Magnetic shoe surface defect detection method

Abstract

The invention discloses a magnetic shoe surface defect detection method. The method comprises the following steps of: inputting a magnetic shoe image into a defect detection network model, and outputting a defect probability graph; judging whether each pixel point on the defect probability graph is a defect point or not; extracting a suspected defect area enclosed by each defect point, and recording the suspected defect area as rect1; extracting a real defect area on the label image corresponding to the magnetic tile image, and recording the real defect area as rect2; calculating a regional area intersection ratio of the rect1 to the rect2; judging whether the prediction result of the model is correct or not according to the cross-parallel ratio, and marking the rect1 area as '1'or '0' according to the prediction result; intercepting each marked rect1 area from the magnetic shoe image and each feature map output by the model; and fusing the intercepted rect1 regions to obtain a area fusion graph. According to the method, the false detection rate of the magnetic shoe defects is reduced.

Description

technical field [0001] The invention relates to the field of defect detection and counting, in particular to a method for detecting defects on the surface of magnetic tiles. Background technique [0002] Magnetic tile is a ferrite tile-shaped permanent magnet material, the main components are iron oxide and strontium oxide, generally used in permanent magnet motors, and its function is to replace the magnetic field generated by the excitation winding. Magnetic tiles are the key components of permanent magnet motors, and the quality of magnetic tiles directly affects the quality of permanent magnet motors. [0003] Representative defects of magnetic tiles include cracks, ring cracks, drop corners, non-planar surfaces of magnetic tiles, etc. For the detection of magnetic tile defects, at present, major magnetic tile manufacturers generally adopt traditional manual detection methods. Manual detection has high labor costs, high labor intensity, and human eyes are prone to fatig...

AI Technical Summary

Problems solved by technology

For the detection of magnetic tile defects, at present, major magnetic tile manufacturers generally adopt traditional manual detection methods. Manual detection has high labor costs, high labor intensity, and human eyes are prone to fatigue. Moreover, the discrimination standards vary from person to person, and the judgment results are not scientific enough. objective

In addition, due to the various sizes and irregular shapes of the magnetic tiles, it is difficult for the human eye to detect the size of the magnetic tiles. Therefore, it is difficult to remove unqualified magnetic tiles by human eye detection methods, and it is also impossible to classify the magnetic tiles according to the size of the magnetic tiles. Divide to increase productivity

[0004] In order to solve the above-mentioned problems in human detection, a magnetic tile defect detection method based on machine vision recognition technology has appeared in recent years. Higher, it is easy to mistakenly detect good products as defective products

Images