Visual inspection method for concave and convex marks based on neighborhood decision-making and gray-level co-occurrence matrix description

Abstract

The invention discloses a method for visual detection of concave and convex marks based on neighborhood decision-making and gray-level co-occurrence matrix description. The steps are: first step, thresholding the original image; second step, target image extraction; third step 1. Target image fitting; the fourth step, target image correction; the fifth step, concave-convex mark recognition. The visual detection method for concave and convex marks based on neighborhood decision-making and gray-level co-occurrence matrix description extracts the contour of the workpiece through the edge extraction method, and then optimizes the workpiece contour through feature extraction, clustering, and line fitting methods to solve the problem of workpiece offset , and then mapped to the standard rectangular image, and then through the method of feature judgment and multi-template matching to detect concave-convex marks, which effectively improves the detection rate of concave-convex marks on the workpiece surface, which has great practical value.

Description

technical field [0001] The invention relates to the technical field of industrial pipeline machine vision detection of surface defects, in particular to a visual detection method for concave and convex marks based on neighborhood decision-making and gray-level co-occurrence matrix description. Background technique [0002] Manual visual inspection is the most commonly used defect detection method, but manual inspection is time-consuming, and the results of manual inspection will be biased due to different situations, which cannot meet the requirements of efficient and accurate inspection in industrial production. [0003] Scratches and concave-convex marks often appear on the surface of objects, and their length, direction and depth are different. They are often interfered by the natural texture or pattern of the product surface, and it is difficult to accurately extract the characteristics of scratches. [0004] Edge detection algorithms usually use Laplacian, Canny, Sobel,...

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is: in order to solve the problems existing in the above-mentioned background technology, provide a visual detection method for concave and convex marks based on neighborhood decision-making and gray-level co-occurrence matrix description, which can overcome the problems caused by dark light environment and target object deviation. And the problem of large recognition errors caused by problems such as shooting angles, effectively improves the detection rate of concave and convex marks on the surface of the workpiece, and has great practical value

Images