JP2654294B2 - Edge detection method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an edge detecting method for obtaining an edge from a gray image.

[0002]

2. Description of the Related Art An example of a conventional edge detection method is as follows.
There is a multi-value image contour detection method proposed in Japanese Patent Application Laid-Open No. 2-171875. In this method of detecting the contour of a multi-valued image, the luminance of the lowermost row among the luminances of N rows and N columns (N is an odd number of 3 or more) around a reference point for determining the contour of the image stored in the memory is determined. Using the difference Yd between the sum and the sum of the brightness of the top row and the difference Xd between the sum of the brightness of the rightmost column and the sum of the brightness of the leftmost column, the magnitude of the direction vector having Yd and Xd as elements, that is, Yd The square root of ² + Xd ² is obtained, and if the magnitude of this direction vector is equal to or greater than a certain threshold value, it is determined that a contour exists. Then, the above-mentioned contour detection is first performed by 3 ×
Starting with three pixels, if the magnitude of the direction vector obtained thereby does not exceed the threshold value, the value of N is increased to recalculate the magnitude of the direction vector.

[0003]

However, in the above-described edge detection method, the direction vector is first obtained from the luminance of a certain area, and if the threshold value is not exceeded, the area is enlarged and the calculation is performed again. There must be. For this reason, there is a disadvantage that the processing time becomes long. For example, in the case of finding the edge of two intersecting works, it is highly likely that the process of redoing the above operation must be repeated many times, and the edge detection method is an appropriate method. It cannot be said that.

[0004] The present invention has been made in view of the above points, and an object of the present invention is to provide an edge detection method capable of performing high-speed and stable edge detection.

[0005]

According to the present invention, in order to achieve the above object, two intersecting workpieces are imaged and captured.
Each of the grayscale images is obtained , and a plurality of masks are set in an area that crosses the work on the grayscale image and is larger than the width, and a search is made to at least one side starting from a pixel in the mask having the maximum light amount. Then, a pixel having a differential value equal to or larger than a threshold value is obtained, and the obtained pixel is defined as an edge of one of the intersecting workpieces. Along the picture
A pixel having a predetermined direction code obtained by coding the elementary differential direction value moves the mask to a position exceeding a predetermined threshold value for determining that an edge exists , and setting the threshold value to
The series of pixels that exceed is defined as the edge of the other workpiece.

[0006] It is to be noted that the work is imaged and each gray-scale image is formed.
An image is obtained, an arbitrary pixel on the grayscale image is set as a starting point, and a search is performed for a plurality of pixels in a predetermined direction.
The operation of obtaining the sum of the differential values of the pixels whose value is in the differential direction code value within a predetermined range is repeated while shifting the start pixel of the search, and the sum of the differential values obtained at the current search position is used for the previous search. If the difference is larger than the sum of the differential values at the position, the above operation is continued. If the difference is smaller, the edge of the previous search position is set as the edge. It may be used in place of the above method.

Further, in order to prevent erroneous detection of edges due to image noise, the above-mentioned work is imaged and
While obtaining each grayscale image, starting from an arbitrary pixel on the grayscale image and searching for a plurality of pixels in a predetermined direction,
The operation of obtaining the sum of the differential values of the pixels in which the differential direction value of the pixel is within a predetermined range is repeated while shifting the search start pixel, and the sum of the differential values obtained at the current search position is obtained. Is compared with a preset threshold value of the sum of the differential values. When the sum of the differential values is greater than the threshold value of the sum of the differential values, the sum of the differential values obtained at the current search position is obtained. Is compared with the sum of the differential values at the previous search position.If the sum of the differential values obtained at the current search position is larger than the sum of the differential values at the previous search position, continue the above operation. If it is smaller, it is preferable to use a method in which the previous search position is set as an edge instead of the second aspect of the present invention.

Further, according to the method of claim 2 or 3, it is possible to prevent erroneous detection of edges due to image noise, and to calculate the sum of differential values obtained at the current search position and a preset differential value. When comparing with the threshold value of the sum of the values, the edge can be reliably detected even when the sum of the differential values does not become smaller than the threshold value of the sum of the differential values. In order to achieve this, as described in claim 4, the work is imaged to obtain respective grayscale images.
At the same time, starting from an arbitrary pixel on the grayscale image and searching for a plurality of pixels in a predetermined direction, the differential direction value of the pixel is copied.
The operation of obtaining the sum of the differential values of the pixels in which the coded differential direction code values are within a predetermined range is repeated while shifting the start pixel of the search, and the sum of the differential values obtained at the current search position,
A comparison may be made with a preset threshold value of the sum of the differential values, and when the sum of the differential values is larger than the threshold value of the sum of the differential values, the search position may be set as an edge.

Furthermore, it is possible to prevent erroneous edge detection due to image noise, and compare the sum of the differential values obtained at the current search position with a preset threshold value of the sum of the differential values. Another method for reliably detecting an edge even when the sum of the differential values does not become smaller than the threshold value of the sum of the differential values is described in claim 5. Then, the above work is imaged and
While obtaining each grayscale image, starting from an arbitrary pixel on the grayscale image and searching for a plurality of pixels in a predetermined direction,
The operation of obtaining the sum of the differential values of the pixels whose differential direction code values obtained by encoding the differential direction values of the pixels are within a predetermined range is repeated while shifting the start pixel of the search, and this operation is performed over the entire preset search range. Search, find the largest sum of the differential values for each search pixel , and search with the largest sum of the differential values
Pixels may be edges.

[0010]

The present invention has the above-described structure,
The edge of one workpiece is determined using the mask, and the edge of the other workpiece can be detected simply by moving the mask with the direction code along the edge of the one workpiece, and the edge can be detected at high speed. In addition, according to this method, the edge detection is obtained by the grayscale image processing, so that the edge detection can be performed stably without being affected by the lighting condition and the shape of the work.

[0011]

【Example】

(Embodiment 1) FIGS. 1 to 7 show an embodiment of the present invention.
In this embodiment, as shown in FIG. 2, an inspection object is imaged by an image input device 1 such as a television camera, and the density of each pixel is converted into a digital signal by an A / D converter 2, and then the preprocessing is performed. By performing the following preprocessing in the unit 3, a differential image, a differential direction code image, and an edge image are obtained in addition to the original image obtained by the A / D conversion unit 2.

In this preprocessing, first, a differential / edge extraction process is performed. In the present algorithm, spatial differentiation processing is performed using a local parallel window of 3 × 3 pixels as the first stage of image processing. FIG. 3 shows the concept of this processing. Attention image E
Then, a local parallel window W of 3 × 3 pixels including eight pixels A to D and F to I around the pixel E is set as an original image as an input image. Here, A to I are 8-bit density values of each pixel. Assuming that the vertical and horizontal density changes of the pixel E are ΔV and ΔH, respectively, ΔV = (A + B + C) − (G + H + I) (1) ΔH = (A + D + G) − (C + F + I) (2) The differential absolute value | e | _E of this pixel E is | e | _E = (ΔV ² + ΔH ² ) ^1/2 (3) Further, the differential direction value ∠E _E of the pixel E ^{_{is, ∠e E = tan -1 (ΔV}} / ΔH + π / 2) ... a (4).

That is, data of eight pixels around the pixel E are taken out at the same time, the above operation is performed, and the result is used as data of the pixel E. The above calculation is 256 × 256
By performing the process on the entire screen of the pixels, it is possible to extract a portion where the density change is large, such as an outline or a defect of the object in the screen, and the direction of the change. | E in equation (3)
An image in which | _E is expressed in terms of density (brightness) for all pixels is called a differential image, and an image in which ∠e _E in Expression (4) is coded is called a differential direction code image.

Next, an edge line extraction process is performed on the differential image. FIG. 4A is an example of an image of the differential absolute value. A high mountain portion in this image indicates that the density change in the original image is large. In areas where the change in concentration is gradual,
The foothills of these mountains widen and the outlines become thicker. Therefore, as shown in FIG. 4B, only the ridge lines of these mountains are extracted. This processing is the ridge line extraction processing.

In practice, attention is paid to the absolute value of the differential of each pixel, and an edge that is larger than the absolute value of the differential of surrounding pixels is defined as a ridgeline. By the processing up to this point, all edges are extracted regardless of the magnitude of the value in the differential absolute value image. Therefore,
This ridge line includes unnecessary small mountains due to noise or the like (a and c in FIG. 4B).
As shown in the above, a and c are removed by slicing with a predetermined threshold value SL. Therefore, finally, only the thick lines b and b 'are extracted.

A ridge line of a larger mountain (hereinafter, referred to as an edge) is extracted in the above-described differential / ridge line extraction process, but the ridge line tends to be discontinuous as shown in FIG. 4B. Therefore, next, a process called an edge extension process is performed, and the points A to B are connected as shown by a dotted line in FIG. 4B. In this process, the following evaluation function f (e _j ) is calculated. f (e _j ) = | e _j | · cos (∠e _j −∠e ₀ ) · cos ((j−1) π / 4−∠e ₀ ) (5) where e ₀ : central pixel density derivative data e _j of (E in Figure 3): means that the larger the value of the differential data the evaluation function of the adjacent pixels (a to I except E in FIG. 3), likely to extend its edge direction .

In this edge extension processing, A in FIG.
The evaluation function of Expression (5) is sequentially calculated with respect to the adjacent images starting from the point, and the evaluation function is extended in the direction indicating the maximum value.
If the point collides with the original edge, the processing is stopped.
The edge obtained at this time is a point at which the brightness change point on the original image is represented by a line drawing. Here, a line image obtained by extracting a brightness change point as an outline from the original image is called an edge image.

By the above processing, a differential image, a differential direction code image, and an edge image are obtained, respectively. The configuration of these images will be described with reference to FIG. In FIG. 5, the addresses on the four images are common, and are set to an arbitrary point P (x, y). The original image f ₁ is an input gray-scale image, which is usually represented by a brightness level of 8 bits (256 gradations). Point P
Is a = f ₁ (x, y) (0 ≦ a ≦ 255).

Assuming that the gradation of the differential value in the differential image f ₂ is, for example, 6 bits, the differential value b at the point P is expressed as b = f ₂ (x, y) (0 ≦ a ≦ 63). If the differential direction in the differential direction code image f ₃ is coded, for example, in 16 directions, the differential direction code c at the point P can be written as c = f ₃ (x, y) (0 ≦ a ≦ 15).

Since the edge image f ₄ is a 1-bit image in which the brightness change point on the original image is extracted as a line drawing, the line drawing portion is “1” and the background is “0”. Therefore, a pixel which is “1” is called an edge flag. When the point P is an edge flag, f ₄ (x, y) = 1, and when the point P is a background, f ₄ (x, y) = 0. Is done.

A method for performing edge detection using each image obtained by the above-described image processing will be described below. In the case of the present embodiment, a case where two works 11 intersect with each other will be described below as an example. In the present embodiment, as shown in FIG. 1, a plurality of masks 12 are set on an image including the intersection of the two works 11 in a region that crosses the work 11 and is larger than the width thereof. Note the case of ,, Figure 1 is set to four masks 12 ₁ to 12 _4.
Then, an average light amount of the mask 12 21 _{to 24} each,
The center of the mask 12 having the highest average light amount is set as the start point of the first edge detection. In other words, this is a process for setting a starting point for the first edge detection inside the work 11. Since the work 11 specularly reflects light from the light source and has a high luminance, the work 11 Can be set as the start point of the first edge detection.

Next, a search is made on both sides from the start point to find a point where an edge flag exists on the same y address as shown in FIG. 6 for more than a predetermined number of pixels. I do. Here, 1 in FIG. 6 is an edge flag and 0 is a background. In this case, the threshold is set to 3, and yi is an edge address. In the above case, since the search is performed on both sides from the start point, two first edges are obtained. However, the search may be performed on only one side. Further, in the above-described case, the detection accuracy of the first edge is set to be higher as the point where the edge flag exists in the same y address as the first edge or more at a pixel set in advance. Depending on 12, a point at which the differential value is equal to or larger than the threshold value may be set as the first edge.

Furthermore, n outside these first edges
A mask 13 having a size of × m pixels is set.
3 is moved along the edge flag in the second edge search direction indicated by the arrow in the figure. In this case, the n × m pixel area is raster-scanned one pixel at a time, and pixels having a predetermined range of differential direction values are identified as differential direction code images (f in FIG. 5).
₃ ) Read from the top and find the total number sum of the pixels.
Then, if the pixel total sum is larger than the threshold value _{SL 1 (sum> SL 1)} , the edge is present, n ×
The x address on the second edge search direction side of the m pixel area is defined as an edge address. In the case of FIG. 1, xi is an edge address. FIG. 7 is a flowchart summarizing the edge detection method.

By performing edge detection as described above, edge detection can be performed at high speed and stably. That is, when detecting the edges of two intersecting workpieces as described above,
The edge of the work 11 intersecting with the work 11 can be detected simply by finding the first edge using the mask and moving the mask with the direction code along the first edge. Detection can be performed.
Further, in the case of a black-and-white binary image, the illumination of the work 11 is not uniform and the shape of the work 11 is not constant. Is not stable. However, in the case of the present embodiment, since edge detection is obtained by grayscale image processing, edge detection can be performed stably without being affected by the lighting conditions and the shape of the work.

(Embodiment 2) FIGS. 8 and 9 show another embodiment of the present invention. In this embodiment, as shown in FIG. 8, an arbitrary point on an image of the workpiece 11 is set as a starting point P, a plurality of pixels (a dots) are searched in a first search direction indicated by a downward arrow in the figure, and differentiation is performed. A differential direction value is read from the direction code image (f ₃ ), and a pixel whose differential direction value is within a predetermined range is determined. Then, a differential absolute value is read from the differential image (f _{2 in} FIG. 5) for the pixel and added. It is assumed that the total number of differential absolute values is SUM.

Next, the search start point for one pixel (one dot) is moved in the second search direction indicated by the left arrow in the figure, and the same processing as in the above case is performed. In this case, the previous processing result (SUM _old ) and the current processing result (SUM _old )
_new ). At this time, the previous processing result (SU
If the current processing result (SUM _new ) is larger than (M _old ), that is, if SUM _new > SUM _old , the search start point is moved by one pixel (1 dot) in the second search direction. Repeat the process.

If the current processing result (SUM _new ) is smaller than the previous processing result (SUM _old ), that is, if SUM _new ≦ SUM _old , the search start position of the previous processing result (SUM _old ) Is an edge. FIG. 9 is a flowchart summarizing the above processing. This embodiment can be used as a method for detecting the first edge in the first embodiment. After the detection of the first edge, the first embodiment is used.
By adopting the method described in the above, the edge of the intersecting work 11 can be detected.

(Embodiment 3) FIGS. 10 and 11 show the present invention.
Another embodiment will be described. In the case of Embodiment 2 described above,
From the fulcrum P, the previous processing result (SUM_old) And this time
Processing result (SUM _new) Was compared with
However, in this case, as shown in FIG.
If there is N, the actual edge is P_EBut also
Regardless, the image noise N may be detected as an edge.
There is.

Therefore, in this embodiment, the following operation is performed after obtaining the total number SUM of the differential absolute values in the second embodiment. In other words, the total number of differential absolute values SUM is determined by a preset threshold value THD of the sum of differential absolute values (shown by a horizontal line in FIG. 11).
Compare with Then, the total number of differential absolute values SUM is larger than the threshold value THD of the sum of differential absolute values, that is, S
When UM> THD, the previous processing result (SUM _old ) described in the second embodiment and the current processing result (SU
M _new ) to perform edge detection processing. Note that the processing of this embodiment is summarized as a flowchart shown in FIG.

In this manner, the total number of differential absolute values SU
When M is small, the edge determination process is not performed, and FIG.
Thus, the influence of the image noise N such as 1 can be eliminated. (Embodiment 4) FIGS. 12 and 13 show still another embodiment of the present invention. In the second and third embodiments, the previous processing result (SUM _old ) and the current processing result (SUM _old )
when comparing _new) and, as shown in FIG. 13, the previous processing result (SUM _old) than even the current processing result (SU
If the state of M _new ) is larger, the edge detection may not be performed.

Therefore, in the present embodiment, as shown in FIG. 12, after calculating the total number of differential absolute values SUM described in the second embodiment, the total number of differential absolute values SUM is calculated based on a preset differential absolute value. Compared to the sum threshold THD (shown by the horizontal line in FIG. 13), the total number of differential absolute values SUM is larger than the threshold THD of the sum of differential absolute values, that is, SUM>
When THD is established, the search position is defined as an edge. In this case, if SUM> THD is not established, the search start point is moved by one pixel (one dot) in the second search direction in FIG. 8 and the above processing is repeated.

In this way, no erroneous edge detection due to image noise occurs as in the third embodiment, and FIG.
As shown in FIG. 3, even when a state in which the current processing result (SUM _new ) is larger than the previous processing result (SUM _old ) continues, the edge can be detected. (Embodiment 5) FIG. 14 shows still another embodiment of the present invention. The present embodiment does not cause erroneous detection of edges due to image noise, and as shown in FIG.
This is another embodiment in which an edge can be detected even when a state in which the current processing result (SUM _new ) is larger than UM _{ol d} ) continues.

In the present embodiment, the process of obtaining the total number of differential absolute values SUM described in the second embodiment is repeated while moving the search start point for one pixel (one dot) in the second search direction in FIG. This operation is performed for the entire search range set in advance. Then, the total number SUM of differential absolute values at each search position is calculated as SUM1, SUM2, SUM for each search position.
UM3,... SUMn, the largest SUM _(MAX) among the total number of differential absolute values SUM is obtained, and this SU
The search position at which M _(MAX) is obtained is defined as an edge.

In the method of this embodiment, no matter what image noise is present, if the total number of differential absolute values SUM is larger than the sum of image noise, it is possible to detect edges stably. Can be.

[0035]

According to the first aspect of the present invention, as described above, when two intersecting works are imaged to obtain respective grayscale images.
In both cases, a plurality of masks are set in an area that traverses the workpiece on the grayscale image and is larger than the width, and a search is made to at least one side starting from a pixel in the mask having the largest light amount, and a differential value is determined. A pixel having a value equal to or larger than the value is obtained, and this is defined as an edge of one of the intersecting workpieces.A plurality of masks having a size including a plurality of pixel regions are set outside the edge, and along the edge, the differentiation direction of the pixel is determined. Code the value
Pixels having a predetermined direction code ized may be present edge
The mask is moved to a position exceeding a predetermined threshold value for judging that a series of pixels exceeding the threshold value is used as the edge of the other work, so that the edge of one work is obtained using the mask, Further, the edge of the other work can be detected simply by moving the mask by the direction code along the edge of the one work, and the edge can be detected at high speed. In addition, according to this method, the edge detection is obtained by the grayscale image processing, so that the edge detection can be performed stably without being affected by the lighting condition and the shape of the work.

According to a second aspect of the present invention, two intersecting works are imaged to obtain respective grayscale images.
Starting from an arbitrary pixel on the grayscale image and searching for a plurality of pixels in a predetermined direction, the differential direction value of the pixel is coded.
The operation of obtaining the sum of the differential values of the pixels whose differential direction code values are within a predetermined range is repeated while shifting the start pixel of the search, and the sum of the differential values obtained at the current search position is used as the differential at the previous search position. If greater than the sum of the values will continue the operation, when it is smaller by using the method of the edge of the previous search position, it first detects the edge of one of the work in the invention of the claim 1 it is possible and this.

Further, as described in claim 3, the workpiece is
Imaging to obtain each grayscale image and the grayscale image
Starting from an arbitrary pixel on the image and extending multiple pixels in a predetermined direction
The operation of obtaining the sum of the differential values of the pixels whose differential direction code values obtained by encoding the differential direction values of the pixels are within a predetermined range is repeated while shifting the start pixel of the search, and is obtained at the current search position. The sum of the differential values is compared with a preset threshold value of the sum of the differential values, and when the sum of the differential values is larger than the threshold value of the sum of the differential values, the value obtained at the current search position is obtained. Compare the sum of the differential values with the sum of the differential values at the previous search position.If the sum of the differential values obtained at the current search position is larger than the sum of the differential values at the previous search position, If the above operation is continued and the previous search position is set to be an edge when the value is smaller, the sum of the differential values smaller than the threshold value of the sum of the differential values can be excluded from the object for edge detection. As a result, noise due to image noise smaller than the threshold value of the sum of differential values Erroneous detection of the di can be prevented.

Further, as described in claim 4, the word
Images to obtain their respective grayscale images,
Starting from an arbitrary pixel on the light image , multiple pixels in a predetermined direction
The operation of searching for the difference and calculating the sum of the differential values of the pixels in which the differential direction code value of the pixel is within a predetermined range is repeated while shifting the start pixel of the search, and is obtained at the current search position. The sum of the differentiated values is compared with a preset threshold value of the sum of the differential values. When the sum of the differential values is larger than the threshold value of the sum of the differential values, the search position is regarded as an edge. For example, the sum of the differential values smaller than the threshold value of the sum of the differential values can be excluded from the object for edge detection, and therefore, the error of the edge due to image noise smaller than the threshold value of the sum of the differential values can be excluded. Detection can be prevented, and when the sum of the differential values obtained at the current search position is compared with a preset threshold value of the sum of the differential values, the sum of the differential values becomes Even when it does not fall below the threshold, Not perform the detection of the edge.

Further, the work is photographed.
The image was obtained to obtain each grayscale image, and starting from an arbitrary pixel on the grayscale image , a plurality of pixels were searched in a predetermined direction, and the differential direction value of the pixel was coded. The operation of calculating the sum of the differential values of the pixels whose differential direction code values are within a predetermined range
This operation is repeated while shifting the start pixel of the search, and this operation is performed over the entire search range set in advance, the largest sum of the differential values for each search pixel is obtained, and the search pixel having the maximum sum of the differential values is obtained. Is an edge, no matter what image noise is present, if the total number of differential absolute values is larger than the total sum of image noise, erroneous detection due to image noise does not occur, and the edge is reliably detected. Can be detected.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing an edge detection method according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a configuration of an image processing apparatus using the above method.

FIG. 3 is an explanatory diagram of a spatial differentiation process as a first stage in the above device.

FIG. 4 is an explanatory diagram of a ridge line extraction / edge extension process according to the first embodiment;

FIG. 5 is an explanatory diagram showing an image handled in the embodiment.

FIG. 6 is an explanatory diagram of a first edge detection method in Embodiment 1;

FIG. 7 is a flowchart showing a process for an edge detection method.

FIG. 8 is an explanatory diagram showing another edge detection method.

FIG. 9 is a flowchart showing a process for an edge detection method according to the embodiment.

FIG. 10 is a flowchart showing still another edge detection process.

FIG. 11 is an explanatory diagram of an edge detection method according to the embodiment.

FIG. 12 is a flowchart showing still another edge detection process.

FIG. 13 is an explanatory diagram of an edge detection method according to the embodiment.

FIG. 14 is a flowchart illustrating still another edge detection process.

[Explanation of symbols]

 11 Work 12, 13 Mask

Claims (5)

(57) [Claims] 1. A edge detection method for detecting the two intersecting workpiece edge, which by imaging the workpiece
Each of the grayscale images is obtained , and a plurality of masks are set in an area that crosses the work on the grayscale image and is larger than the width, and a search is made to at least one side starting from a pixel in the mask having the maximum light amount. Then, a pixel having a differential value equal to or larger than a threshold value is obtained, and the obtained pixel is defined as an edge of one of the intersecting workpieces. Along the picture
A pixel having a predetermined direction code obtained by coding the elementary differential direction value moves the mask to a position exceeding a predetermined threshold value for determining that an edge exists , and setting the threshold value to
An edge detection method, wherein a series of pixels that exceed each other is formed as an edge of another workpiece. 2. An edge detection method for detecting an edge of a work , wherein said work is imaged and a gray image
With obtaining, by starting from any pixel on the concentration pale image, searching in a predetermined direction by a plurality of pixels, the differential direction of the pixel
The operation of obtaining the sum of the differential values of the pixels whose value is in the differential direction code value within a predetermined range is repeated while shifting the start pixel of the search, and the sum of the differential values obtained at the current search position is used for the previous search. An edge detection method characterized in that the above operation is continued when the difference is larger than the sum of the differential values at the position, and when the difference is smaller, the previous search position is set as the edge. 3. An edge detection method for detecting an edge of a work , wherein the work is imaged and a gray image
With obtaining, by starting from any pixel on the concentration pale image, searching in a predetermined direction by a plurality of pixels, the differential direction of the pixel
The operation of obtaining the sum of the differential values of the pixels in which the differential direction code value whose value is coded is within a predetermined range is repeated while shifting the search start pixel , and the sum of the differential values obtained at the current search position is set in advance. The sum of the differential values obtained is compared with the threshold value of the sum of the differential values, and when the sum of the differential values is greater than the threshold value of the sum of the differential values, the sum of the differential values obtained at the current search position and the previous search value Compare with the sum of the differential values at the position, and if the sum of the differential values found at the current search position is larger than the sum of the differential values at the previous search position, continue the above operation. An edge detection method characterized in that the previous search position is used as an edge. 4. An edge detection method for detecting an edge of a work , wherein said work is imaged and a gray image
With obtaining, by starting from any pixel on the concentration pale image, searching in a predetermined direction by a plurality of pixels, the differential direction of the pixel
The operation of obtaining the sum of the differential values of the pixels in which the differential direction code value whose value is coded is within a predetermined range is repeated while shifting the search start pixel , and the sum of the differential values obtained at the current search position is set in advance. An edge detection method comprising: comparing a threshold value of a sum of differential values obtained with the threshold value; and when the sum of the differential values is larger than the threshold value of the sum of differential values, uses the search position as an edge. 5. An edge detection method for detecting an edge of a work , wherein the work is imaged and a gray image
With obtaining, by starting from any pixel on the concentration pale image, searching in a predetermined direction by a plurality of pixels, the differential direction of the pixel
The operation of obtaining the sum of the differential values of the pixels in which the differential direction code value whose value is coded is within a predetermined range is repeated while shifting the start pixel of the search, and this operation is performed over the entire preset search range, and each search is performed. edge detection method characterized by seeking the largest one in the sum of the differential value of each pixel, and the search pixel having the sum of the maximum differential value as an edge.