Texture defect detection with combined local homogeneity analysis and discrete cosine transform

In this paper a new technique for defect detection in gray-level textured images is proposed. The first step of the algorithm consists in computing the local homogeneity of each pixel to construct a new homogeneity image denoted as (Himage). The second step is devoted to divide the H-image into squared blocks and applied the discrete cosine transform (DCT) Some representative energy features of each DCT block are extracted. These energy features are integrated by the Hotelling's T-squared statistic and the defect blocks can be determined by the multivariate statistical method Finally, a simple thresholding method is applied to set a threshold for distinguishing between defective areas and uniform regions. Simulations on different textured images and different defect aspects show good promising results.