Application of computer vision in the automatic identification and classification of woven fabric weave patterns

Traditionally, fabric texture identification is based on visual inspection. Recent studies have proposed automatic recognition, which utilizes computer vision to recognize the texture of different fabrics. In the recognition process, the fabric weave patterns are identified by the warp and weft floats. However, due to the optical environments and the appearance differences of fabrics and yarns, the stability and fault-tolerance of the computer vision method are yet to be improved. By using the fabric weave patterns image identification system, this study analyzed the fabric image to find out the warp and weft by the pixel gray-level cumulative values. It then cut out the image of the warp and weft floats to obtain the texture feature values, and used the Fuzzy C-Means (FCM) algorithm to identify the warp and weft floats. The identification results can derive the black-white digital image and the digital matrix of the fabric weave patterns. Finally, weaves classification is conducted based on the successfully trained two-stage Back-Propagation Neural Network. This two-stage neural network can be used to construct the computer vision system to recognize fabric texture, and to increase the system reliability and accuracy. This study used the first-order and second-order co-occurrence matrix, and confirmed that fabric patterns can be identified and classified accurately with this method.