基于超像素分割的扫描图像去网算法.pdf

包 装 工 程 第38 卷 第9 期 ·236 · PACKAGING ENGINEERING 2017 年5 月 基于超像素分割的扫描图像去网算法 张帆，渠星星，张偌雅，李珍珍，张新红 （河南大学，开封 475001 ） 摘要： 目的 研究一种扫描图像的去网算法，以去除影响扫描图像质量的半色调网纹或者加网网纹。方 法 首先基于SLIC 超像素算法对扫描图像进行分割并对边界进行矢量化，然后采用线性平滑滤波器和非 线性平滑滤波器对图像进行逆半调处理，得到平滑的背景图像，最后把矢量边界与平滑背景整合在一起 得到去网后的图像。结果 在去除网纹的同时有效保留了边界信息，实验图像的峰值信噪比和结构相似 度优于其他算法。结论 文中方法可以有效去除网纹，与其他算法相比具有较好的去网效果。 关键词：扫描图像；去网算法；超像素 中图分类号：TP391 文献标识码：A 文章编号： 1001-3563(2017)09-0236-04 Descreening Algorithm of Scanned Images Based on Superpixel Segmentation ZHANG Fan, QU Xing-xing, ZHANG Ruo-ya, LI Zhen-zhen, ZHANG Xin-hong (Henan University, Kaifeng 475001, China) ABSTRACT: The work aims to study a descreening algorithm of scanned image to remove the halftone pattern or the screen pattern which influences the quality of scanned images. Firstly, the scanned image was segmented based on SLIC superpixel al- gorithm and the boundary region of image was vectored. Then, the smooth background image was got by inverse halftone processing with linear smoothing filter and nonlinear smoothing filter. Finally, the vectored boundary and smooth background were combined together to get the descreened image. The boundary information was effectively retained at the time of de- screening. The PSNR and the SSIM of experimental images were superior to other algorithms. The proposed method can effec- tively remove the screen patterns, and has better descreening performance compared with other algorithms. KEY WORDS: scanned image; descreening algorithm; superpixels 随着计算机技术和网络技术的发展，大量的印刷 域混合方法[4—8] 。常见的去网算法有局部平均算法、 文本被转换为电子文档在网上传播。在印刷工业中