Belt Tear Detection Algorithm Based on Template Matching

Aiming at the high precision and fast response monitoring requirements of conveyor belt defect monitoring system, a machine vision belt tearing detection algorithm based on template matching and affine transformation is proposed. This paper by analyzing the threshold range of the laser line in the gray distribution histogram, the position information of the key points in the laser line matching detection image is taken as the feature point. The affine transformation uses the information to do translation, rotation and other operations on the detection image, and then the detection image and the template image are differenced. The difference result is used as the basis for judgment. When the result is greater than the given threshold, the belt is judged to be tearing. The experimental results show that the accuracy of this algorithm is 96 %, and the detection time of a single image is 26 ms. Compared with the existing algorithms, both the detection time and the detection accuracy are significantly improved.