Automatic defects detection based on adaptive wavelet packets for leather manufacture

The visual inspection system for leather surfaces was developed to quality control and raw material cut, an important component of automatic CAD/CAM cutting systems. The industrial detection of leather defects is difficult because of the large dimensions of the leather hides (3m×2.5 m), and the small dimensions of the defects (200μ×200μm). An efficient approach, using wavelet packets, is presented for the detection of defects embedded in leather surface images. Every inspection leather image is decomposed with a family of real orthonormal wavelet bases. The wavelet packet coefficients from a set of dominant frequency channels containing significant information are used for the characterization of leather images. A fixed number of shift invariant measures from the wavelet packet coefficients are computed. The magnitude and position of these shift invariant measures in a quadtree representation forms the feature set for a two-layer neural network classifier. The neural network classifier classifies these feature vectors into either of defect or defect-free classes. The experimental results suggest that this proposed scheme can successfully identify the defects, and can be used for automated visual leather inspection.