基于RPCA的纸病图像分割算法

针对实际纸病检测应用中采集到的图像分辨率越来越高,在图像处理过程中出现数据维数过大的问题,提出一种基于鲁棒主成分分析法(Robust Principal Component Analysis,RPCA)的纸病图像分割算法,该算法将纸病图像对应的矩阵分解成稀疏矩阵和低秩矩阵。在后续检测中只需选取稀疏矩阵对应的图像进行检测就可以满足纸病检测的要求,有效减少了计算量,最终节省了整个纸病检测环节的检测时间。仿真结果表明,该方法可用于纸病图像的分割,并且具有良好的分割效果。

Segmentation Algorithm of Paper Defect Images Based on RPCA

In the practical detection, the resolution of collected image is getting higher and higher, resulting the data dimension is too large in image processing, a paper image segmentation algorithm based on Robust Principal Component Analysis (RPCA) was proposed in this paper. The matrix of paper defect image could be decomposed into sparse matrix and low rank matrix. In the subsequent detection, just selecting the image corresponded by the sparse matrix for detection could meet the requirements of paper defect detection, and reduce the amount of computation effectively, and eventually reduce the detection time of the whole paper defect. The simulation results showed that the proposed algorithm could be used for the segmentation of the paper image and had good segmentation performance.