关键词: 织物起球, 客观评价, Log-Gabor滤波器, 支持向量机, 特征提取

Abstract: As an improvement of the traditional Gabor wavelet, the Log-Gabor filter has been widely used in the field of machine vision. This paper proposes a new method of rating the fabric pilling objectively using the characteristics of Log-Gabor filter combined with Principal Component Analysis （PCA） and Support Vector Machine（SVM）. For the high dimensional problem of Log-Gabor features, this paper improves the traditional feature extraction methods, which can improve the computation efficiency and reduce the running time. Compared with the experimental results of Gabor wavelet, this method can effectively capture the pilling information. The highest correct recognition rate is 95%.

Key words: fabric pilling, objective rating, Log-Gabor filter, Support Vector Machine（SVM）, feature extraction