基于稀疏表示的声纳图像识别及超分辨率重建
|
摘要
声纳图像的识别和超分辨率重建是未来船舶与海洋工程的两项关键技术，其发展无论是在民用上或是在军事上都有重要意义。近年来，稀疏表示方法受到研究人员的追捧，已经应用到图像压缩、图像去噪和图像复原等诸多领域。本文结合水下的复杂环境和声纳图像的自身特点，研究了基于稀疏表示的声纳图像识别及超分辨率重建方法。主要研究内容如下：
综述了国内外声纳图像识别、超分辨重建以及稀疏表示方法的发展现状，将稀疏表示方法引入到了声纳图像识别和超分辨率重建中。研究了稀疏表示方法中压缩传感的三个重要组成部分：稀疏基、观测矩阵和重构算法。声纳图像含有大量噪声，在声纳图像的预处理中，选择合适的去噪方法，去除声纳图像的噪声，并对声纳图像进行规范化处理。
考虑到前视声纳图像中目标局部特征的重要性，引入了非负矩阵分解方法（Non-negative Matrix Factorization，NMF）。在压缩传感方法中，为了减小测量矩阵与稀疏基矩阵的相关性以确保重建的精确，对NMF进行改进，将改进后的NMF与稀疏表示的分类方法相结合构成压缩传感识别方法，该方法具有较好的识别效果。
前视声纳图像中常会受到气泡、水泡和遮挡物等影响，使得识别效果迅速下降。稀疏表示方法可以通过添加闭塞字典来有效去除闭塞部分，但特征提取后的闭塞字典的原子数量巨大，使得识别时间增长。针对上述问题，通过字典学习的方法，设计出新的闭塞字典，大大减少了字典中的原子数量，提高了声纳图像识别的实时性，且与原闭塞字典方法的识别率相当。
针对侧扫声纳图像中含有重要纹理信息，而单一灰度信息不能表达纹理的问题，引入了灰度-梯度共生矩阵特征提取方法，比较了Roberts和Sobel两种算子求解梯度的效果。将灰度-梯度共生矩阵提取的纹理数字特征替代灰度信息特征构成稀疏基矩阵进行稀疏表示的识别，取得了很好的识别效果，且具有旋转不变的性质。
对于声纳图像来说，噪声对其影响很大，图像的光滑成分的表示不容忽视，将声纳图像分为光滑、边缘和纹理三种成分，分别利用离散平稳小波基、Contourlet基和Gabor基构成字典稀疏表示这三种成分，并构造出基于多重稀疏表示的多帧声纳图像超分辨重建模型。多帧的声纳图像有利于声纳图像中信息的补充，针对该多帧模型对基追踪（BasisPursuit Denoising，BPDN）重构算法进行了扩展。该方法取得了很好的超分辨重建效果，并具有鲁棒性。
Sonar image recognition and super-resolution reconstruction are two crucial technologiesin future shipping and ocean industry. Whose developments are of great importance in civilianuse and military affairs.In recent years, sparse representation gains much attention ofresearchers, and it has been applied to image compression, image de-noising and imagerestoration. Considering the complexed underwater envioment and the characteristics of sonarimage, sonar image recognition and super-resolution reconstruction are studied based onspares representation in this thesis. Main study contents are as follows:
The thesis summarized the development of image recognition, super-resolutionreconstruction and sparse representation. Sparse representation is introduced in the process ofsonar image recognition and super-resolution reconstruction. Three important parts ofcompression sensing method in sparse representation are studied, which are sparse-basis,observing matrix and reconstruction algorithm. Sonar image recognition has great noises,during the preprocessing of sonar image, a appropriate de-noising method is used to removethe noises of sonar image, and then its normalized treatment is given.
Considering the local feature’s importance of forward looking sonar image,Non-negative Matrix Factorization is introduced. Because compressed sensing must meet theneed of irrelevance between measurement matrix and sparse-base matrix, so Non-negativeMatrix Factorization is improved. Compressed sensing recognition method is proposed by thecombination of improved NMF and sparse representation. Simulator show that the proposedmethod has great recognition rate effect.
The forward looking image is often influenced by bubbles, vesicles and occludes, whichdecreases the recognition effect quickly. Sparse representation can eliminate the occlusive partefficiently through the method of adding occlusive dictionary. But after characteristicsextraction, the atom number are huge, which increases the recognition time. According to theabove problems, a new occlusive dictionary is designed based on dictionary learning, whichdecreases the atom number of the dictionary, increasethe real-time performance of the sonarimage recognition, and obtains same recognition rate compared with original occlusivedictionary.
Aiming at the important texture information and rotation invariance of side scan sonarimages, gray level-gradient co-occurrence matrix feature extraction method is introduced,which is used to compare two kinds of gradient-solving effect between Roberts operator and Sobel operator. After gray level-gradient co-occurrence matrix extraction, the texture numbercharacteristics can replace the gray level information characteristics to recognize the sparserepresentation as sparse basis matrix, which leads to good recognition effect and rotationinvariance.
For sonar image, the noise influence is great, the expression of the smooth componentcan’t be neglected. Sonar image contains smooth, edge, and texture parts. Using discretestable wavelet basis, Contourlet basis and Gabor basis to build a dictionary to depict the threeparts of sonar image, multi frame sonar image super-resolution reconstruction model based onmulti-layer sparse representation is constructed. Multi frame sonar image are beneficial to thecomplement of sonar image in formations, and extended Basis Pursuit De-noisingreconstruction algorithm is proposed, which obtains good super-resolution reconstructioneffect and robustness.
综述了国内外声纳图像识别、超分辨重建以及稀疏表示方法的发展现状，将稀疏表示方法引入到了声纳图像识别和超分辨率重建中。研究了稀疏表示方法中压缩传感的三个重要组成部分：稀疏基、观测矩阵和重构算法。声纳图像含有大量噪声，在声纳图像的预处理中，选择合适的去噪方法，去除声纳图像的噪声，并对声纳图像进行规范化处理。
考虑到前视声纳图像中目标局部特征的重要性，引入了非负矩阵分解方法（Non-negative Matrix Factorization，NMF）。在压缩传感方法中，为了减小测量矩阵与稀疏基矩阵的相关性以确保重建的精确，对NMF进行改进，将改进后的NMF与稀疏表示的分类方法相结合构成压缩传感识别方法，该方法具有较好的识别效果。
前视声纳图像中常会受到气泡、水泡和遮挡物等影响，使得识别效果迅速下降。稀疏表示方法可以通过添加闭塞字典来有效去除闭塞部分，但特征提取后的闭塞字典的原子数量巨大，使得识别时间增长。针对上述问题，通过字典学习的方法，设计出新的闭塞字典，大大减少了字典中的原子数量，提高了声纳图像识别的实时性，且与原闭塞字典方法的识别率相当。
针对侧扫声纳图像中含有重要纹理信息，而单一灰度信息不能表达纹理的问题，引入了灰度-梯度共生矩阵特征提取方法，比较了Roberts和Sobel两种算子求解梯度的效果。将灰度-梯度共生矩阵提取的纹理数字特征替代灰度信息特征构成稀疏基矩阵进行稀疏表示的识别，取得了很好的识别效果，且具有旋转不变的性质。
对于声纳图像来说，噪声对其影响很大，图像的光滑成分的表示不容忽视，将声纳图像分为光滑、边缘和纹理三种成分，分别利用离散平稳小波基、Contourlet基和Gabor基构成字典稀疏表示这三种成分，并构造出基于多重稀疏表示的多帧声纳图像超分辨重建模型。多帧的声纳图像有利于声纳图像中信息的补充，针对该多帧模型对基追踪（BasisPursuit Denoising，BPDN）重构算法进行了扩展。该方法取得了很好的超分辨重建效果，并具有鲁棒性。
Sonar image recognition and super-resolution reconstruction are two crucial technologiesin future shipping and ocean industry. Whose developments are of great importance in civilianuse and military affairs.In recent years, sparse representation gains much attention ofresearchers, and it has been applied to image compression, image de-noising and imagerestoration. Considering the complexed underwater envioment and the characteristics of sonarimage, sonar image recognition and super-resolution reconstruction are studied based onspares representation in this thesis. Main study contents are as follows:
The thesis summarized the development of image recognition, super-resolutionreconstruction and sparse representation. Sparse representation is introduced in the process ofsonar image recognition and super-resolution reconstruction. Three important parts ofcompression sensing method in sparse representation are studied, which are sparse-basis,observing matrix and reconstruction algorithm. Sonar image recognition has great noises,during the preprocessing of sonar image, a appropriate de-noising method is used to removethe noises of sonar image, and then its normalized treatment is given.
Considering the local feature’s importance of forward looking sonar image,Non-negative Matrix Factorization is introduced. Because compressed sensing must meet theneed of irrelevance between measurement matrix and sparse-base matrix, so Non-negativeMatrix Factorization is improved. Compressed sensing recognition method is proposed by thecombination of improved NMF and sparse representation. Simulator show that the proposedmethod has great recognition rate effect.
The forward looking image is often influenced by bubbles, vesicles and occludes, whichdecreases the recognition effect quickly. Sparse representation can eliminate the occlusive partefficiently through the method of adding occlusive dictionary. But after characteristicsextraction, the atom number are huge, which increases the recognition time. According to theabove problems, a new occlusive dictionary is designed based on dictionary learning, whichdecreases the atom number of the dictionary, increasethe real-time performance of the sonarimage recognition, and obtains same recognition rate compared with original occlusivedictionary.
Aiming at the important texture information and rotation invariance of side scan sonarimages, gray level-gradient co-occurrence matrix feature extraction method is introduced,which is used to compare two kinds of gradient-solving effect between Roberts operator and Sobel operator. After gray level-gradient co-occurrence matrix extraction, the texture numbercharacteristics can replace the gray level information characteristics to recognize the sparserepresentation as sparse basis matrix, which leads to good recognition effect and rotationinvariance.
For sonar image, the noise influence is great, the expression of the smooth componentcan’t be neglected. Sonar image contains smooth, edge, and texture parts. Using discretestable wavelet basis, Contourlet basis and Gabor basis to build a dictionary to depict the threeparts of sonar image, multi frame sonar image super-resolution reconstruction model based onmulti-layer sparse representation is constructed. Multi frame sonar image are beneficial to thecomplement of sonar image in formations, and extended Basis Pursuit De-noisingreconstruction algorithm is proposed, which obtains good super-resolution reconstructioneffect and robustness.
引文
[1]郭日生.海洋高技术进展[M].北京：海洋出版社，2010:25-64
[2]周世锋.海洋开发战略研究[M].杭州：浙江大学出版社，2009:63-78
[3]刘晨晨.高分辨率成像声纳图像识别技术研究[D].哈尔滨工程大学，2006
[4]刘卓夫.基于图像内容的水下目标识别技术研究[D].哈尔滨工程大学，2004
[5] Olshausen B A, Field D J. Emergence of simple-cell receptive field properties bylearning a sparse code for natural images[J]. Nature,1996,381(6583):607-607.
[6] Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory,2006,52(4):1289-1306
[7] Wright J, Yang A Y, Ganesh A, etc. Robust face recognition via sparserepresentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227
[8] Yang J, Wright J, Huang T, etc. Image super-resolution as sparse representation ofraw image patches[C]//26th IEEE Conference on Computer Vision and PatternRecognition. Anchorage, AK, United states: Inst. of Elec. and Elec. Eng. ComputerSociety,2008:1-8
[9] Tang X. Multiple competitive learning network fusion for object classification[J].IEEE Transactions on Systems,1998，28(4):532-543
[10] Foresti G L, Gentili S. Vision based system for object detection in underwaterimages[J]. International Journal of Pattern Recognition and Artificial Intelligence,2000,14(2):167-188
[11] Thyagarajan K S, Nguyen T, Persons C E. Maximum likelihood approach to imagetexture and acoustic signal classification[J]. IEEE Proceedings: Vision, Image andSignal Processing,1999,146(1):34-39
[12] Sutton J P, Sha D D, Perry S, etc. Enhancing mine signatures in sonar images usingnested neural networks[J]. The International Society for Optical Engineering,1999,37(10):570-577
[13] Murino V, Trucco A. Confidence-based approach to enhancing underwater acousticimage formation[J]. IEEE Transactions on Image Processing,1999,8(2):270-285
[14] Calder B R, Linnett L M, Carmichael D R. Bayesian approach to object detection insidescan sonar[J]. IEEE Proceedings: Vision, Image and Signal Processing,1998,145(3):221-228
[15]阳凡林.多波束和侧扫声纳数据融合及其在海底底质分类中的应用[D].武汉大学,2003
[16] Hodgetts M A, Greig A R, Fairweather A. Underwater imaging using MarkovRandom Fields with feed forward prediction[J]. Underwater Technology,1999,23(4):157-167
[17] Mignotte M, Collet C, Perez P, etc. Bayesian inference and optimization strategies forsome detection and classification problems in sonar imagery[J]. The InternationalSociety for Optical Engineering,1999,36(46):14-27
[18] Mignotte M, Collet C, Perez P, etc. Markov random field and fuzzy logic modeling insonar imagery: application to the classification of underwater floor[J]. ComputerVision and Image Understanding,2000,79(1):4-24
[19] Slater R, Robinson C, Lingsch S. Object detection and discrimination in side scansonar by means of intensity contouring[J]. The International Society for OpticalEngineering,1999,37(10):496-503
[20]刘晨晨,桑恩方.基于数学形态学的水声图像处理[J].吉林大学学报,2003,52-57.
[21]田坦刘,孙大军.声纳技术[M].哈尔滨：哈尔滨工程大学出版社,2010:4-8
[22] Waite A D.实用声纳工程[M].北京：电子工业出版社,2004:1-2
[23]于志刚．海洋军事[M].北京：海洋出版社,2009:1-5
[24] Harris J L. Diffraction and resolving power[J]. J.Opt.Soc.Am,1964,54:931-936
[25] Tsai R, Y Huang T.S. Multiframe Image Resoration and Registration[J]. ComputerVision and Image Processing,1984,317-339
[26] Kim S P, Bose N K, Valenzuela H M. Recursive reconstruction of high resolutionimage from noisy undersampled multiframes[J]. IEEE Transactions on Acoustics,Speech, and Signal Processing,1990,38(6):1013-1027
[27] Irani M, Peleg S. Improving resolution by image registration[J].1991,53(3):231-239
[28] Sezan M I, Stark H．Tomographic Image Reconstruction from Incomplete View Databy Convex Projections and Direct Fourier Inversion[J]. IEEE Transactions onMedical Imaging,1984,3(2):91-98
[29] Tekalp A M, Ozkan M K, Sezan M I. High-resolution image reconstruction fromlower-resolution image sequences and space-varying image restoration[C]//Speechand Signal Processing, San Francisco: IEEE Press,1992:169-172.
[30]程倩倩,范新南,李庆武,等.基于神经网络的声纳图像的超分辨率重建方法[P]中国：201110052542,2011.3.5
[31]刘长红,杨扬,陈勇.基于压缩传感的手写字符识别方法[J].计算机应用,2009,(08):2080-2082
[32]王庆伟,唐承志.基于稀疏表示的鲁棒掌纹识别[J].知识经济,2009,(11):96
[33] Huang J, Yang M. Fast sparse representation with prototypes[C]//IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition. San Francisco:IEEE Computer Society,2010:3618-3625
[34]刘彬.基于随机投影和稀疏表征的红外人脸识别方法[D].西安电子科技大学,2009:23-36
[35]苏光大,王晶,熊英.基于约束采样的稀疏表示人脸识别方法[P].中国：201010140797，2010.4.2
[36] Yang J, Wright J, Huang T, etc. Image super-resolution as sparse representation ofraw image patches[C]//IEEE Conference on Computer Vision and PatternRecognition, CVPR2008, Anchorage, AK, United states: Inst. of Elec. and Elec. Eng.Computer Society,2008:1-8
[37] Ma L, He X, Huang Z. Sidescan sonar image super resolution based on sparserepresentation[C]//3rd International Conference on Measuring Technology andMechatronics Automation. Shanghai, China: Trans Tech Publications,2011:1049-1052.
[38]浦剑,张军平.基于词典学习和稀疏表示的超分辨率方法[J].模式识别与人工智能,2010,(03):335-340.
[39]孙玉宝,费选,韦志辉,等.基于前向后向算子分裂的稀疏性正则化图像超分辨率算法[J].自动化学报,2010,(09):1232-1238.
[40]杨淑莹.模式识别与智能计算-Matlab技术实现[M].北京：电子工业出版社,2008:4-6
[41]冈萨雷斯.数字图像处理[M].北京：电子工业出版社,2003:467-474
[42] Schultz R R, Stevenson R L. Extraction of high-resolution frames from videosequences[J]. IEEE Transactions on Image Processing,1996,5(6):996-1011
[43] Schultz R R, Stevenson R L. Improved definition video frame enhancement[C]//Acoustics speech, and signal processing, USA: IEEE Press,1995:2169-2172.
[44] Nguyen N, Milanfar P, Golub G. Efficient generalized cross-validation withapplications to parametric image restoration and resolution enhancement[J]. IEEETransactions on Image Processing,2001,10(9):1299-1308.
[45] Chang H, Yeung D, Xiong Y. Super-resolution through neighbor embedding[C]//Proceedings of the2004IEEE Computer Society Conference on Computer Visionand Pattern Recognition, Washington, DC, United states: Institute of Electrical andElectronics Engineers Computer Society,2004:1275-1282.
[46] Baraniuk R G. Compressive sensing[J]. IEEE Signal Processing Magazine,2007,24(4):118-120+124.
[47]张贤达,保铮.非平稳信号分析与处理[M].北京：国防工业出版社,1998:4-10
[48] Candes E J, Wakin M B. An introduction to compressive sampling: Asensing/sampling paradigm that goes against the common knowledge in dataacquisition[J]. IEEE Signal Processing Magazine,2008,25(2):21-30
[49]李树涛,魏丹.压缩传感综述[J].自动化学报,2009,(11):1369-1377
[50]石光明,刘丹华,高大化,等.压缩感知理论及其研究进展[J].电子学报,2009,(05):1070-1081
[51] Chen S S, Donoho D L, Saunders M A. Atomic decomposition by basis pursuit[J].SIAM Review,2001,43(1):129-159
[52] Donoho D L, Elad M, Temlyakov V N. Stable recovery of sparse overcompleterepresentations in the presence of noise[J]. IEEE Transactions on Information Theory,2006,52(1):6-18
[53] Mallat S. A wavelet tour of signal processing[M]. USA: Academic Press,2008:1-55
[54] Olshausen B A, Field D J. Emergence of simple-cell receptive field properties bylearning a sparse code for natural images[J]. Nature,1996,381(6583):607-607
[55] Candes E J. Ridgelets: theory and applications[D]. USA: Stanford University,1998
[56] Candes E J, Donoho D L. Continuous curvelet transform: I. Resolution of thewavefront set[J]. Applied and Computational Harmonic Analysis,2005,19(2):162-197
[57] Do M N, Vetterli M. The contourlet transform: An efficient directionalmultiresolution image representation[J]. IEEE Transactions on Image Processing,2005,14(12):2091-2106
[58] Le Pennec E, Mallat S. Sparse geometric image representations with bandelets[J].IEEE Transactions on Image Processing,2005,14(4):423-438
[59]张春梅,尹忠科,肖明霞.基于冗余字典的信号超完备表示与稀疏分解[J].科学通报,2006,(06):628-633
[60] Mallat S G, Zhifeng Zhang. Matching pursuits with time-frequency dictionaries[J].Signal Processing, IEEE Transactions on,1993,41(12):3397-3415
[61] Donoho D L, Huo X. Uncertainty principles and ideal atomic decompositionIEEE [J].Transactions on Information Theory,2001,47(7):2845-2862
[62] Baraniuk R, Davenport M, DeVore R and Wakin M. A Simple Proof of the RestrictedIsometry Property for Random Matrices[J]. Constructive Approximation,2008,28(3):253-263
[63] Candes E J, Romberg J K, Tao T. Stable signal recovery from incomplete andinaccurate measurements[J]. Communications on Pure and Applied Mathematics,2006,59(8):1207-1223
[64] Candes E J, Tao T. Near-Optimal Signal Recovery From Random Projections:Universal Encoding Strategies[J]. Information Theory, IEEE Transactions on,2006,52(12):5406-5425
[65]祝勇.基于序列图像的超分辨率重构技术研究[D].长春理工大学，2009
[66]赵建虎.多波束深度及图像数据处理方法研究[D].武汉大学，2002
[67] Do T T, Tran T D, Gan L. Fast compressive sampling with structurally randommatrices[C]//2008IEEE International Conference on Acoustics, Speech and SignalProcessing. Las Vegas, NV, United states: Institute of Electrical and ElectronicsEngineers Inc,2008:3369-3372
[68] Koh K, Kim S, Boyd S. An interior-point method for large-scale1-regularizedlogistic regression[J]. Journal of Machine Learning Research,2007,81519-1555
[69] Figueiredo M A T, Nowak R D, Wright S J. Gradient projection for sparsereconstruction: Application to compressed sensing and other inverse problems[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):586-597
[70] Donoho D L, Tsaig Y. Fast solution of l1-norm minimization problems when thesolution may be sparse[J]. IEEE Transactions on Information Theory,2008,54(11):4789-812
[71] Needell D, Vershynin R. Greedy signal recovery and uncertainty principles[C]//Computational Imaging VI. San Jose, CA, United states: SPIE,2008:3369-3372
[72] Needell D, Tropp J A. CoSaMP: Iterative signal recovery from incomplete andinaccurate samples[J]. Applied and Computational Harmonic Analysis,2009,26(3):301-321
[73] Candes E J, Romberg J, Tao T. Robust uncertainty principles: Exact signalreconstruction from highly incomplete frequency information[J]. IEEE Transactionson Information Theory,2006,52(2):489-509
[74] Lobo M S, Vandenberghe L, Boyd S, etc. Applications of second-order coneprogramming[J]. Linear Algebra and Its Applications,1998,284(1-3):193-228
[75] Herrity K K, Gilbert A C, Tropp J A. Sparse approximation via iterativethresholding[C]//2006IEEE International Conference on Acoustics, Speech andSignal Processing. Toulouse, France: Institute of Electrical and Electronics EngineersInc,2006(3):624-627
[76] Yaghoobi M, Blumensath T, Davies M. Quantized sparse approximation withiterative thresholding for audio coding[C]//2007IEEE International Conference onAcoustics, Speech and Signal Processing. Honolulu, HI, United states: Institute ofElectrical and Electronics Engineers Inc,2007:257-260
[77]李启虎.声纳信号处理引论[M].北京：海洋出版社,2000:107-108;113-118
[78] Yang M, Zhang L. Gabor Feature Based Sparse Representation for Face Recognitionwith Gabor Occlusion Dictionary[C]//11th European Conference on ComputerVision. Berlin, Germany: Springer Verlag,2010:448-461.
[79]丁凯.基于前视声纳的水下目标跟踪技术研究[D].哈尔滨工程大学,2006
[80] Strohmer T, Heath R W, J. Grassmannian frames with applications to coding andcommunication[J]. Applied and Computational Harmonic Analysis,2003,14(3):257-75.
[81] Wang Q, Liu Z. Sampling matrix perturbation analysis of subspace pursuit forcompressive sensing[C]//2010International Symposium on Information andAutomation. Guangzhou, China: Springer Verlag,2011:580-588
[82] Zhao W, Chellappa R, Phillips P J, etc. Face recognition: a literature survey[J]. ACMComputing Surveys,2003,35(4):399-459
[83] Mika S, Ratsch G, Weston J, etc. Fisher discriminant analysis with kernels[C]//Neural Networks for Signal Processing IX. Madison, WI, USA. Proceedings of theIEEE Signal Processing Society Workshop.1999:41-48
[84] Lee D D, Seung H S. Learning the parts of objects by non-negative matrixfactorization[J]. Nature,1999,401(6755):788-791
[85] Bucak S S, Giinsel B, Giirsoy O. Incremental nonnegative matrix factorization forbackground modeling in surveillance video[C]//15th IEEE Signal Processing andCommunications Applications. Piscataway, NJ, USA: IEEE Press,2007:509-12.
[86] Yuan W, Yunde J, Changbo H, etc. Fisher Non-Negative Matrix Factorization forLearning Local Features[J]. Asian Conference on Computer Vision,2004:27-30
[87] Feng T, Li S Z, Heung-Yeung Shum, etc. Local non-negative matrix factorization as avisual representation[C]//ICDL2002. Los Alamitos, CA, USA: IEEE Comput. Soc,2002:178-83.
[88] Xu J, Pi Y, Cao Z. Optimized projection matrix for compressive sensing[J]. EurasipJournal on Advances in Signal Processing,2010:43-48
[89] Nhat V D M, Vo D, Challa S, etc. Efficient projection for compressed sensing[C]//7th IEEE/ACIS International Conference on Computer and Information Science,Portland, OR, United states: Inst. of Elec. and Elec. Eng. Computer Society,2008:322-327
[90]孙友涛,杜丽莉.一种带有正则约束的非负矩阵分解算法[J].内蒙古师范大学学报,2008,(04):477-481
[91]廖锋,高兴宝,杨轩.一种改进的非负矩阵分解算法[J].济南大学学报,2008,(02):193-196
[92]张宇飞.加稀疏约束的非负矩阵分解[D].大连理工大学,2010:40-50
[93] Lee D D, Seung H S. Algorithms for Non-negative Matrix Factorization[J].2001,13:556-562
[94] Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcompletedictionaries for sparse representation[J]. IEEE Transactions on Signal Processing,2006,54(11):4311-4322
[95]滕惠忠,严晓明,李胜全.侧扫声纳图像增强技术[J].海洋测绘,2004,(02):47-49+70
[96]张岩.纹理合成技术的研究及其应用[D].吉林大学,2006:30-38
[97]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001:146-147；419-424
[98] Xu Y, Tseng C, Fu H. Texture recognition by generalized probabilistic decision-basedneural networks[J]. Expert Systems with Applications,2011,38(5):6184-6189
[99]章毓晋.图像分割[M].北京：科学出版社,2001:122
[100] Charalampidis D. Novel textural features and techniques for image segmentation andclassification[D]. Orlando Florida: University of Central Florida,2001:1-5.
[101]马晓川,侯朝焕,唐姗.新的纹理分类算法中国图象图形学报[J],1999,(05):32-35
[102] Ninassi A, Le Meur O, Le Callet P, etc. On the performance of human visual systembased image quality assessment metric using wavelet domain[C]//Human Vision andElectronic Imaging XIII. USA: The International Society for Optical Engineering,2008:610-611
[103] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J].IEEE Transactions on Systems, Man and Cybernetics,1973,3(6):610-621.
[104] Pentland A. Fractal-based description of natural scenes[C]//Proceedings of the IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SilverSpring, MD, USA: IEEE Comput. Soc. Press,1983:201-209.
[105] Tsatsanis M K, Giannakis G B. Object and texture classification using higher orderstatistics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(7):733-50
[106] Zhang H, Tan T. Brief review of invariant texture analysis methods[J]. PatternRecognition,2002,35(3):735-747
[107] Lam W, Li C. Rotated texture classification by improved iterative morphologicaldecomposition[J]. IEEE Proceedings-Vision, Image and Signal Processing,1997,144(3):171-179
[108] Eichmann G, Kasparis T. Topologically invariant texture descriptors[J]. ComputerVision, Graphics, and Image Processing,1988,41(3):267-281
[109] Krishnamachari S, Chellappa R. Multiresolution Gauss-Markov random field modelsfor texture segmentation[J]. IEEE Transactions on Image Processing,1997,6(2):251-267.
[110] Tamura H, Mori S, Yamawaki T. Textural features corresponding to visualperception[J]. IEEE Transactions on Systems, Man and Cybernetics,1978,8(6):460-73.
[111] Bovik A C, Clark M, Geisler W S. Multichannel texture analysis using localizedspatial filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-73
[112]洪继光.灰度-梯度共生矩阵纹理分析方法[J].自动化学报,1984,(01):22-25
[113] Reed T R. A review of recent texture segmentation and feature extractiontechniques[J]. Image Understanding,1993,57(3):359-72
[114]谢美华,王正明.基于图像梯度信息的插值方法[J].中国图象图形学报,2005,(07):856-861
[115] Alam M S, Iftekharuddin K M, Karim M A. Polarization-encoded optical shadowcasting: Edge detection using Roberts operator[J]. Microwave and OpticalTechnology Letters,1993,6(3):190-193
[116] Dony R D, Wesolkowski S, Edge detection on color image using vector angles[C]//IEEE Conference on Electrical and Computer Engineering, Edmonton, Alta. Canada:IEEE Press,1999,(2):687-692.
[117] Alam M S, Gu Y. Sobel operator based multiobject joint transform correlation[J].Optik (Jena),1995,100(1):28-32
[118] Tong X, Ren A, Zhang H, etc. Edge detection based on genetic algorithm and sobeloperator in image[C]//International Conference on Graphic and Image Processing,Cairo, Egypt: SPIE,2011:.
[119]葛静祥.图像纹理特征提取及分类算法研究[D].天津大学,2010:35-38
[120] Bruzzone L, Serpico S B, Vernazza G. Effects of parameter tuning and de-specklefiltering on the accuracy of SAR image classification based on gray-levelco-occurrence matrix features[J]. Geoscience and Remoto Sensing,1997,(2):764-766
[121]杨清跃,高飞,聂青.纹理图像识别中的旋转不变性分析[J].计算机工程与应用,2010,(33):205-207
[122]曹佃国,陈浩杰,李鹏.基于Matlab的双线性插值算法在图像旋转中的应用[J].中国印刷与包装研究,2010,(04):74-78
[123]孙玉宝,韦志辉,肖亮,等.多形态稀疏性正则化的图像超分辨率算法[J].电子学报,2010,(12):2898-2903
[124]乔建苹.超分辨率重建与图像增强技术研究[D].山东大学,2008
[125] Ng M K, Bose N K. Mathematical analysis of super-resolution methodology[J]. IEEESignal Processing Magazine,2003,20(3):62-74
[126] Meyer Y. Oscillating patterns in image processing and nonlinear evolutionequations[M]. Baston：Amer Mathematical Society,2001:35-46
[127] Arivazhagan S, Ganesan L, Subash Kumar T G. Texture classification using ridgelettransform[J]. Pattern Recognition Letters,2006,27(16):1875-1883
[128] Guo Q, Yu S. Image denoising using a multivariate shrinkage function in the curveletdomain[J]. IEICE Electronics Express,2010,7(3):126-131
[129] Kazemi F M, Izadian J, Moravejian R, etc. Numeral recognition using curvelettransform[C]//6th IEEE/ACS International Conference on Computer Systems andApplications, Qatar: Inst. of Elec. and Elec. Eng. Computer Society,2008:606-612.
[130] Tang L, Zhao Z. Multiresolution image fusion based on the wavelet-based contourlettransform[C]//10th International Conference on Information Fusion, Quebec, QC,Canada: Inst. of Elec. and Elec. Eng. Computer Society,2007:1-6
[131] Liu K, Guo L, Chen J. Contourlet transform for image fusion using cycle spinning[J].Journal of Systems Engineering and Electronics,2011,22(2):353-357
[132] Lukin V V, Fevralev D V, Ponomarenko N N, etc. Discrete cosine transform-basedlocal adaptive filtering of images corrupted by nonstationary noise[J]. Journal ofElectronic Imaging,2010,19(2):7-15
[133] Demanet L, Ying L. Wave atoms and sparsity of oscillatory patterns[J]. Applied andComputational Harmonic Analysis,2007,23(3):368-387
[134] Demanet L, Ying L. Curvelets and wave atoms for mirror-extended images[C]//Wavelets XII. San Diego, CA, United states: SPIE,2007:1-15
[135] Liu G, Feng X, Zhang X. Threshold algorithm of texture images with wave atoms[J].Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology,2009,31(8):1791-1795
[136] Lee T S. Image representation using2D Gabor wavelets[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(10):959-971
[137] Zeng Z. Gabor feature-based complete fisher discriminant framework for facialfeature extraction[C]//International Conference on Wireless Communications andSignal Processing, Nanjing, China: IEEE Computer Society,2009:1-5
[138] Zhang C, Wang X, Zhang H. An intelligent algorithm for enhancing contrast forimage based on discrete stationary wavelet transform and in-complete betatransform[C]//International Conference on ffective Computing and IntelligentInteraction. Beijing, China: Springer Verlag,2005:135-143
[139] Wang X H, Istepanian R S H, Yong H S. Microarray image enhancement bydenoising using stationary wavelet transform[J]. IEEE Transactions onNanobioscience,2003,2(4):184-189
[140] Do M N, Vetterli M. Contourlets: A new directional multiresolution imagerepresentation[C]//The Thirty-Sixth Asilomar Conference on Signals Systems andComputers. Pacific Groove, CA, United states: Institute of Electrical and ElectronicsEngineers Computer Society,2002:497-501.
[141] Marcelja S. Mathematical description of the responses of simple cortical cells[J].Journal of the Optical Society of America,1980,70(11):1297-300
[142] Daugman J G. Two-dimensional spectral analysis of cortical receptive fieldprofiles[J]. Vision research,1980,20(10):847-56
[143] Grigorescu S E, Petkov N, Kruizinga P. Comparison of texture features based onGabor filters[J]. IEEE Transactions on Image Processing,2002,11(10):1160-1167
[144]谢建辉.纹理特征提取与分类研究[D].华中科技大学,2008
[145]汪雄良,王春玲.基于改进基追踪方法的信号去噪[J].电子技术应用,2005,(08):19-21
[146] Xiao C, Duan J, Yu J. POCS super-resolution reconstruction from image sequences[J].Beijing Gongye Daxue Xuebao/Journal of Beijing University of Technology,2009,35(1):108-113
[147] Ma L, He X, Huang Z. Sidescan sonar image super resolution based on sparserepresentation[C]//3rd International Conference on Measuring Technology andMechatronics Automation. Shanghai, China: Trans Tech Publications,2011:1049-1052.
[148]邓承志.图像稀疏表示理论及其应用研究[D].华中科技大学,2008
[2]周世锋.海洋开发战略研究[M].杭州：浙江大学出版社，2009:63-78
[3]刘晨晨.高分辨率成像声纳图像识别技术研究[D].哈尔滨工程大学，2006
[4]刘卓夫.基于图像内容的水下目标识别技术研究[D].哈尔滨工程大学，2004
[5] Olshausen B A, Field D J. Emergence of simple-cell receptive field properties bylearning a sparse code for natural images[J]. Nature,1996,381(6583):607-607.
[6] Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory,2006,52(4):1289-1306
[7] Wright J, Yang A Y, Ganesh A, etc. Robust face recognition via sparserepresentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227
[8] Yang J, Wright J, Huang T, etc. Image super-resolution as sparse representation ofraw image patches[C]//26th IEEE Conference on Computer Vision and PatternRecognition. Anchorage, AK, United states: Inst. of Elec. and Elec. Eng. ComputerSociety,2008:1-8
[9] Tang X. Multiple competitive learning network fusion for object classification[J].IEEE Transactions on Systems,1998，28(4):532-543
[10] Foresti G L, Gentili S. Vision based system for object detection in underwaterimages[J]. International Journal of Pattern Recognition and Artificial Intelligence,2000,14(2):167-188
[11] Thyagarajan K S, Nguyen T, Persons C E. Maximum likelihood approach to imagetexture and acoustic signal classification[J]. IEEE Proceedings: Vision, Image andSignal Processing,1999,146(1):34-39
[12] Sutton J P, Sha D D, Perry S, etc. Enhancing mine signatures in sonar images usingnested neural networks[J]. The International Society for Optical Engineering,1999,37(10):570-577
[13] Murino V, Trucco A. Confidence-based approach to enhancing underwater acousticimage formation[J]. IEEE Transactions on Image Processing,1999,8(2):270-285
[14] Calder B R, Linnett L M, Carmichael D R. Bayesian approach to object detection insidescan sonar[J]. IEEE Proceedings: Vision, Image and Signal Processing,1998,145(3):221-228
[15]阳凡林.多波束和侧扫声纳数据融合及其在海底底质分类中的应用[D].武汉大学,2003
[16] Hodgetts M A, Greig A R, Fairweather A. Underwater imaging using MarkovRandom Fields with feed forward prediction[J]. Underwater Technology,1999,23(4):157-167
[17] Mignotte M, Collet C, Perez P, etc. Bayesian inference and optimization strategies forsome detection and classification problems in sonar imagery[J]. The InternationalSociety for Optical Engineering,1999,36(46):14-27
[18] Mignotte M, Collet C, Perez P, etc. Markov random field and fuzzy logic modeling insonar imagery: application to the classification of underwater floor[J]. ComputerVision and Image Understanding,2000,79(1):4-24
[19] Slater R, Robinson C, Lingsch S. Object detection and discrimination in side scansonar by means of intensity contouring[J]. The International Society for OpticalEngineering,1999,37(10):496-503
[20]刘晨晨,桑恩方.基于数学形态学的水声图像处理[J].吉林大学学报,2003,52-57.
[21]田坦刘,孙大军.声纳技术[M].哈尔滨：哈尔滨工程大学出版社,2010:4-8
[22] Waite A D.实用声纳工程[M].北京：电子工业出版社,2004:1-2
[23]于志刚．海洋军事[M].北京：海洋出版社,2009:1-5
[24] Harris J L. Diffraction and resolving power[J]. J.Opt.Soc.Am,1964,54:931-936
[25] Tsai R, Y Huang T.S. Multiframe Image Resoration and Registration[J]. ComputerVision and Image Processing,1984,317-339
[26] Kim S P, Bose N K, Valenzuela H M. Recursive reconstruction of high resolutionimage from noisy undersampled multiframes[J]. IEEE Transactions on Acoustics,Speech, and Signal Processing,1990,38(6):1013-1027
[27] Irani M, Peleg S. Improving resolution by image registration[J].1991,53(3):231-239
[28] Sezan M I, Stark H．Tomographic Image Reconstruction from Incomplete View Databy Convex Projections and Direct Fourier Inversion[J]. IEEE Transactions onMedical Imaging,1984,3(2):91-98
[29] Tekalp A M, Ozkan M K, Sezan M I. High-resolution image reconstruction fromlower-resolution image sequences and space-varying image restoration[C]//Speechand Signal Processing, San Francisco: IEEE Press,1992:169-172.
[30]程倩倩,范新南,李庆武,等.基于神经网络的声纳图像的超分辨率重建方法[P]中国：201110052542,2011.3.5
[31]刘长红,杨扬,陈勇.基于压缩传感的手写字符识别方法[J].计算机应用,2009,(08):2080-2082
[32]王庆伟,唐承志.基于稀疏表示的鲁棒掌纹识别[J].知识经济,2009,(11):96
[33] Huang J, Yang M. Fast sparse representation with prototypes[C]//IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition. San Francisco:IEEE Computer Society,2010:3618-3625
[34]刘彬.基于随机投影和稀疏表征的红外人脸识别方法[D].西安电子科技大学,2009:23-36
[35]苏光大,王晶,熊英.基于约束采样的稀疏表示人脸识别方法[P].中国：201010140797，2010.4.2
[36] Yang J, Wright J, Huang T, etc. Image super-resolution as sparse representation ofraw image patches[C]//IEEE Conference on Computer Vision and PatternRecognition, CVPR2008, Anchorage, AK, United states: Inst. of Elec. and Elec. Eng.Computer Society,2008:1-8
[37] Ma L, He X, Huang Z. Sidescan sonar image super resolution based on sparserepresentation[C]//3rd International Conference on Measuring Technology andMechatronics Automation. Shanghai, China: Trans Tech Publications,2011:1049-1052.
[38]浦剑,张军平.基于词典学习和稀疏表示的超分辨率方法[J].模式识别与人工智能,2010,(03):335-340.
[39]孙玉宝,费选,韦志辉,等.基于前向后向算子分裂的稀疏性正则化图像超分辨率算法[J].自动化学报,2010,(09):1232-1238.
[40]杨淑莹.模式识别与智能计算-Matlab技术实现[M].北京：电子工业出版社,2008:4-6
[41]冈萨雷斯.数字图像处理[M].北京：电子工业出版社,2003:467-474
[42] Schultz R R, Stevenson R L. Extraction of high-resolution frames from videosequences[J]. IEEE Transactions on Image Processing,1996,5(6):996-1011
[43] Schultz R R, Stevenson R L. Improved definition video frame enhancement[C]//Acoustics speech, and signal processing, USA: IEEE Press,1995:2169-2172.
[44] Nguyen N, Milanfar P, Golub G. Efficient generalized cross-validation withapplications to parametric image restoration and resolution enhancement[J]. IEEETransactions on Image Processing,2001,10(9):1299-1308.
[45] Chang H, Yeung D, Xiong Y. Super-resolution through neighbor embedding[C]//Proceedings of the2004IEEE Computer Society Conference on Computer Visionand Pattern Recognition, Washington, DC, United states: Institute of Electrical andElectronics Engineers Computer Society,2004:1275-1282.
[46] Baraniuk R G. Compressive sensing[J]. IEEE Signal Processing Magazine,2007,24(4):118-120+124.
[47]张贤达,保铮.非平稳信号分析与处理[M].北京：国防工业出版社,1998:4-10
[48] Candes E J, Wakin M B. An introduction to compressive sampling: Asensing/sampling paradigm that goes against the common knowledge in dataacquisition[J]. IEEE Signal Processing Magazine,2008,25(2):21-30
[49]李树涛,魏丹.压缩传感综述[J].自动化学报,2009,(11):1369-1377
[50]石光明,刘丹华,高大化,等.压缩感知理论及其研究进展[J].电子学报,2009,(05):1070-1081
[51] Chen S S, Donoho D L, Saunders M A. Atomic decomposition by basis pursuit[J].SIAM Review,2001,43(1):129-159
[52] Donoho D L, Elad M, Temlyakov V N. Stable recovery of sparse overcompleterepresentations in the presence of noise[J]. IEEE Transactions on Information Theory,2006,52(1):6-18
[53] Mallat S. A wavelet tour of signal processing[M]. USA: Academic Press,2008:1-55
[54] Olshausen B A, Field D J. Emergence of simple-cell receptive field properties bylearning a sparse code for natural images[J]. Nature,1996,381(6583):607-607
[55] Candes E J. Ridgelets: theory and applications[D]. USA: Stanford University,1998
[56] Candes E J, Donoho D L. Continuous curvelet transform: I. Resolution of thewavefront set[J]. Applied and Computational Harmonic Analysis,2005,19(2):162-197
[57] Do M N, Vetterli M. The contourlet transform: An efficient directionalmultiresolution image representation[J]. IEEE Transactions on Image Processing,2005,14(12):2091-2106
[58] Le Pennec E, Mallat S. Sparse geometric image representations with bandelets[J].IEEE Transactions on Image Processing,2005,14(4):423-438
[59]张春梅,尹忠科,肖明霞.基于冗余字典的信号超完备表示与稀疏分解[J].科学通报,2006,(06):628-633
[60] Mallat S G, Zhifeng Zhang. Matching pursuits with time-frequency dictionaries[J].Signal Processing, IEEE Transactions on,1993,41(12):3397-3415
[61] Donoho D L, Huo X. Uncertainty principles and ideal atomic decompositionIEEE [J].Transactions on Information Theory,2001,47(7):2845-2862
[62] Baraniuk R, Davenport M, DeVore R and Wakin M. A Simple Proof of the RestrictedIsometry Property for Random Matrices[J]. Constructive Approximation,2008,28(3):253-263
[63] Candes E J, Romberg J K, Tao T. Stable signal recovery from incomplete andinaccurate measurements[J]. Communications on Pure and Applied Mathematics,2006,59(8):1207-1223
[64] Candes E J, Tao T. Near-Optimal Signal Recovery From Random Projections:Universal Encoding Strategies[J]. Information Theory, IEEE Transactions on,2006,52(12):5406-5425
[65]祝勇.基于序列图像的超分辨率重构技术研究[D].长春理工大学，2009
[66]赵建虎.多波束深度及图像数据处理方法研究[D].武汉大学，2002
[67] Do T T, Tran T D, Gan L. Fast compressive sampling with structurally randommatrices[C]//2008IEEE International Conference on Acoustics, Speech and SignalProcessing. Las Vegas, NV, United states: Institute of Electrical and ElectronicsEngineers Inc,2008:3369-3372
[68] Koh K, Kim S, Boyd S. An interior-point method for large-scale1-regularizedlogistic regression[J]. Journal of Machine Learning Research,2007,81519-1555
[69] Figueiredo M A T, Nowak R D, Wright S J. Gradient projection for sparsereconstruction: Application to compressed sensing and other inverse problems[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):586-597
[70] Donoho D L, Tsaig Y. Fast solution of l1-norm minimization problems when thesolution may be sparse[J]. IEEE Transactions on Information Theory,2008,54(11):4789-812
[71] Needell D, Vershynin R. Greedy signal recovery and uncertainty principles[C]//Computational Imaging VI. San Jose, CA, United states: SPIE,2008:3369-3372
[72] Needell D, Tropp J A. CoSaMP: Iterative signal recovery from incomplete andinaccurate samples[J]. Applied and Computational Harmonic Analysis,2009,26(3):301-321
[73] Candes E J, Romberg J, Tao T. Robust uncertainty principles: Exact signalreconstruction from highly incomplete frequency information[J]. IEEE Transactionson Information Theory,2006,52(2):489-509
[74] Lobo M S, Vandenberghe L, Boyd S, etc. Applications of second-order coneprogramming[J]. Linear Algebra and Its Applications,1998,284(1-3):193-228
[75] Herrity K K, Gilbert A C, Tropp J A. Sparse approximation via iterativethresholding[C]//2006IEEE International Conference on Acoustics, Speech andSignal Processing. Toulouse, France: Institute of Electrical and Electronics EngineersInc,2006(3):624-627
[76] Yaghoobi M, Blumensath T, Davies M. Quantized sparse approximation withiterative thresholding for audio coding[C]//2007IEEE International Conference onAcoustics, Speech and Signal Processing. Honolulu, HI, United states: Institute ofElectrical and Electronics Engineers Inc,2007:257-260
[77]李启虎.声纳信号处理引论[M].北京：海洋出版社,2000:107-108;113-118
[78] Yang M, Zhang L. Gabor Feature Based Sparse Representation for Face Recognitionwith Gabor Occlusion Dictionary[C]//11th European Conference on ComputerVision. Berlin, Germany: Springer Verlag,2010:448-461.
[79]丁凯.基于前视声纳的水下目标跟踪技术研究[D].哈尔滨工程大学,2006
[80] Strohmer T, Heath R W, J. Grassmannian frames with applications to coding andcommunication[J]. Applied and Computational Harmonic Analysis,2003,14(3):257-75.
[81] Wang Q, Liu Z. Sampling matrix perturbation analysis of subspace pursuit forcompressive sensing[C]//2010International Symposium on Information andAutomation. Guangzhou, China: Springer Verlag,2011:580-588
[82] Zhao W, Chellappa R, Phillips P J, etc. Face recognition: a literature survey[J]. ACMComputing Surveys,2003,35(4):399-459
[83] Mika S, Ratsch G, Weston J, etc. Fisher discriminant analysis with kernels[C]//Neural Networks for Signal Processing IX. Madison, WI, USA. Proceedings of theIEEE Signal Processing Society Workshop.1999:41-48
[84] Lee D D, Seung H S. Learning the parts of objects by non-negative matrixfactorization[J]. Nature,1999,401(6755):788-791
[85] Bucak S S, Giinsel B, Giirsoy O. Incremental nonnegative matrix factorization forbackground modeling in surveillance video[C]//15th IEEE Signal Processing andCommunications Applications. Piscataway, NJ, USA: IEEE Press,2007:509-12.
[86] Yuan W, Yunde J, Changbo H, etc. Fisher Non-Negative Matrix Factorization forLearning Local Features[J]. Asian Conference on Computer Vision,2004:27-30
[87] Feng T, Li S Z, Heung-Yeung Shum, etc. Local non-negative matrix factorization as avisual representation[C]//ICDL2002. Los Alamitos, CA, USA: IEEE Comput. Soc,2002:178-83.
[88] Xu J, Pi Y, Cao Z. Optimized projection matrix for compressive sensing[J]. EurasipJournal on Advances in Signal Processing,2010:43-48
[89] Nhat V D M, Vo D, Challa S, etc. Efficient projection for compressed sensing[C]//7th IEEE/ACIS International Conference on Computer and Information Science,Portland, OR, United states: Inst. of Elec. and Elec. Eng. Computer Society,2008:322-327
[90]孙友涛,杜丽莉.一种带有正则约束的非负矩阵分解算法[J].内蒙古师范大学学报,2008,(04):477-481
[91]廖锋,高兴宝,杨轩.一种改进的非负矩阵分解算法[J].济南大学学报,2008,(02):193-196
[92]张宇飞.加稀疏约束的非负矩阵分解[D].大连理工大学,2010:40-50
[93] Lee D D, Seung H S. Algorithms for Non-negative Matrix Factorization[J].2001,13:556-562
[94] Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcompletedictionaries for sparse representation[J]. IEEE Transactions on Signal Processing,2006,54(11):4311-4322
[95]滕惠忠,严晓明,李胜全.侧扫声纳图像增强技术[J].海洋测绘,2004,(02):47-49+70
[96]张岩.纹理合成技术的研究及其应用[D].吉林大学,2006:30-38
[97]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001:146-147；419-424
[98] Xu Y, Tseng C, Fu H. Texture recognition by generalized probabilistic decision-basedneural networks[J]. Expert Systems with Applications,2011,38(5):6184-6189
[99]章毓晋.图像分割[M].北京：科学出版社,2001:122
[100] Charalampidis D. Novel textural features and techniques for image segmentation andclassification[D]. Orlando Florida: University of Central Florida,2001:1-5.
[101]马晓川,侯朝焕,唐姗.新的纹理分类算法中国图象图形学报[J],1999,(05):32-35
[102] Ninassi A, Le Meur O, Le Callet P, etc. On the performance of human visual systembased image quality assessment metric using wavelet domain[C]//Human Vision andElectronic Imaging XIII. USA: The International Society for Optical Engineering,2008:610-611
[103] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J].IEEE Transactions on Systems, Man and Cybernetics,1973,3(6):610-621.
[104] Pentland A. Fractal-based description of natural scenes[C]//Proceedings of the IEEEComputer Society Conference on Computer Vision and Pattern Recognition. SilverSpring, MD, USA: IEEE Comput. Soc. Press,1983:201-209.
[105] Tsatsanis M K, Giannakis G B. Object and texture classification using higher orderstatistics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(7):733-50
[106] Zhang H, Tan T. Brief review of invariant texture analysis methods[J]. PatternRecognition,2002,35(3):735-747
[107] Lam W, Li C. Rotated texture classification by improved iterative morphologicaldecomposition[J]. IEEE Proceedings-Vision, Image and Signal Processing,1997,144(3):171-179
[108] Eichmann G, Kasparis T. Topologically invariant texture descriptors[J]. ComputerVision, Graphics, and Image Processing,1988,41(3):267-281
[109] Krishnamachari S, Chellappa R. Multiresolution Gauss-Markov random field modelsfor texture segmentation[J]. IEEE Transactions on Image Processing,1997,6(2):251-267.
[110] Tamura H, Mori S, Yamawaki T. Textural features corresponding to visualperception[J]. IEEE Transactions on Systems, Man and Cybernetics,1978,8(6):460-73.
[111] Bovik A C, Clark M, Geisler W S. Multichannel texture analysis using localizedspatial filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-73
[112]洪继光.灰度-梯度共生矩阵纹理分析方法[J].自动化学报,1984,(01):22-25
[113] Reed T R. A review of recent texture segmentation and feature extractiontechniques[J]. Image Understanding,1993,57(3):359-72
[114]谢美华,王正明.基于图像梯度信息的插值方法[J].中国图象图形学报,2005,(07):856-861
[115] Alam M S, Iftekharuddin K M, Karim M A. Polarization-encoded optical shadowcasting: Edge detection using Roberts operator[J]. Microwave and OpticalTechnology Letters,1993,6(3):190-193
[116] Dony R D, Wesolkowski S, Edge detection on color image using vector angles[C]//IEEE Conference on Electrical and Computer Engineering, Edmonton, Alta. Canada:IEEE Press,1999,(2):687-692.
[117] Alam M S, Gu Y. Sobel operator based multiobject joint transform correlation[J].Optik (Jena),1995,100(1):28-32
[118] Tong X, Ren A, Zhang H, etc. Edge detection based on genetic algorithm and sobeloperator in image[C]//International Conference on Graphic and Image Processing,Cairo, Egypt: SPIE,2011:.
[119]葛静祥.图像纹理特征提取及分类算法研究[D].天津大学,2010:35-38
[120] Bruzzone L, Serpico S B, Vernazza G. Effects of parameter tuning and de-specklefiltering on the accuracy of SAR image classification based on gray-levelco-occurrence matrix features[J]. Geoscience and Remoto Sensing,1997,(2):764-766
[121]杨清跃,高飞,聂青.纹理图像识别中的旋转不变性分析[J].计算机工程与应用,2010,(33):205-207
[122]曹佃国,陈浩杰,李鹏.基于Matlab的双线性插值算法在图像旋转中的应用[J].中国印刷与包装研究,2010,(04):74-78
[123]孙玉宝,韦志辉,肖亮,等.多形态稀疏性正则化的图像超分辨率算法[J].电子学报,2010,(12):2898-2903
[124]乔建苹.超分辨率重建与图像增强技术研究[D].山东大学,2008
[125] Ng M K, Bose N K. Mathematical analysis of super-resolution methodology[J]. IEEESignal Processing Magazine,2003,20(3):62-74
[126] Meyer Y. Oscillating patterns in image processing and nonlinear evolutionequations[M]. Baston：Amer Mathematical Society,2001:35-46
[127] Arivazhagan S, Ganesan L, Subash Kumar T G. Texture classification using ridgelettransform[J]. Pattern Recognition Letters,2006,27(16):1875-1883
[128] Guo Q, Yu S. Image denoising using a multivariate shrinkage function in the curveletdomain[J]. IEICE Electronics Express,2010,7(3):126-131
[129] Kazemi F M, Izadian J, Moravejian R, etc. Numeral recognition using curvelettransform[C]//6th IEEE/ACS International Conference on Computer Systems andApplications, Qatar: Inst. of Elec. and Elec. Eng. Computer Society,2008:606-612.
[130] Tang L, Zhao Z. Multiresolution image fusion based on the wavelet-based contourlettransform[C]//10th International Conference on Information Fusion, Quebec, QC,Canada: Inst. of Elec. and Elec. Eng. Computer Society,2007:1-6
[131] Liu K, Guo L, Chen J. Contourlet transform for image fusion using cycle spinning[J].Journal of Systems Engineering and Electronics,2011,22(2):353-357
[132] Lukin V V, Fevralev D V, Ponomarenko N N, etc. Discrete cosine transform-basedlocal adaptive filtering of images corrupted by nonstationary noise[J]. Journal ofElectronic Imaging,2010,19(2):7-15
[133] Demanet L, Ying L. Wave atoms and sparsity of oscillatory patterns[J]. Applied andComputational Harmonic Analysis,2007,23(3):368-387
[134] Demanet L, Ying L. Curvelets and wave atoms for mirror-extended images[C]//Wavelets XII. San Diego, CA, United states: SPIE,2007:1-15
[135] Liu G, Feng X, Zhang X. Threshold algorithm of texture images with wave atoms[J].Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology,2009,31(8):1791-1795
[136] Lee T S. Image representation using2D Gabor wavelets[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(10):959-971
[137] Zeng Z. Gabor feature-based complete fisher discriminant framework for facialfeature extraction[C]//International Conference on Wireless Communications andSignal Processing, Nanjing, China: IEEE Computer Society,2009:1-5
[138] Zhang C, Wang X, Zhang H. An intelligent algorithm for enhancing contrast forimage based on discrete stationary wavelet transform and in-complete betatransform[C]//International Conference on ffective Computing and IntelligentInteraction. Beijing, China: Springer Verlag,2005:135-143
[139] Wang X H, Istepanian R S H, Yong H S. Microarray image enhancement bydenoising using stationary wavelet transform[J]. IEEE Transactions onNanobioscience,2003,2(4):184-189
[140] Do M N, Vetterli M. Contourlets: A new directional multiresolution imagerepresentation[C]//The Thirty-Sixth Asilomar Conference on Signals Systems andComputers. Pacific Groove, CA, United states: Institute of Electrical and ElectronicsEngineers Computer Society,2002:497-501.
[141] Marcelja S. Mathematical description of the responses of simple cortical cells[J].Journal of the Optical Society of America,1980,70(11):1297-300
[142] Daugman J G. Two-dimensional spectral analysis of cortical receptive fieldprofiles[J]. Vision research,1980,20(10):847-56
[143] Grigorescu S E, Petkov N, Kruizinga P. Comparison of texture features based onGabor filters[J]. IEEE Transactions on Image Processing,2002,11(10):1160-1167
[144]谢建辉.纹理特征提取与分类研究[D].华中科技大学,2008
[145]汪雄良,王春玲.基于改进基追踪方法的信号去噪[J].电子技术应用,2005,(08):19-21
[146] Xiao C, Duan J, Yu J. POCS super-resolution reconstruction from image sequences[J].Beijing Gongye Daxue Xuebao/Journal of Beijing University of Technology,2009,35(1):108-113
[147] Ma L, He X, Huang Z. Sidescan sonar image super resolution based on sparserepresentation[C]//3rd International Conference on Measuring Technology andMechatronics Automation. Shanghai, China: Trans Tech Publications,2011:1049-1052.
[148]邓承志.图像稀疏表示理论及其应用研究[D].华中科技大学,2008