基于K-SVD算法的织物线性瑕疵检测研究

Research on the Fabric Linear Defect Detection Based on K-SVD Algorithm

为进一步提高织物线性瑕疵的检测效率,文章提出了一种K-SVD算法,用于检测织物线性瑕疵。研究过程如下:首先分析K-SVD算法及其织物瑕疵表达;接着分析如何通过线性瑕疵投影增强、滤波处理提高瑕疵的分割效果;最后选择小波重构算法与K-SVD算法进行对比性实验。实验结果表明:K-SVD算法检出正确率高于小波重构算法4%,误检率较低,验证了K-SVD算法的有效性。

In order to further improve the detection efficiency of linear defects in fabrics,a K-SVD algorithm is proposed to detect the linear defects in fabrics.The research process is as follows.Firstly,the K-SVD algorithm and the expression of fabric defects are analyzed.Then it analyzes how to improve the segmentation effect of defects by linear defect projection enhancement and filter processing.Finally,the wavelet reconstruction algorithm and K-SVD algorithm are selected for comparative experiment.The experimental result shows that the detection accuracy of the K-SVD algorithm is higher than that of the wavelet reconstruction algorithm by 4%,and the error detection rate is lower,thus verifying the effectiveness of the K-SVD algorithm.