Wavelet Analysis of Fabric Surface Wrinkle and Self-organized Neural Network Grade Assessment
织物表面折皱的小波分析与自组织神经网络等级评定

In this paper, Multi-Scale two-dimensional wavelet transform is imported to analysze fabric surface wrinkle in order to acquire the finer image information. Firstly, fabric image can be filtered through Gaussian filter, and decomposed by wavelet transform; meanwhile, high frequency information is extracted. Secondly, four kinds of wrinkle feature parameter are applied to calculate the fabric wrinkle degree with different wrinkle replica, which are horizontal variance, vertical variance, horizontal offset and vertical offset separately. Through analyzing the correlation coefficient between feature parameter and wrinkle grade, which indicates the four kinds of wrinkle feature parameter can be taken as the input value for pattern recognition. Finally, Kohonen self-organized neural network is also used to evaluate fabric wrinkle grade objectively. The wrinkle feature parameters are input to the Kohonen self-organized neural network, through training and studying process, the output value can be obtained, different wrinkle grade of fabric replica will be classified by applying self-organized neural network, and wrinkle grade of 26 different type fabrics can be evaluated according to this result. For describing the assessment result with quantify, the correlation coefficient is calculated between objective assessment and subjective assessment in order to validate the feasibility of this method.