Intelligent computerized fabric texture recognition system by using Grey-based neural fuzzy clustering

This paper proposes an approach to texture analysis that could be applied to identify the fabric nature and type of the main weaving texture. Firstly, the RGB color space of original color image is transferred to HSV color space; secondly, wavelet transfer is used to acquire horizontal, vertical and diagonal images of hue and value; and calculate their wavelet energy to take them as texture features of this image. Finally, the grey-based back-propagation neural network is adopted to make fuzzy clustering analysis of this image texture feature. From experimental result, grey-based back-propagation neural network fuzzy clustering (grey-based BNNFC) can accurately recognize plain, twill and satin weave textures of women fabric, single and double textures of knitted fabric, and nonwomen texture of nonwomen fabric. Among 300 test samples in total where there are 50 samples each kind of fabric texture, the recognition rate amounts to 98.3%.