-
压缩感知理论基于信号的稀疏性和可压缩性, 突破传统Nyquist采样频率的限制, 以较低的数据量对信号进行采样和高概率重构. 在压缩感知理论中, 信号的稀疏度确定了稀疏采样的最低数据量, 是验证采样方法及重构方法优劣的重要参数. 在实际研究过程中, 图像稀疏度通常未知, 这就可能导致过采样或欠采样的情况, 从而无法验证采样方法及重构方法的优劣. 因此, 快速而客观地估计图像的稀疏度对于压缩感知理论研究来说意义重大. 本文分析了基于小波变换的图像稀疏化表示方法, 通过遍历采样和重构得到基于小波变换方法的图像稀疏度, 但过程复杂, 而且结果的准确性依赖于小波基和变换尺度的选择. 本文通过压缩感知理论对主成分变换进行阐述, 在基于主成分变换系数近似为正态函数的假设下, 建立了图像稀疏度与系数函数方差间的线性关系, 并通过多组图像数据进行仿真验证, 结果表明线性关系的正确性. 通过分析和仿真可以看出, 基于主成分变换的稀疏度估计方法比小波变换简单、快速、客观, 对压缩感知理论研究有重要的应用价值.In compressive sensing, signal sparsity is an important parameter which influences the number of data sampling in reconstruction process and the quantity of the reconstructed result. But in practice, undersampled and oversampled phenomenon will occur because of the unknown sparsity, which may lose the advantages of compressive sensing. So how to determine the image sparsity quickly and accuratly is significant in the compressive sensing process. In this paper, we calculate the image sparsity based on the data acquired during compressive sensing recontruction projection which sparses the origin image in wavelets domain, but we find that its procession is complex, and the final results are seriously influenced by wavelet basis function and the transform scales. We then introduce the principle component analysis (PCA) theory combined with compressive sensing, and establish a linear relationship between image sparsity and coefficient founction variance based on the assumption that PCA is of approximately normal distribution. Multiple sets of experiment data verify the correctness of the linear relationship mentioned above. Through previous analysis and simulation, the sparsity estimation based on PCA has an important practical value for compressive sensing study.
-
Keywords:
- compressive sensing /
- sparsity /
- wavelet transform /
- principle component analysis
[1] Donoho D 2006 IEEE Trans. Inform. Theory 52 1289
[2] Zhao X F, Huang S X, Xiang J, Shi W L 2011 Chin. Phys. B 20 099201
[3] Liu Y Y, L Q B, Zeng X R, Huang M, Xiang L B 2013 Acta Phys. Sin. 62 060203 (in Chinese) [刘扬阳, 吕群波, 曾晓茹, 黄旻, 相里斌 2013 物理学报 62 060203]
[4] Jin X L 2010 Acta Phys. Sin. 59 692 (in Chinese) [季小玲 2010 物理学报 59 692]
[5] Wei H Y, Wu Z S, Peng H 2008 Acta Phys. Sin. 57 6666 (in Chinese) [韦宏艳, 吴振森, 彭辉 2008 物理学报 57 6666]
[6] Candés E J, Romberg J, Tao T 2006 IEEE Trans. Signal Process. 52 489
[7] Duarte M F, Baraniuk R G 2012 IEEE Trans. Image Proc. 21 494
[8] Jin L X, Zhang R F 2013 Chin. Phys. B 22 064203
[9] Tsaig Y, Donoho D L 2006 Signal Process. 86 549
[10] Duarte M F 2008 IEEE Signal Proc. Mag. 25 83
[11] Zhang H M, Wang L Y, Yan B, Li L, Xi X Q, Liu L Z 2013 Chin. Phys. B 22 078701
[12] He L, Carin L 2009 IEEE Trans. Signal Process. 57 3488
[13] Xue B, Chen X D, Zhang Y, Liu B 2011 Signal Process. 9 1085
[14] Duarte M F, Wakin M, Baraniuk R G 2008 Int. Conf. Acoustics, Speech, and Signal Process. (ICASSP) Las Vegas USA March 30-April 4, 2008 p5137
[15] Hu L Y, Fan H Y 2011 Chin. Phys. B 19 074205
[16] Tropp J A, Gilbert A C 2007 IEEE Trans. Inform. Theory 53 4655
[17] Ronald A D 1998 Acta Numerica 7 51
[18] Kim E, Paul G 1987 Principal Component Analysis (Amsterdam: Elsevier Science Publishers) pp37-52
-
[1] Donoho D 2006 IEEE Trans. Inform. Theory 52 1289
[2] Zhao X F, Huang S X, Xiang J, Shi W L 2011 Chin. Phys. B 20 099201
[3] Liu Y Y, L Q B, Zeng X R, Huang M, Xiang L B 2013 Acta Phys. Sin. 62 060203 (in Chinese) [刘扬阳, 吕群波, 曾晓茹, 黄旻, 相里斌 2013 物理学报 62 060203]
[4] Jin X L 2010 Acta Phys. Sin. 59 692 (in Chinese) [季小玲 2010 物理学报 59 692]
[5] Wei H Y, Wu Z S, Peng H 2008 Acta Phys. Sin. 57 6666 (in Chinese) [韦宏艳, 吴振森, 彭辉 2008 物理学报 57 6666]
[6] Candés E J, Romberg J, Tao T 2006 IEEE Trans. Signal Process. 52 489
[7] Duarte M F, Baraniuk R G 2012 IEEE Trans. Image Proc. 21 494
[8] Jin L X, Zhang R F 2013 Chin. Phys. B 22 064203
[9] Tsaig Y, Donoho D L 2006 Signal Process. 86 549
[10] Duarte M F 2008 IEEE Signal Proc. Mag. 25 83
[11] Zhang H M, Wang L Y, Yan B, Li L, Xi X Q, Liu L Z 2013 Chin. Phys. B 22 078701
[12] He L, Carin L 2009 IEEE Trans. Signal Process. 57 3488
[13] Xue B, Chen X D, Zhang Y, Liu B 2011 Signal Process. 9 1085
[14] Duarte M F, Wakin M, Baraniuk R G 2008 Int. Conf. Acoustics, Speech, and Signal Process. (ICASSP) Las Vegas USA March 30-April 4, 2008 p5137
[15] Hu L Y, Fan H Y 2011 Chin. Phys. B 19 074205
[16] Tropp J A, Gilbert A C 2007 IEEE Trans. Inform. Theory 53 4655
[17] Ronald A D 1998 Acta Numerica 7 51
[18] Kim E, Paul G 1987 Principal Component Analysis (Amsterdam: Elsevier Science Publishers) pp37-52
计量
- 文章访问数: 6229
- PDF下载量: 1627
- 被引次数: 0