step occurs in density is a defect R ₀ . When such a density distribution is generated, it is difficult to detect the low-contrast defect R ₀ even if the average density of the entire area is calculated and the density threshold is set. In such a case
Are inspection lines L ₁ -L which are orthogonal to the concentration gradient direction.
If set to L _n, it is considered that hardly is inclined concentration on each inspection line L ₁ ~L _n, defects R
_It is considered that the detection of ₀ becomes easy . In the present invention , since each of the inspection lines L _{1 to} L _n is binarized using the density threshold values WS _k and BS _k obtained based on the mode values M _{1 to} M _n , a defect with low contrast is obtained. R ₀ also be easy to detect
It is possible to

Excluded candidate pixels consisting of bright region candidate points and dark region candidate points binarized using the density threshold values WS _k , BS _k are generally a plurality of pixels adjacent to each other. is there. That is, since the chunks composed of only the same pixel value in the binary image (0 or 1) is formed, in the following referred to unity exclusion candidate pixels and non-inspection candidate region D _2. Since in the examining window D ₁ has a plurality of non-inspection candidate region D ₂ as shown in FIG. 3 is formed, the label applied to each non-inspection candidate region D ₂ (S10
4). In this way, the stage of applying a label to each non-inspection candidate region D _2, as shown in FIG. 4, it becomes that the label is applied to the defect R ₀ (non-test candidate label is applied area D ₂ is surrounded by a dashed line).

Since the defect R ₀ must be included in the area to be inspected, to find the area to be inspected,
It is necessary to remove the non-test candidate region D ₂ except for defective R ₀ of the inspection window D _1. To realize this process, counts the number of pixels each non-inspection candidate region D _2, by comparing the count value with the non-inspection area determined threshold, labeled for each non-examination candidate region D ₂ Area (number of pixels)
Depending on, to classify non-inspection candidate region D ₂ in the defect R ₀ and other areas. Number of pixels uninspected candidate region D _2, if the use of the label image (image by use of numerical values the label as a pixel value of each pixel) is determined by the pixel value is counted the number of pixels of the same value be able to. In order to distinguish the defect R ₀ from other areas, the number of pixels included in the non-inspection candidate area D ₂ composed of bright area candidate points and the number of pixels included in the non-inspection candidate area D ₂ composed of dark area candidate points are determined. , A non-inspection area determination threshold is set in advance, and when any of the pixels exceeds the non-inspection area determination threshold, the non-inspection candidate area D ₂ is determined not to be the defect R _0. This is a non-inspection area. For example, the non-inspection area determination threshold is
W for the non-inspection candidate area D ₂ composed of bright area candidate points
T, and WB for non examination candidate region D ₂ consisting of dark region candidate points, the number of pixels uninspected candidate regions D ₂ and K. Here, when the non-inspection candidate area D ₂ is composed of bright area candidate points, if K> WT, the non-inspection candidate area D ₂ is determined as a non-inspection area, and the non-inspection candidate area D ₂ is determined from the dark area candidate points. If K> BT, the non-inspection candidate area D ₂
Is determined as a non-inspection area (S105).

[0025] By removing the non-inspection area determined in the above manner from the inspection window D _1, remaining space is inspected area. That is, the conveyor R ₁ or the background or the groove R ₂ is excluded from the inspection target region as a non-inspection region, and the defect R ₀ is not included in the non-inspection region but is included in the inspection target region. By performing image processing according to the inspection item on the inspection target area obtained in this way, the processing amount required for the inspection can be reduced and the processing efficiency can be improved.

An example of the arrangement of the density measurement points P _{(x, y)} will be described below. Shape and spacing and density measurement point P _{(x, y)} of the inspection line L ₁ ~L _n in the above example is not particularly constrained for spacing, inspection line L ₁ ~L _n in the following examples
Are parallel and straight to each other. The extension direction of the inspection lines L _{1 to} L _n is defined as the X direction, and the density measurement point P
Inspection lines L _{1 to} L ₁ in a plane where _{(x, y)} are arranged
_The direction orthogonal to _n is defined as the Y direction.

First, the interval between the inspection lines L _{1 to} L _n is set to be constant, and the interval between the density measurement points P _{(x, y)} on each of the inspection lines L _{1 to} L _n is set to be constant. There is a way. Further, to match the X position of the density measurement point P of the pair of inspection line L ₁ ~L _n adjacent _{(x, y).} That is, the inspection window D unit cell in ₁ sets a grid of a square or rectangular shape, lattice points each concentration measuring point P
_{(x, y)} may be used. By adopting such a setting method, the density measurement point P _{(x, y)} can be easily set.

Second, as shown in FIG. 7, each pair of adjacent
Inspection line L₁~ L_nSet the intervals between
Inn L₁~ L_nMeasurement point P on_{(x, y)}Interval is one
There is a fixed setting method. In addition, each pair of adjacent inspection lines
Inn L₁~ L_nMeasurement point P above_{(x, y)}In the X direction
The positions are the same. That is, the concentration measurement point P
_{(x, y)}Are constant in the X direction and arbitrary in the Y direction.
You. In this setting method, the inspection object Q₁Surface concentration distribution
Is inclined in the Y direction, or the inspection object Q₁On the surface of
A pattern that causes a density change in the Y direction is formed
In such a case, as described above, the concentration measurement point P_{(x, y)}Set
Then, the accuracy of determining the inspection target area increases.

Third, as shown in FIG.
Inspection line L₁~ L_nOf the inspection line
L₁~ L_nMeasurement point P on_{(x, y)}Is constant
There is a setting method. However, the adjacent inspection line L₁
~ L_nMeasurement point P on _{(x, y)}The position in the X direction of
Other inspection lines L to each other₁~ L_nOne adjacent on
Pair concentration measurement point P_{(x, y)}Is set in the center of Toes
The concentration measurement point P_{(x, y)}Are arranged in a staggered pattern
Will be. By adopting such an arrangement, the unit cell
Square or rectangular shape and each inspection line L₁
~ L_nMeasurement point P on_{(x, y)}With equal intervals
Then, the interval in the X direction is halved, and the density
Measurement point P_{(x, y)}If the number of
Leakage is reduced. That is, the concentration measurement point P_{(x, y)}Pieces
Set the number as low as possible to reduce processing time
However, it is possible to reduce the omission of detection in the non-inspection area.
You can do it.

Fourth, the density measurement point P shown in FIG.
_{(x, y)}Each inspection line L₁~ L_nof
Above, each pair of adjacent density measurement points P_{(x, y)}Constant spacing
And the adjacent inspection line L₁~ L_nConcentration measurement point above
P_{(x, y)}Are placed at different positions in the X direction
At this time, as shown in FIG.₁~
L _nThere is a setting method for appropriately setting the interval of. like this
If a simple setting is adopted, the concentration measurement point P_{(x, y)}Arranged in a staggered pattern
As in the case of a row, a relatively small number of concentration measurement points P_{(x , y)}
Can extract the non-inspection area with high accuracy.
Inspection object Q₁Concentration distribution on the surface of is inclined in the Y direction
Case and inspection object Q₁Density changes in the Y direction on the surface of
If such a pattern is formed, check each inspection line.
L₁~ L_nBy setting the interval of
The determination accuracy of the region is increased.

Fifth, as shown in FIG.
Point P_{(x, y)}For each inspection line L₁~ L _nArrange appropriately as above
There are different setting methods. FIG. 10 shows a pair of adjacent inspection lines.
Inn L₁~ L_nAre set constant. like this
Setting is inspected object Q₁Concentration distribution on the surface of
When the inspection object Q₁X direction on the surface of
If a pattern that changes the density is formed on the
If applied, the accuracy of determining the inspection target region is increased.

Sixth, as shown in FIG.
Point P_{(x, y)}For each inspection line L₁~ L _nArrange appropriately as above
And the adjacent inspection line L₁~ L_nAs appropriate
There is a setting method to set. Such a setting method is
Inspection object Q₁Concentration distribution on the surface of
When the inspection object Q₁X direction on the surface of
Or a pattern with a density change in the Y direction
When this setting method is used,
The accuracy of determining the area can be improved.

(Embodiment 2) In this embodiment, Embodiment 1
By further correcting the non-inspection area obtained in the above, the non-inspection area is to be obtained with higher accuracy. That is, as described above, the concentration measurement point P _{(x, y)} is 1
Normally, the non-inspection area E ′ is set at an interval larger than the pixel. Therefore, when the non-inspection area is determined only by the density measurement point P _{(x, y)} , the non-inspection area E ′ is actually set as shown in FIG. It may be smaller than the range to be set as the non-inspection area E.

Therefore, in the present embodiment, the non-inspection area E is determined with high accuracy by enlarging and correcting the non-inspection area E 'obtained in the first embodiment. To enable this process, in the present embodiment performs a differential processing on the concentration in the gray-scale image of the object Q _1, it is previously extracted larger portion of the density change as an edge. This type of processing is generally used as a thinning processing used for extracting the contour of the inspection object. For example, for example, a differential value (a change rate of the density of an adjacent pixel) and a differential direction value (a density of an adjacent pixel) are used. A process in which the line in which the differential value is equal to or larger than a predetermined value is extended in the direction of the differential direction value by the width of one pixel. When such an edge is obtained, the non-inspection area E is surrounded by the edge. Therefore, if the non-inspection area E ′ is enlarged, it is considered that the outer peripheral edge of the non-inspection area E ′ contacts the edge of the non-inspection area E. .

Therefore, as shown in FIG.
Processing up to S105 is performed in the same procedure as in the first embodiment, and the outer peripheral edge of the obtained non-inspection area E 'is enlarged and corrected. The enlargement correction process is performed in the following procedure. First, an edge is searched for one pixel at a time in a spiral shape with each density measurement point P _{(x, y)} on the outer peripheral edge of the non-inspection area E 'as a center.
By performing such a search, a point on the edge can always be detected. Therefore, a point on the edge is detected for each density measurement point P _{(x, y)} , and further, a point on the detected edge is detected. The edges are connected as lines by tracing the edges pixel by pixel. That is, one of the concentration measurement points P
_{If the} edge is traced from a point on the edge detected corresponding to _{(x, y)} , it reaches a point on the edge detected corresponding to another density measurement point P _{(x, y).} By sequentially performing such processing, edges can be connected as lines (S106). If the edge obtained in this way is the edge of the non-inspection area E, the number of pixels on the edge should be equal to or greater than a predetermined value, and the sum of differential values on the edge should be a relatively large value. (In other words, the difference in brightness is large across the edge of the non-inspection area E), the number of pixels and the sum of the differential values are compared with predetermined thresholds for determination, and the number of pixels and the differential values are determined. Are determined as the edges of the non-inspection area E (S10).
7). Subsequent processing is the same as in the first embodiment.

[0036]

According to the first aspect of the present invention, an inspection line is set in an inspection window including at least a partial region of an inspection object, and a density measurement point is set on the inspection line.
Since the density measurement point is binarized for each inspection line using the density threshold set based on the mode of the density of the density measurement point for each inspection line, the density threshold used for binarization Is automatically set according to each inspection object. In addition , the number of density measurement points in the non-inspection candidate area, which is a group of exclusion candidate pixels obtained by binarization, is determined, and it is determined whether each non-inspection candidate area should be excluded from the inspection window. Since the target area is determined, it is possible to remove a non-inspection area such as a hole or a protrusion of the inspection object or a conveyor that conveys the inspection object from the exclusion candidate pixels, and as a result, does not become an inspection object. There is an advantage that the region can be sufficiently excluded, leading to an improvement in processing efficiency.

The second aspect of the present invention is an extension of the method of the first aspect of the present invention, wherein the non-inspection candidate area obtained in the first aspect of the present invention has an error of about the interval between the density measurement points and actually has an error. Since the non-inspection area is often slightly smaller than the area to be excluded from the inspection window, the non-inspection area can be accurately set by correcting the non-inspection candidate area to be enlarged.

The invention according to claims 3 to 8 is a preferred method for setting an inspection line and a density measurement point, wherein the density measurement point is determined if the density of the surface of the inspection object is substantially uniform. Is desirably distributed uniformly, and when there is some distribution in the concentration of the surface of the inspection object,
The intervals between the inspection lines and the intervals between the density measurement points may be appropriately set according to the distribution as in the inventions of claims 4, 6, 7, and 8. Furthermore, if the density measurement points are arranged in a staggered manner as in the inventions of claims 5 and 6, a non-inspection area can be accurately extracted using a relatively small number of density measurement points.

[Brief description of the drawings]

FIG. 1 is a flowchart showing a procedure of a first embodiment.

FIG. 2 is a diagram showing an inspection object used for describing the first embodiment.

FIG. 3 is a diagram illustrating a relationship between an inspection object, an inspection window, a non-inspection candidate area of an exclusion candidate pixel, and the like in the first embodiment.

FIG. 4 is a diagram showing a state including a non-inspection candidate area of an exclusion candidate pixel in the first embodiment.

FIG. 5 is a diagram illustrating an example of setting a density measurement point according to the first embodiment.

FIG. 6 is a diagram illustrating a reason for setting an inspection line in the first embodiment.

FIG. 7 is a diagram illustrating an example of setting a density measurement point according to the first embodiment.

FIG. 8 is a diagram illustrating an example of setting a density measurement point according to the first embodiment.

FIG. 9 is a diagram illustrating a setting example of density measurement points according to the first embodiment.

FIG. 10 is a diagram illustrating an example of setting a density measurement point according to the first embodiment.

FIG. 11 is a diagram illustrating an example of setting a density measurement point according to the first embodiment.

FIG. 12 is a flowchart showing a procedure according to the second embodiment.

FIG. 13 is a diagram showing the concept of the second embodiment.

[Explanation of symbols]

D ₁ Inspection window D ₂ Non-inspection candidate area P _{(x, y)} concentration measurement point Q ₁ Inspection object R ₁ Conveyor R ₂ Groove R ₀ Defect

Claims (8)

(57) [Claims] An inspection window including at least a partial region of an inspection object is set in a grayscale image obtained by imaging a spatial region including the inspection object by an imaging unit, and the inspection window of the inspection object in the inspection window is set. In the method of inspecting appearance, a plurality of inspection lines that do not intersect each other are set in an inspection window, and a plurality of density measurement points are set on each inspection line, and the density of the density measurement points is set for each inspection line. Of the mode, set a density threshold shifted from the mode by at least one of the high density side and the low density side by a specified offset value, and set the density threshold for each inspection line. After extracting exclusion candidate pixels from the inspection window by binarizing the pixels for each inspection line using the threshold, the pixels in the non-inspection candidate region, which is a group of adjacent exclusion candidate pixels, are extracted. The number of density measurement points is determined, and a non-inspection candidate area in which the number is equal to or greater than a predetermined number is defined as a non-inspection area, and the appearance of the inspection object is inspected only in an inspection target area excluding the non-inspection area from the inspection window. Features a visual inspection method. 2. An inspection window including at least a partial area of an object to be inspected is set in a grayscale image obtained by imaging a spatial area including the object to be inspected by an imaging unit. In the method of inspecting the appearance, an edge passing through the peak of the density difference between pixels is determined based on the grayscale image, a plurality of inspection lines that do not intersect each other are set in the inspection window, and a plurality of inspection lines are set on each inspection line. The number of density measurement points is set, the mode of the density at the density measurement point is determined for each inspection line, and the mode is biased by at least one of the high density side and the low density side by the specified offset value. Extraction candidate pixels are extracted from the inspection window by setting the shifted density threshold and binarizing the pixels for each inspection line using the density threshold for each inspection line. After that, the number of density measurement points in the non-inspection candidate area, which is a group of adjacent exclusion candidate pixels, is determined, and the number is determined from each density measurement point on the outer peripheral edge of the non-inspection candidate area in which the number is equal to or greater than a predetermined number. The edge is searched in the direction, and when the edge is detected, the edge is traced to determine an edge surrounding the outer periphery of the non-inspection candidate area, and the number of pixels of the determined edge and the sum of differential values of the pixels are obtained. If the calculated number of pixels and the sum of the differential values are respectively equal to or more than predetermined values, the inside of the edge is regarded as a non-inspection area, and the appearance of the inspection object is inspected only in the inspection target area excluding the non-inspection area from the inspection window. A visual inspection method characterized by the following. 3. Each inspection line is a straight line parallel to each other,
The interval between each pair of adjacent test lines and the interval between each pair of adjacent density measurement points on each test line are constant,
3. The visual inspection method according to claim 1, wherein the positions of the density measurement points on each pair of adjacent inspection lines are matched in the extension direction of the inspection line. 4. Each inspection line is a straight line parallel to each other,
The interval between each pair of adjacent test lines is appropriately set, the interval between each pair of adjacent density measurement points on each test line is fixed, and the position of the density measurement point on each pair of adjacent test lines is determined. 3. The visual inspection method according to claim 1, wherein the inspection lines are aligned in an extension direction of the inspection line. 5. Each inspection line is a straight line parallel to each other,
The interval between each pair of adjacent test lines and the interval between each pair of adjacent density measurement points on each test line are constant,
And a pair of adjacent inspection lines, wherein the density measurement points on the other inspection line are located at the center of the pair of adjacent density measurement points in the extension direction of the inspection line. Item 2. An appearance inspection method according to Item 2. 6. Each inspection line is a straight line parallel to each other,
The interval between each pair of adjacent test lines is appropriately set, the interval between each pair of adjacent density measurement points on each test line is constant, and each pair of adjacent test lines is on the other test line. 3. The appearance inspection method according to claim 1, wherein the density measurement point is located at the center of each of the pair of density measurement points adjacent to each other in the extension direction of the inspection line. 7. Each inspection line is a straight line parallel to each other,
3. The visual inspection according to claim 1, wherein an interval between each pair of adjacent inspection lines is constant, and an interval between each pair of adjacent density measurement points on each inspection line is appropriately set. Method. 8. Each inspection line is a straight line parallel to each other,
3. The visual inspection method according to claim 1, wherein an interval between each pair of adjacent inspection lines and an interval between each pair of adjacent density measurement points on each inspection line are appropriately set.