An image detection method for surface defects of silicon steel plate under the interference of oil pollution

Abstract

The invention discloses a silicon steel plate surface defect image detection method under oil pollution interference. The method comprises the following steps: acquiring a silicon steel plate surface defect image by using an area array industrial camera; performing defect detection on the acquired silicon steel plate surface defect image by using a visual salience method; performing positioning defection on the oil pollution defect image by using a salient line scanning morphology-based detection method. According to the method, the situation that a silicon steel plate is covered by oil pollution interferents is removed from the defect detection, and the difficulty of target detection and recognition is increased by the pseudo defect interference. The problems of disordered background during defect detection, oil pollution interference of coverage and pseudo defect interface of reflection are solved; line scanning filling operation is performed on a binary image in lack of information, and the operation can effectively obtain an oil pollution interference region; the oil pollution edge and the reflective pseudo defect edge are removed by applying an edge processing method of a morphology theory, and the problem that the pseudo edge cannot be effectively eliminated by subtraction operation is avoided.

Description

technical field [0001] The invention belongs to the technical field of machine vision and nondestructive testing, and in particular relates to an image detection method for surface defects of a silicon steel plate under the interference of oil pollution. Background technique [0002] Among metal sheets, silicon steel sheets are high-end steel products, and their manufacturing technology and product quality have become one of the important symbols to measure a country's special steel production and technological development level. Silicon steel plate, also known as silicon steel plate, is a silicon-iron soft magnetic alloy with extremely low carbon content, generally containing 0.5-4.5% silicon. It is mainly used to make iron cores of various generators, motors and transformers. At the same time, silicon steel plates are also indispensable and important soft magnetic alloy materials in electronics, electric power and military industries. Since the silicon steel plate is clos...

AI Technical Summary

Problems solved by technology

However, target information may still be covered by disturbances in the obtained defect images. For example, defect targets may be covered by oil stains in the surface images of silicon steel sheets. These pseudo-defect interferences increase the accuracy of target detection and recognition. difficulty

Images