Workpiece surface defect detection method and device

Abstract

The invention discloses a workpiece surface defect detection method, which converts the image of the input workpiece into a grayscale image, performs binarization processing, extracts the contour of the workpiece, and extracts the grayscale image of the workpiece. degree image, after filtering out the strip texture in the vertical direction of the surface of the workpiece and at an angle of 5 degrees with the horizontal direction, performing edge sharpening processing and then performing adaptive binarization processing to obtain Contour image, use the patch of preset size for contour detection processing, so as to obtain the corresponding feature vector, bring it into the pre-trained SVM model for discriminant operation, and output the result of the discriminant operation, so it can accurately and quickly extract all The image of the corresponding range of the workpiece can greatly reduce the amount of calculation in the subsequent processing process, and can also avoid interference, improve the accuracy of discrimination, and also improve the robustness.

Description

technical field [0001] The invention relates to the field of workpiece quality detection, in particular to a method and device for detecting surface defects of a workpiece. Background technique [0002] The continuous progress of human society is closely related to the use of new materials to some extent. For example, the introduction and use of bronze and steel have greatly improved the productivity and production efficiency of human society, so it is of epoch-making significance. Since the beginning of the 20th century, polymer materials, another innovation in the field of materials, are affecting the development of human society more and more profoundly. Plastic is a kind of polymer material we are familiar with. It has the advantages of low density, light weight, good insulation performance, low dielectric loss, high chemical stability and good wear resistance. It is widely used in industry, agriculture, construction, national defense, etc. The growth rate of cutting-ed...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a method and device for detecting workpiece surface defects, aiming to solve the problem that manual detection methods can only sort products with obvious shapes and surface defects, and due to the subjective factors of the inspected personnel The impact is great, the real-time performance is poor, the false detection rate is high, and quantitative description cannot be made, which affects the accuracy and reliability of the evaluation.

Images