遗传算法的钢铁表面缺陷特征优化的应用

efects on the surface of cold steel strips are main factors to evaluate the quality of cold strips, so surface defects inspection is of great importance to improve quality of cold steel strips. Major contrast steel pressed into the surface of the iron oxide, roll marks , scratches, edge cracks, scratches, scarring, and other common defects. According to the image processing technologies for sample image information chose form, gray and texture characteristics and 32-dimensional feature vector, Based on the genetic algorithm to optimize the 32-dimensional feature vector selection, and 20-dimensional feature vectors were selected to classify types of the defects images. Finally the example shows the algorithm and PCA method are used for comparing with the results to verify the superiority.