基于多元判别函数的纹理材料快速缺陷自动检测方法

efect inspection in textured material is of great importance to improve the quality. Digital image processing methods have been developed for defect detection for past few years. As an automated on-line detection system, the research on rapid defect detection is quite significant. In this paper, an approach to detect defects of textured material based on multivariate discriminant function is discussed. By subdividing the images into blocks and extracting related features, tiny defects are effectively detected. With the inspection of the defects, a multivariate discriminant function model has been established. The experimental results prove the feasibility and accuracy of the proposed method.