CN111539951A - A kind of visual detection method of ceramic grinding wheel head profile size - Google Patents

Abstract

The invention discloses a visual detection method for the outline size of a ceramic grinding wheel head, which comprises the following steps: step 1, obtaining an image; step 2, processing the image; step 3, extracting a target area; step 4, calculating the outline size and evaluating the result; shooting a clear grinding wheel head image by using a backlight source, then carrying out image processing such as graying, filtering, binarization and the like to obtain a grinding wheel head outline image, obtaining an outline straight line of a grinding wheel rod according to a Hough straight line, rotating the image to a correct position according to the straight line, finally extracting a target detection window, and calculating the outline size of the grinding wheel head to carry out result evaluation; compared with the traditional detection method, the visual detection method provided by the invention has higher efficiency and accuracy, and can utilize the grinding wheel head contour pixels to fit the contour line and analyze the local size error of the grinding wheel head, thereby providing convenience for production and manufacture.

Description

A kind of visual detection method of ceramic grinding wheel head profile size

【Technical field】

The invention belongs to the technical field of automatic quality inspection of industrial processing parts, and relates to a visual inspection method for the outline size of a ceramic grinding wheel head.

【Background technique】

In the quality inspection of industrial processing parts, inspection accuracy, inspection efficiency, and inspection cost are the basic evaluations of the pros and cons of inspection methods. Due to the rapid development of the Internet of Things and the increase of personalized customized products, there are new requirements for inspection methods and equipment. With new requirements, how to improve the real-time and applicability of detection methods and equipment has become a new evaluation target.

The automated visual inspection system can well solve the above-mentioned evaluation targets in the surface quality inspection. By extracting the local target detection area of the acquired image, and searching through image grayscale, filtering, erosion, and expansion contours The visual information of the target area can be accurately obtained by image enhancement processing methods, and the quality inspection of machined parts can be completed through the calculation method of camera calibration and matching.

In addition to the current rapid development of robots, it is not difficult to realize multi-pose detection of industrial parts with visual inspection. Moreover, the robot can set different working rhythms as needed, and has a stable working state. This aspect can replace manual labor and improve detection accuracy. And work efficiency, reduce testing costs. Quality inspection is the last line of defense in the production industry, and automated visual inspection will become a future development goal.

[Content of the invention]

The purpose of the present invention is to solve the practical problem of the quality detection of the outer surface of the machined parts, and to provide a visual detection method of the outline size of the ceramic grinding wheel head.

To achieve the above object, the present invention adopts the following technical solutions to realize:

A method for visual inspection of the outline size of a ceramic grinding wheel head, comprising the following steps:

Step 1, image acquisition:

Place the target grinding wheel to be detected on the inspection V-block and fix it so that the grinding wheel head is in the center of the field of view, and the grinding wheel rod is placed vertically in the field of view, and a surface light source is placed under the grinding wheel head, and the image obtained by the industrial camera is used;

Step 2, image processing:

Filter the redundant information in the image, detect the outer contour size of the grinding wheel head, and highlight the characteristics of the target area; the image processing includes the steps of image grayscale, filtering, binarization, finding contours, Hough line detection, and rotating the image;

Step 3, target area extraction:

Draw a rectangular frame in the processed image, distinguish the target area from the non-target area, and calculate the outline size of the target area;

Step 4, outline size calculation and result evaluation:

After the camera is calibrated, the size of the contour of the target area is calculated, and the calculation result is compared with the standard design size to obtain the size error and evaluate the grinding wheel head.

The further improvement of the present invention is:

The specific method of step 2 is as follows:

Step 2-1, image grayscale:

Perform grayscale processing on the image, and process the three-channel RGB image into a single-channel grayscale image;

Step 2-2, Gaussian filtering:

Set the width and kernel size of the filter window to perform image Gaussian filtering;

Step 2-3, image binarization:

Set the gray value of all pixels on the image to 0 or 255, and set the threshold to binarize the image;

Steps 2-4, find contours:

Detect the outer contour, convert all points in the contour encoding into points, obtain the pixel value position of the outer contour, and create a new blank image to draw on it;

Step 2-5, Hough line detection:

Perform Hough line detection on the obtained outer contour image, set the polar diameter resolution, polar angle resolution, line intersection threshold, minimum point threshold for forming a line, and maximum distance between the two points of the line, and obtain the straight line of the grinding wheel profile as the basis of the rotating image;

Steps 2-6, rotate the image:

Select a vertical straight line and the straight line detected by the Hough straight line, use the vector dot product to calculate the angle, and rotate the image until the grinding wheel bar is in the vertical position.

If the camera is set to acquire grayscale images, step 2 starts from step 2-2.

In the step 3, an effective detection field of view is set or selected in the acquired image to avoid detection of an invalid area.

In the step 4, the camera is calibrated first, and the image obtained in steps 2-6 starts with the outline of one side and ends with the outline of the other side to obtain the outline diameter line, and calculates the outline diameter size of the detection target layer by layer. Then compare it with the standard design drawing, obtain the dimensional error of the key position, and judge whether the detected workpiece is qualified.

Compared with the prior art, the present invention has the following beneficial effects:

The detection method provided by the present invention is visual detection, that is, non-contact measurement, which can avoid damage to the surface of the workpiece to be detected, and reduce the cost of upgrading the detection equipment; the visual detection algorithm can be modified according to the workpiece to be detected, which improves the application Compared with manual work, the automated robot with the vision of the camera has a stable working state, which can effectively improve the detection accuracy, improve the detection efficiency, reduce the inspection cost.

【Description of drawings】

Fig. 1 is the flow chart of the detection method of the present invention;

Fig. 2 is the partial structure schematic diagram of the target part of the grinding wheel head to be detected according to the present invention;

3 is a schematic diagram of the target part to be detected area according to the present invention;

FIG. 4 is a specific detection result diagram of the present invention.

【Detailed ways】

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only The embodiments are part of the present invention, not all of the embodiments, and are not intended to limit the scope of the present disclosure. Furthermore, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. The figures are not to scale, some details have been exaggerated for clarity, and some details may have been omitted. The shapes of various regions and layers shown in the figures and their relative sizes and positional relationships are only exemplary, and in practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art should Regions/layers with different shapes, sizes, relative positions can be additionally designed as desired.

In the context of the present disclosure, when a layer/element is referred to as being "on" another layer/element, it can be directly on the other layer/element or intervening layers/elements may be present therebetween. element. In addition, if a layer/element is "on" another layer/element in one orientation, then when the orientation is reversed, the layer/element can be "under" the other layer/element.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

Below in conjunction with accompanying drawing, the present invention is described in further detail:

Referring to Fig. 1, the visual detection method of the outline size of the ceramic grinding wheel head of the present invention comprises the following steps:

Step 1, image acquisition, place the target grinding wheel to be detected on the detection V-block and fix it, try to make the grinding wheel head in the center of the field of view, and place the grinding wheel rod vertically in the field of view, and place a surface light source under the grinding wheel head, Use an industrial camera to get a clear image, as shown in Figure 2;

Step 2: Image processing: After the initial image acquisition, the outline size of the grinding wheel head cannot be directly detected. Image processing must be performed to filter the redundant information in the image. Only the outer contour is required for the outline size detection of the grinding wheel head, and no color information is required. , highlight the features of the target area, image processing includes image grayscale, filtering, binarization, finding contours, Hough line detection, rotating images and other steps, the specific steps are as follows:

Step 2-1, grayscale image: the color information of the part is not required for the contour size detection of the grinding wheel head, then the image is grayscaled, and the three-channel RGB image is processed into a single-channel grayscale image. If the camera is set to obtain a grayscale image, it will not be grayscaled;

Step 2-2, Gaussian filtering: The purpose of this step is to smooth the image. In order to reduce the influence of noise and artifacts on the image, set the width and kernel size of the filter window to perform image Gaussian filtering;

Step 2-3, image binarization: set the gray value of all pixels on the image to 0 or 255. This step is to highlight the image in two distinct display states of black and white, and lay the foundation for finding contours. The threshold is used to binarize the image;

Step 2-4, find the contour: This step is to find the outer contour of the grinding wheel in the image, set it to detect only the outer contour, convert all the points in the contour coding into points, get the pixel value position of the outer contour, and create a new one. A blank image is drawn on top;

Step 2-5, Hough line detection: perform Hough line detection on the obtained outer contour image, and set parameters such as polar diameter resolution, polar angle resolution, line intersection threshold, minimum point threshold for forming a line, and maximum distance between two points on a line. Obtain the straight line of the grinding wheel profile as the basis of the rotated image;

Step 2-6, rotate the image: select a vertical line and the straight line detected by the Hough line to calculate the angle by vector point product, and rotate the image to the correct position, that is, the grinding wheel bar is in the vertical position.

Step 3, target area extraction, as shown in Figure 3: After image processing, the objects in the field of view are not all target detection areas, and a rectangular frame is drawn in the processed image to distinguish the target area and the non-target area. Calculate the contour size of the target area to avoid wasting computer resources due to redundant calculations, improve detection efficiency, and improve detection accuracy;

Step 4, outline size calculation and result evaluation, as shown in Figure 4: After the camera is calibrated, the size of the outline of the target area can be calculated, and the calculation result can be compared with the standard design size to obtain the size error. Evaluate whether the grinding wheel head is qualified. Specifically, the image obtained in steps 2-6 starts with the left contour and ends with the right contour to obtain the contour diameter line, calculates the contour diameter size of the detection target layer by layer, and then compares it with the standard design drawing to obtain the key The dimensional error of the position is used to judge whether the detected workpiece is qualified.

The above content is only to illustrate the technical idea of the present invention, and cannot limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention all fall within the scope of the claims of the present invention. within the scope of protection.

Claims (5)

1. a ceramic grinding wheel head outline dimension visual detection method, is characterized in that, comprises the following steps: Step 1, image acquisition: Place the target grinding wheel to be detected on the inspection V-block and fix it so that the grinding wheel head is in the center of the field of view, and the grinding wheel rod is placed vertically in the field of view, and a surface light source is placed under the grinding wheel head, and the image obtained by the industrial camera is used; Step 2, image processing: Filter the redundant information in the image, detect the outer contour size of the grinding wheel head, and highlight the characteristics of the target area; the image processing includes the steps of image grayscale, filtering, binarization, finding contours, Hough line detection, and rotating the image; Step 3, target area extraction: Draw a rectangular frame in the processed image, distinguish the target area from the non-target area, and calculate the outline size of the target area; Step 4, outline size calculation and result evaluation: After the camera is calibrated, the size of the contour of the target area is calculated, and the calculation result is compared with the standard design size to obtain the size error and evaluate the grinding wheel head. 2. ceramic grinding wheel head outline size visual detection method according to claim 1, is characterized in that, the concrete method of described step 2 is as follows: Step 2-1, image grayscale: Perform grayscale processing on the image, and process the three-channel RGB image into a single-channel grayscale image; Step 2-2, Gaussian filtering: Set the width and kernel size of the filter window to perform image Gaussian filtering; Step 2-3, image binarization: Set the gray value of all pixels on the image to 0 or 255, and set the threshold to binarize the image; Steps 2-4, find contours: Detect the outer contour, convert all points in the contour encoding into points, obtain the pixel value position of the outer contour, and create a new blank image to draw on it; Step 2-5, Hough line detection: Perform Hough line detection on the obtained outer contour image, set the polar diameter resolution, polar angle resolution, line intersection threshold, minimum point threshold for forming a line, and maximum distance between the two points of the line, and obtain the straight line of the grinding wheel profile as the basis of the rotating image; Steps 2-6, rotate the image: Select a vertical straight line and the straight line detected by the Hough straight line, use the vector dot product to calculate the angle, and rotate the image until the grinding wheel bar is in the vertical position. 3 . The method for visual inspection of the outline size of a ceramic grinding wheel head according to claim 2 , wherein if the camera is set to acquire a grayscale image, step 2 is performed from step 2-2. 4 . 4 . The method for visual inspection of the outline size of a ceramic grinding wheel head according to claim 1 , wherein in the step 3, an effective detection field of view is set or selected in the acquired image to avoid detection of an invalid area. 5 . 5. The method for visual inspection of the outline size of a ceramic grinding wheel head according to claim 2 or 3, wherein in the step 4, the camera is calibrated first, and the image obtained in the steps 2-6 starts with a side profile , take the other side contour as the end to obtain the contour diameter line, calculate the contour diameter size of the detection target layer by layer, and then compare it with the standard design drawing to obtain the dimensional error of the key position, and judge whether the inspection workpiece is qualified.

Images