JPS61293754A - Image processing method for tool wear measurement - Google Patents

Abstract

PURPOSE:To have automatic decision of the threshold value for the brightness to an appropriate value by setting a wind within an zone including the worn part of a tool, the other part of tool and the backdrop to the tool, and by measuring the brightness distribution of the image in this zone of wind. CONSTITUTION:The zone A of a wind 5a including the worn part W of a tool 2a, a wind 5b including this zone A and extended to the zone B including the other part g than worn part of the tool 2a and the backdrop b to the tool 2a, and a wind 5C till the zone C enlarged to the zone including the backdrop b according to necessity are established, and the brightness distribution in each wind zone is computed. Obtained brightness distributions are compared, and a brightness threshold value is set between the zone in which the brightness distributions vary to each other and the zone in which they do not make relative variation, and thereby making the image information in two values can be performed properly.

Description

Detailed Description of the Invention [Field of Industrial Application] The present invention relates to an image processing method used when measuring tool wear using an ITV camera. It is about how to make a difference.

[Prior Art] Generally, when measuring tool wear, the worn surface of a tool used for cutting is observed for a predetermined period of time, and the worn parts and the like are measured. The present inventors used IT to measure such tool wear.
We have been conducting research on technology that uses a V-camera to process captured images and measure wear contours, etc.
In measuring tool wear using such an ITV camera, it is first necessary to divide the image information of the ITV camera into a worn part and other parts, that is, to binarize the image information.

When the image information is binarized, the brightness threshold for the binarization is determined by trial and error. However, when automating the wear measurement, the photographing conditions of the tool, It is necessary to always set the luminance threshold for binarization described above to an appropriate value in response to changes in illumination conditions and the like.

[Problems to be Solved by the Invention] An object of the present invention is to automatically determine the brightness threshold to an appropriate value in response to changes in photographing conditions, illumination conditions, etc. of worn parts of tools using an extremely simple method. The goal is to provide a way to

[Means for Solving the Problems] In order to achieve the above object, the image processing method of the present invention photographs the worn part of the tool along with its surrounding parts with an ITV camera, and compares the worn part of the tool and the tool in the image. A window is set within a range that includes parts other than the worn part and the background part of the tool, and the brightness distribution of the image within the range of this window is measured, and the brightness distribution is determined to include the range of the window, Then, compare the brightness distribution within the window set by expanding the range to parts other than the worn part of the tool and the background part of the tool, and compare the brightness distribution between the range where the brightness distribution mutually changes and the range where it does not change. This method is characterized in that a threshold value is set and image information is binarized using the threshold value.

The image processing method of the present invention will be explained in more detail below with reference to the drawings.

FIG. 1 shows an example of a device suitable for carrying out the method of the invention. To explain with reference to the same figure, ITV camera 1
When the worn part of the tool 2 is photographed together with its surrounding parts, the image is recorded in the video frame memory 3. For example, this memory 3 has 512 x 512 bits in the X direction and Y direction of one image, and the brightness is 258 bits.
A three-dimensional digital memory of bits is used.

When photographing tools, the lighting is usually such that worn parts are bright and other parts are dark, but the opposite may be used.

In the image processing device 4 connected to the memory 3,
First, as illustrated in FIG. 2, the worn part W of the tool 2a and the part g other than the worn part of the tool 2a in the above image.
and, for example, 6 within the range including the background part of the tool 2a.
A window 5a of approximately 0x44 bits is set, and the luminance distribution within the range of this window 5a is measured. FIG. 3 shows an example of the measurement, and in this example, the luminance distribution is shown with 4 bits of luminance on the horizontal axis as one unit. As can be seen from this measurement example, clear peaks appear in the brightness distribution corresponding to the above-mentioned worn portion W, the portion g other than the worn portion, and the background portion S.

The image processing device 4 further includes a range A of the window 5a, a part g of the tool 2a other than the worn part, and a background part of the tool 2a, as illustrated in FIG. A window 5b expanded to B is set, the luminance distribution within the window 5b is measured, and if necessary, a window 5c is further expanded to range C including the background part (A+B+C). Then, the luminance distribution within the window 5c is measured.

When the brightness distribution is measured by setting windows in different ranges in this way, as shown in Fig. 4, the tool 2a
Although the brightness distribution corresponding to the worn portion W does not substantially change regardless of the window setting range, the brightness distribution corresponding to the portion g other than the worn portion and the background portion I will vary greatly. Therefore, by comparing the brightness distributions within each window and setting a brightness threshold between the ranges where the brightness distributions change and the ranges where they do not change, one image information can be binarized appropriately. Can be done. As mentioned above, if you light the worn area brightly,
As shown in FIG. 4, the threshold value is set at the lowest luminance within the range where the luminance distribution does not change.

Note that although the explanation has been made here to compare the brightness distributions in windows 5a, 5b, and 5c,
, 5b can be compared only. Further, the above-mentioned window does not need to be set to include the entire worn part W, but as illustrated in FIG. The window 8b, 8c or 7b, 7c may have a wider range.

In this way, the brightness/darkness value is set, and the worn portion is determined from the binarized image obtained by comparing this threshold value with the brightness of the image. However, in this case, there are the following problems. #
The inside of the contour of the worn part obtained from the above binarized image is naturally a worn part, so it should be at the same logical level of 1 or O as a whole, but realistically measured When this is done, the contour contains a dark spot with an inverted logic level. Therefore, a method suitable for removing this dark spot and determining the worn portion will be described below.

In the binarized image obtained as described above, assuming that there are no dark spots, the value of each bit is sequentially examined in the X direction, for example along the line, as shown in Figure 6. Sometimes there may be many transition points between logical levels 1 and 0, while when examining the value of each bit in the Y direction (cutting direction), due to the nature of tool wear itself, there may be many transition points between l and 0. and the change point from O to 1 exists once each.

Utilizing such characteristics, when a dark spot 9 exists within the contour 8 of a worn part as shown in Fig. 6 (the logic level is l within the contour 8, and 0 outside the contour 8 and within the dark spot 8), ), there are 0 in both the up and down directions as shown by the arrows Yu and Yd.
Extract the change point from
J OHIll rhX2
02 02
U2 Ro2X3 ・03
D3 υ3 03X+
Ll+D+Ui
D+Xn Lln
On On [For the 1nx1st (i=1.2...,n) line, if the upper change point is Ui and the lower change point is Ill, the measurement results shown in Table 1 are obtained, When the figures obtained from the odd and other points extracted for each direction are displayed individually,
The results are as shown in Figure 7 (a) and (b), and these are clearly affected by the scotoma, but the lower change point Di and the lower change point Di when the x1th line is extracted upward. The figure displayed by the upper change point U1 when extracted is as shown in FIG. 7(C), which is the contour shape of the worn part from which the dark spot has been removed.

In other words, by such a simple method, it is possible to extract the contour shape of the worn part from which the influence of dark spots has been removed.

As a result of experiments conducted by the present inventors, it was possible to extract a worn surface contour shape that was extremely similar to the actual worn portion.

In the above description, flank wear is primarily targeted, but it goes without saying that the present invention is not limited to flank wear.

[Effects of the Invention] As detailed above, according to the image processing method of the present invention, the photographing conditions, lighting conditions, etc. of worn parts of tools can be determined using a very simple device and a very simple method. The brightness threshold for binarization processing of the worn portion can be automatically determined to an appropriate value in response to the change.

[Brief explanation of drawings]

FIG. 1 is a configuration diagram showing an example of an apparatus suitable for carrying out the image processing method of the present invention, FIG. 2 is an explanatory diagram showing how a window is set for an image of a worn part, and FIG. 3 is a diagram showing the brightness within the window. A line diagram showing an example of distribution measurement. Figure 4 is a diagram showing the brightness distribution within each window when multiple windows are set. Figure 5 is an explanation showing how other windows are set for images of worn parts. Figures 6 and 7 (a) to (
c) is an explanatory diagram regarding the removal of dark spots in a binarized image. l... ITV camera, 2. fist tool, 2a... tool (image), 5a ~ 5c, 8a ~ 8c, ? a ~7c
e *Window, b. Background part of the fist, g.. Parts other than worn parts, W.. Worn parts. Figure 1 Figure 2 Figure 3 Figure 4 'Brightness

Claims (1)

[Claims] 1. Photograph the worn part of the tool along with its surrounding parts using an ITV camera, and set a window within the range that includes the worn part of the tool, parts of the tool other than the worn part, and the background part of the tool in the image. The brightness distribution of the image within the range of this window is measured, and the brightness distribution is set as a window that includes the range of the window and expands the range to areas other than the worn parts of the tool and the background of the tool. A tool wear method characterized in that a brightness threshold is set between a range where the brightness distribution mutually changes and a range where the brightness distribution does not change, and the image information is binarized using the threshold. Image processing method for measurement.