压缩感知算法.pdfVIP

第33 卷第4 期 电 子 与 信 息 学 报 Vol.33No.4 2011 年4 月 Journal of Electronics Information Technology Apr. 2011 基于小波树结构和迭代收缩的图像压缩感知算法研究 练秋生* 肖 莹 (燕山大学信息科学与工程学院 秦皇岛 066004) 摘 要：模型化压缩感知图像重构在标准压缩感知重构的基础上利用了小波树结构的先验知识，分别用贪婪树逼近 和最优树逼近的方法求解重构优化问题。该文以模型化压缩感知重构中已有的小波树结构为基础，依据对大量自然 图像小波系数关系的统计结果，提出了基于相邻系数、父系数与子系数之间统计相依关系的小波系数合理树结构， 并结合小波系数合理树结构的思想，改进了普通迭代硬阈值压缩感知图像重构算法和基于最优树的模型化压缩感知 图像重构算法。实验结果表明，该文算法能获得更高的图像重构质量。 关键词：图像压缩感知；贪婪树结构；最优树结构；模型化压缩感知；迭代硬阈值重构 中图分类号：TN911.73 文献标识码： A 文章编号：1009-5896(2011)-04-0967-05 DOI: 10.3724/SP.J.1146.2010.00684 Image Compressed Sensing Algorithm Based on Wavelet Tree Structure and Iterative Shrinkage Lian Qiu-sheng Xiao Ying (Institute of Information Science and Technology, Yanshan University, Qinhuangdao 066004, China) Abstract: Based on the standard compressed sensing, the model-based Compressed Sensing (CS) uses the tree structure priors, and solves the optimal reconstruction problem with two existing tree structure approximation which are greedy tree approximation and optimal tree approximation. Through numerous statistics test of wavelet relationship, a new tree structure which is named reasonable tree structure is proposed, which is based on the relationship between neighbor coefficients, parent coefficients and children coefficients. What is more, combining with the new reasonable tree structure, an improvement is made for the iterative hard threshold reconstruction algorithm and model-based compressed sensing reconstruction algorithm. Comparing with the iterative hard threshold algorithm and model-based compressed sensi