Abstract: Based on the sparse characteristic of image signal in Contourlet transform domain, the theory of image Contourlet transform is analyzed, and the image Compressive Sensing(CS) reconstruction method is proposed based on the Contourlet transform. Because the basis of Contourlet transform is not orthogonal strictly and can not construct orthogonal matrix, this paper proposes an image reconstruction method which is based on ameliorative gradient projection algorithm to improve the conventional reconstruct algorithm. The image reconstruction method which is based on ameliorative gradient projection algorithm can realize the high quality image reconstructed with low sampling rate. Experimental result shows that the proposed method has good robustness.

Key words: Contourlet transform, image signal, sparse characteristic, image compressive, Compressive Sensing(CS), gradient projection algorithm

摘要： 根据图像信号在Contourlet变换域的稀疏特性，分析Contourlet变换的基本原理，提出一种基于Contourlet变换的压缩感知重构方法。针对Contourlet变换的基函数并不严格规范正交、无法构造正交变换矩阵的问题，采用改进梯度投影算法恢复稀疏处理后的系数，在保证图像质量的情况下，实现图像的低速率重构。实验结果表明，该算法的鲁棒性较好。

关键词: Contourlet变换, 图像信号, 稀疏特性, 图像压缩, 压缩感知, 梯度投影算法

CLC Number: 

• TP391