Fabric texture representation using the stable learned discrete cosine transform dictionary

To obtain a stable fabric texture representation result and improve the computation speed, a novel method based on dictionary learning is presented. The dictionary is learned by the alternating least-squares method using discrete cosine transform (DCT) as the initiation dictionary. To test the effectiveness of the dictionary, we comprehensively investigated 42 diverse fault-free woven fabric samples, and three fabrics with defects. After the preprocessing procedure, the woven fabric samples were characterized by the learned dictionary. The experiments on 37 samples with different fabric densities demonstrated that the Peak Signal to Noise Ratio becomes larger while the Root Mean Square Error (RMSE) diminishes as the weaving density increases. For defect fabric samples, the proposed algorithm can efficiently inspect the different types of fabric flaws. Results revealed that the learned dictionary is stable, highly efficient, and suitable for modeling fabric textures. In addition, the algorithm was validated by comparing it with the K-Singular Value Decomposition dictionary and the DCT dictionary. The learned dictionary presented strikingly better results in terms of calculation speed, consistent results, and RMSE. In general, the proposed method can be applied in studying the influence of fabric density on the representation of the fabric texture and detecting fabric flaws.