织物表面疵点检测方法的设计与实现

针对传统织物生产企业中,人工检测织物存在瑕疵检出效率低、误检率高的问题,提出了一种织物表面疵点检测方法。该方法首先采用高斯滤波、线性归一化以及限制对比度自适应直方图均衡化对织物表面图像进行预处理,从而有效增强图像中的疵点表现细节,然后通过改进的Gabor优化选择,再对选择后的图像进行初分解,从中挑选出最优滤波图像进行二值化处理,最后运用统计学方法进行疵点判断并获得最终结果。该方法实现简便、硬件要求低、适应性广,可用于判断织物表面是否含有疵点,并定位疵点。实验证明,织物表面疵点检测准确率高达95.38%。

Design and Implementation of Defect Detection Method for Fabric Surface

To address the problems of low defect detection efficiency and high false detection rate of manual fabric detection in traditional fabric manufacturing enterprises,a fabric surface defect detection method is proposed.For purpose of this method,the Gaussian filter,linear normalization and limited contrast adaptive histogram equalization are adopted for preprocessing fabric surface images,to display detect details of the images clearly.Secondly,the selected images are preliminarily decomposed via improved optimal Gabor filter,with a view to picking out the ones with the optimal filtering for binarization processing.Lastly,defect judgment is conducted by means of statistical approach,and the final result is obtained.The method is easy to operate,has low requirements in terms of hardware,and is of wide adaptability.It can be used to judge the presence of defects on fabric surface,and locate them.The method is proved to have an accuracy rate of fabric surface defect detection as high as 95.38%through experiments.