Defects Detection of Billet Surface Using Optimized Gabor Filters

This paper deals with a defects detection algorithm for billet surface. To get good performance, detection algorithm has to solve several difficult problems such as shape of a billet, many kinds of defects, much scale. Especially, the scale, that is a metallic oxide on steel surface, makes worse severely the performance of detection. To solve above problems, this paper presents a new effective defects detection algorithm based on Gabor filters optimized by Genetic Algorithm. The experimental results conducted on real billet surface images and demonstrate the good performance of the proposed algorithm.