A new cluster-based feature extraction method for surface defect detection

In this paper, a new cluster-based approach is proposed for feature extraction from the coefficients of two-dimensional discrete wavelet transform. The proposed method divides the matrices of wavelet coefficients into clusters by identifying regions with no holes. The features that contain the informative attributes of the images are computed from the energy content of so obtained clusters. Images are classified based on these feature vectors. The experimental results have shown that the proposed cluster-based feature extraction method is able to effectively extract important intrinsic information content of the test images, and increase the overall classification accuracy as compared to conventional feature extraction methods.