纺织品缺陷检测是纺织品自动检测的重要环节，而纺织品缺陷检测的目的是为了准确地对纺织品的缺陷区域进行定位。为了对纺织品缺陷进行准确有效的检测，提出了一种新的基于纹理分水岭的纺织品缺陷检测方法。该方法首先利用小波变换提取了图像的各子带纹理特征；然后对各子带纹理特征求梯度，并通过融合各子带梯度来获得纹理梯度，使其在纹理梯度中能有效地突出纹理区域的边界；最后在此基础上，结合分水岭分割，即能准确地检测出纺织品的缺陷区域。通过对一组6类纺织品缺陷进行检测的实验证明，该新算法是有效的。

Fabric defect detection and classification (FDDC) plays an important role in the automated inspection of fabric products. In this paper, a novel defect detection method based on texture watershed is proposed. The properties of texture defects are characterized using the wavelet method. Texture gradient can be acquired by calculating the sub-band wavelet. Texture gradient contains many texture features and the boundary of texture regions in fabric images can be enhanced. Combined with the watershed transform, the defective regions in fabric images can be detected accurately. The proposed method achieves efficient and accurate performance on the detection of 6 fabric images containing fabric defects.