Defect detection in flat surface products using log-Gabor filters

Abstract

This paper introduces a novel method for defect detection in homogeneous flat surface products. The coefficient of variation is used as a homogeneity measure for approximate defect localization and features extracted from the Log – Gabor filter bank response are used to accurately localize and detect the defect while reducing the complexity of Gabor based inspection approaches. The scanning window size and threshold parameter are the two major factors that affect the system performance. An adaptive technique is proposed for selecting the size of the scanning window and automating the selection of the threshold level. Compared to the Log-Gabor filters, the proposed combination resulted in speeding up the defect detection process by about ten times. The experimental results show that the proposed system gives promising results and is applicable for defect detection in homogeneous surfaces like paper, steel plates, ceramic tiles and foils.