[1]宋晓宁,薛益时,於东军,等.一种优化恢复压缩传感矩阵的模糊自适应方法[J].南京理工大学学报(自然科学版),2013,37(04):479.
 Song Xiaoning,Xue Yishi,Yu Dongjun,et al.Fuzzy adaptive method for optimizing recovery of compressive sensing matrix[J].Journal of Nanjing University of Science and Technology,2013,37(04):479.
点击复制

一种优化恢复压缩传感矩阵的模糊自适应方法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
37卷
期数:
2013年04期
页码:
479
栏目:
出版日期:
2013-08-31

文章信息/Info

Title:
Fuzzy adaptive method for optimizing recovery of compressive sensing matrix
作者:
宋晓宁123薛益时4於东军1杨习贝123刘 梓12
1.南京理工大学 计算机科学与工程学院,江苏 南京 210094; 2.江苏尚博信息科技有限公司 博士后工作站,江苏 无锡 214072; 3.江苏科技大学 计算机科学与工程学院,江苏 镇江 212003; 4.南京邮电大学 海外教育学院,江苏 南京 210023
Author(s):
Song Xiaoning123Xue Yishi4Yu Dongjun1Yang Xibei123Liu Zi12
1.School of Computer Science and Engineering,NUST,Nanjing 210094,China; 2.Post-doctoral Research Center,Jiangsu Sunboon Information Technology Co.,Ltd.,Wuxi 214072,China; 3.School of Computer Science and Engineering,Jiangsu University of Science and Technology, Zhenjiang 212003,China; 4.Overseas Education College,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
关键词:
稀疏表示 传感矩阵 压缩观测 优化恢复 图像识别
Keywords:
sparse representation sensing matrix compressive measurement optimization recovery image recognition
分类号:
TP391.41
文献标志码:
A
摘要:
为了解决高维信号恢复过程中的欠定线性问题,该文提出一种优化恢复压缩传感矩阵的模糊自适应方法并应用在图像重建和识别中。首先对输入样本通过局部分块并建立三阶张量的样本描述方式,提出对降维信号进行多尺度结构分析和独立成分分析,并对结果执行压缩观测,从而使线性观测之间保持线状奇异性和统计独立性。提出一种优化传感矩阵的模糊代价函数,使传感矩阵的原子更新随后按照模糊方式计算,优化后的观测矩阵与字典矩阵之间保持了低相干性。该文方法使样本的稀疏信号在相同重构条件下具备了更优的测量数目和质量。在ORL和Yale人脸数据库及91幅自然图像库上的实验结果验证了本文算法的有效性。
Abstract:
To solve the underdetermined linear problem in the signal recovery from high-dimensional data,a fuzzy adaptive method for optimizing recovery of compressive sensing matrix is proposed for image reconstruction and recognition.By this means,each high dimensional input sample is firstly partitioned into the several local blocks,and those local blocks are combined to represent the sample as a third-order tensor.Moreover,the compressive measurement is performed on the dimensionality-reduced source signal,which is able to find the properties of statistical independence and linear singular by using multi-scale structural analysis and independent component analysis.Finally,a new fuzzy cost function for optimization of sensing matrix is proposed,in which the update of atoms from sensing matrix are fuzzily handled,and the low coherence is obtained between the properties of observation matrix and dictionary matrix.The merit of the method is that the sparse signal has desirable properties for the number of measurements and representation qualities under the same reconstruction conditions.Extensive experimental studies conducted on ORL,Yale face images and 91 natural images databases show that the effectiveness of the proposed method.

参考文献/References:

[1] Candes E,Wakin M.An introduction to compressive sampling[J].IEEE Signal Processing Magazine,2008,25(2):21-30.
[2]焦李成,杨淑媛,刘芳,等.压缩感知回顾与展望[J].电子学报,2011,39(7):1651-1661.
Jiao Licheng,Yang Shuyuan,Liu Fang,et al.Development and prospect of compressive sensing[J].Acta Electronica Sinica,2011,39(7):1651-1661.
[3]何楚,刘明,冯倩,等.基于多尺度压缩感知金字塔的极化干涉SAR图像分类[J].自动化学报,2011,37(7):820-827.
He Chu,Liu Ming,Feng Qian,et al.PolInSAR image classifcation based on compressed sensing and multi-scale pyramid[J].Acta Automatica Sinica,2011,37(7):820-827.
[4]肖亮,韦志辉.图像超分辨率重建的非局部正则化模型与算法研究[J].计算机学报,2011,34(5):931-942.
Xiao Liang,Wei Zhihui.Research on non-local regularization model and algorithms for image super-resolution reconstruction[J].Chinese Journal of Computers,2011,34(5):931-942.
[5]李星秀,韦志辉,肖亮.基于稀疏支撑集先验的压缩感知图像序列重建算法[J].南京理工大学学报,2012,36(6):973-978.
Li Xingxiu,Wei Zhihui,Xiao Liang.Compressed sensing image sequence reconstruction algorithm based on sparse support prior[J].Journal of Nanjing University of Science and Technology,2012,36(6):973-978.
[6]余正涛,邹俊杰,赵兴,等.基于主动学习的最小二乘支持向量机稀疏化[J].南京理工大学学报,2012,36(1):12-17.
Yu Zhengtao,Zou Junjie,Zhao Xing,et al.Sparseness of least squares support vector machines based on active learning[J].Journal of Nanjing University of Science and Technology,2012,36(1):12-17.
[7]Duarte-Carvajalino J M,Sapiro G.Learning to sense sparse signals:simultaneous sensing matrix and sparsifying dictionary optimization[J].IEEE Transactions on Image Processing,2009,18(7):1395-1408.
[8]Mehran S,Mohammad T M S.Three-dimensional modular discriminant analysis(3DMDA):A new feature extraction approach for face recognition[J].Computers and Electrical Engineering,2011,37:811-823.
[9]邓承志.图像稀疏表示理论及其应用研究[D].武汉:华中科技大学电子与信息工程系,2008.
[10]Aharon M,Elad M,Bruckstein A.K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[11]AT&T Laboratories Cambridge.ORL face database[EB/OL],[M/OL],[M/OL].[2009-02-14].Http://www.camorl.co.uk/facedatabase.htm.
[12]Yale database,Available from:<http://cvc.yale.edu/projects/yalefaces/yalefaces.html>.
[13]Yu Hua,Yang Jie.A direct LDA algorithm for high-dimensional data with application to face recognition[J].Pattern Recognition,2001,34:2067-2070.
[14]Yang Jian,Frangi A F,Yang Jingyu,et al.KPCA plus LDA:A complete kernel Fisher discriminant framework for feature extraction and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(2):230-244.
[15]Bartlett M S,Movellan J R,Sejnowski T J.Face recogni-tion by independent component analysis[J].IEEE Transactions on Neural Networks,2002,13(6):1450-1464.
[16]Zhang Xiaoxun,Jia Yunde.A linear discriminant analysis framework based on random subspace for face recognition[J].Pattern Recognition,2007,40:2585-2591.
[17]Liang Zhizheng,Li Youfu,Shi Pengfei.A note on two-dimensional linear discriminant analysis[J].Pattern Recognition Letters,2008,29(16):2122-2128.
[18]He Xiaofei,Yan Shuicheng,Hu Yuxiao,et al.Face recognition using laplacianfaces[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2005,27:328-40.
[19]You Qubo,Zheng Nanning,Du Shaoyi,et al.Neighborhood discriminant projection for face recognition[J].Pattern Recognition Letters,2007,28:1156-1163.

相似文献/References:

[1]周晓雨,余博思,丁恩杰.基于稀疏表示和低秩逼近的自适应异常事件 检测算法[J].南京理工大学学报(自然科学版),2016,40(06):666.[doi:10.14177/j.cnki.32-1397n.2016.40.06.005]
 Zhou Xiaoyu,Yu Bosi,Ding Enjie.Adaptive abnormal event detection algorithm based on sparse representation and low rank approximation[J].Journal of Nanjing University of Science and Technology,2016,40(04):666.[doi:10.14177/j.cnki.32-1397n.2016.40.06.005]

备注/Memo

备注/Memo:
收稿日期:2012-10-21 修回日期:2013-01-05
基金项目:国家自然科学基金(61100116); 中国博士后科学基金(2011M500926); 江苏省自然科学基金(BK2012700,BK2011492); 江苏省博士后科学基金(1102063C); 人工智能四川省重点实验室开放基金(2012RZY02)
作者简介:宋晓宁(1975-),男,博士后,副教授,主要研究方向:模式识别与智能系统,图像识别,计算机视觉等,E-mail:xnsong@yahoo.com.cn。
更新日期/Last Update: 2013-08-31