摘要
在模式识别领域,如何在高维数据中寻找有效的低维表示是个核心问题。而特征抽取是解决此问题的关键环节。本文对基于图嵌入和视觉注意的特征抽取理论与算法进行了较为深入的研究,主要工作和研究成果如下：
(1)在基于图嵌入方法的特征抽取算法中,邻域图的构造是整个算法的核心问题。本文改进了类间惩罚图的构造方法,并设计了类间相斥图。由于改进的类间惩罚图刻画了更多的局部边缘信息,而类间相斥图则描述了全局边缘信息,本文算法综合了两个图的优点,这有助于该算法在优化目标函数过程中寻找最佳的鉴别边缘。在此基础上,提出了融合类间相斥图的局部最大边界嵌入算法(RLMME)。本在YALE、ORL、AR人脸数据库以及USPS数字手写体数据库上的实验结果证实了该算法的识别性能优于PCA, LDA, LPP, MFA。
(2)在邻域图的构造过程中,如何设计一个正确反映样本关系的边界权重函数非常重要。在邻域图中,边界权重函数的本质就是样本相似度或差异度的度量函数。本文提出了模糊局部保持嵌入的特征抽取算法(FLMME).在该算法中,我们设计了一种新的模糊渐进的权重度量函数,该函数赋予同类中越近的近邻越大的权重,对于异类的近邻样本,越近的近邻则赋予越小的权重。基于此权重度量准则,本文构造了模糊渐进的类内邻域图和类间邻域惩罚图。在利用新构造的邻域图得到的投影子空间上,相邻同类样本将更加紧致,而相邻的不同类样本则更加远离。在WINE人工数据集,YALE、ORL、AR人脸数据库以及USPS数字手写体数据库上的实验结果表明该算法比PCA, LDA, LPP, RLMME算法更为有效。
(3)近二十年来,人们提出了许多视觉注意的计算模型。但是这些模型依然存在着选择合适的初级特征以及特征融合策略问题。为此,本文提出了融合边缘信息稀疏嵌入的显著性视觉注意改进算法。在视觉特征抽取初级阶段,本文引入边缘特征,以增加全局轮廓信息的描述。此外,通过考虑不同的特征显著性的差异,本文提出了稀疏显著性因子来度量特征显著的程度。越稀疏的特征,其显著程度越高。根据特征的显著程度,可以把不同特征图重新组合为稀疏嵌入的显著图。在自然彩色图像上的实验结果表明,相对于传统的视觉注意算法,改进后的算法能更准确合理地刻画显著区域。此外在Sheffield建筑物数据库上的识别实验表明,基于本文算法得到的Gist特征优于传统方法,这进一步证明了本文提出算法的有效性。
(4)在传统的建筑物识别方法基础上,本文提出了多尺度Gist特征流形方法,并分阶段描述了基于该方法的建筑物识别模式。在特征抽取阶段,本文抽取了一种多尺度Gist特征,用以描述建筑物图像的全局结构信息。由于高维Gist特征具有潜入在低维特性,所以在特征降维阶段,本文提出了增强模糊局部最大边界嵌入算法(EFLMME)对Gist特征进行维数约简单。在Sheffield建筑物数据库上的实验效果表明,相对于传统的建筑物识别方法,本文提出的方法对光照变化、旋转变换、有遮挡等问题具有较强的鲁棒性,在建筑物图像上的识别率也得到显著的提高。
It is one of the most important problems to find the low dimensional and effective representations in the field of pattern recognition. And feature extraction is a key step to solve the problem. The dissertation presented the deep researches on feature extraction theorems and algorithms based on graph embedding and visual attention. The main works and research results are as follows:
(1) In graph-based dimensionality reduction algorithms, the construction of neighborhood graph is an essential problem in the graph embedding algorithms for feature extraction. The paper improved the construction of inter-class penal graph and designed a novel inter-class repulsion graph. The improved inter-class penal graph characterized more local marginal information and the inter-class repulsion graph described the global marginal information, which help us find the optimal discriminant margin. According to the local and global inter-class graph, we proposed a local maximal margin embedding algorithm combined with inter-repulsion graph (RLMME). Experimental results on the Yale, ORL, AR face databases and USPS handwriting digital databases show that our proposed algorithm outperforms PCA, LDA, LPP, and MFA.
(2) In the procedures of constructing the neighborhood graph, it is crucial to construct a marginal weithted function that can correctly reflect the relationships among the samples. In the neighbor graph, the weight of edge is, in essence, used to measure the similarity and diversity between samples. The paper presented an improved algorithm called fuzzy local maximal marginal embedding (FLMME) for linear dimensionality reduction. Significantly differing from the existing graph-based algorithms is that two novel fuzzy gradual graphs are constructed in FLMME, which help to pull the near neighbor samples in same class nearer and nearer and repel the near neighbor samples of margin between different classes farther and farther when they are projected to feature subspace. The proposed FLMME algorithm is evaluated through experiments by using the WINE database, the Yale, ORL and AR face image databases and the USPS handwriting digital databases. The results show that the FLMME outperforms PCA. LDA, LPP and RLMME.
(3) Numerous computational models of visual attention have been suggested during the last two decades. But, there are still some challenges such as which of early visual features should be extracted and how to combine these different features into a unique "saliency" map. According to these challenges, we proposed a sparse embedding visual attention system combined with edge information, which is described as a hierarchical model in this paper. In the first stage, we extract edge information besides color, intensity and orientation as early visual features, adding the global edge information in the saliency maps. In the second stage, we present a novel sparse embedding feature combination strategy based on sparse saliency factor. Results on scene image show that our model outperforms other visual attention computational models. In addition, experimental results on the Sheffield building database show that the gist feature based on the proposed method can achieve the better performance than that of traditional method. This further testified the effectiveness of the proposed method.
(4) Multi-scale gist (MS-gist) feature manifold for building recognition is presented in the paper. It is described as a two-stage model. In the first stage, we extract the multi-scale gist features that represent the structural information of the building images. Since the MS-gist features are extrinsically high dimensional and intrinsically low dimensional, in the second stage, an enhanced fuzzy local maximal marginal embedding (EFLMME) algorithm is proposed to project MS-gist feature manifold to low dimensional subspace. To evaluate the performance of our proposed model, experiments were carried out on the Sheffield buildings database. Results show that the proposed model is superior to other models in practice of building recognition and can handle the building recognition problem caused by rotations, variant lighting conditions and occlusions very well.
引文
[1]H. S. Seung, D. D. Lee. The Manifold Ways of Perception. Science,2000,290(5500): 2268-2269.
[2]孙明明.流行学习理论和算法研究.南京理工大学博士论文.2007
[3]罗四维,赵连伟.基于谱图理论的流形学习算法.计算机研究与发展,2006,43(7)：1173-1179.
[4]D.马尔著.视觉计算理论.姚国正,刘磊,王云九译.北京：科学出版社,1988
[5]D. Navon, Forest before trees:The procedure of global features in visual perception. Cognitive Psychology,1997,9(2):353-383.
[6]A.K. Jain, R.P.W. Duin, J. Mao. Statistical pattern recognition:A review. IEEE Trans. on Pattern Analysis and Machine Intelligence,2000,22(1):4-37.
[7]罗四维等著.视觉感知系统信息处理理论.北京：电子工业出版社,2006.
[8]杨静宇,金忠,杨健.模式特征抽取研究进展.2009.
[9]郭军.流形学习及其在模式识别中的应用.北京邮电大学博士论文.2007
[10]尹峻松.流行学习理论与方法研究在人脸识别中的应用.国防科学技术大学.2007
[11]L.G. Ungerleiger, M. Mishkin. Two cortical visual systems. In:D. J. Ingle, M. A.Goodale, R.J.W. Mansfield, Analysis of visual behavior. Cambridge, MA:MIT Press, 1982:549-586.
[12]M. Goodale, A.D. Milner. Separate visual pathways for perception and action. Trends in Neuroscience,1992,15(1):20-25.
[13]A.D. Milner, M.A. Goodale. The visual brain in action. USA:Oxford University Press, 1995.
[14]M.Watanabe, Reward expectancy in primate prefrontal neurons. Nature,1996, 382(6592):521-535.
[15]B. Scholkopf, A. Smola. Learning with Kernels. Cambridge, Mass.:MIT Press,2002.
[16]B. Scholkopf, A. Smola, K. R. Muller. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation,1998,10(5):1299-1319.
[17]B. Scholkopf, S. Mika, C. Burges, P. Knirsch, K. R. Muller, G. Ratsch, A. Smola. Input space vs. feature space in kernel-based methods. IEEE Trans. on Neural Networks, 10(5):1000-1017, September 1999.
[18]A.J. Smola, S. Mika, B. Scholkopf, R.C. Williamson. Regularized Principal Manifolds. Journal of Machine Learning Research, (1)3:179-209,2001.
[19]S.T. Roweis, L.K. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science,2000,290(5500):2323-2326.
[20]S.C. Yan, D. Xu, B.Y. Zhang. Graph embedding and extensions:a general framework for dimensionality reduction. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2007,29(1):40-51.
[21]Y. Bengio, J.F. Paiement, P.Vincent. Out-of-sample extensions for LLE, Isomap, MDS, Eigenmaps and Spectral Clustering. Technical Report 1238, University de Montreal, July 25,2003.
[22]黄鸿.图嵌入框架下流形学习理论及应用研究.重庆大学博士论文.2008
[23]尹峻松,肖健,周宗潭,胡德文.非线性流形学习方法的分析与应用.自然科学进展.2007,17(8)：1015-1025.
[24]A.Treisman, G. Gelade. A feature-integration theory of attention. Cognitive Psychology, 1980,12(1):97-136.
[25]C. Koch, S. Ullman. Shifts in selective visual attention:towards the underlying neural circuitry, Human Neurobiology,1985,4(4):219-227.
[26]L.Itti, C.Koch, E.Niebur, A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence,1998,20 (11): 1254-1259.
[27]L. Itti, C. Koch. Saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research,2000,40 (10-12):1489-1506.
[28]L. Itti. Neuromorphic Attentional Selection for Efficient Allocation of Computing Resources. In:Proc. Virtual Worlds and Simulation Conference,2002.
[29]L.Itti, C. Koch. Computational Modeling of Visual Attention. Nature Reviews Neuroscience,2001,2(3):194-203.
[30]L.Itti. Models of bottom-up attention and saliency. Neurobiology of Attention. San Diego, CA:Elsevier,2005,576-582.
[31]L. Itti, P.Baldi. A principled approach to detecting surprising events in video. IEEE Conference on Computer Vision and Pattern Recognition,2005, pp.631-637.
[32]S.Satoh, S.Miyake. A model for selective visual attention based on discrete scale-spaces, Knowledge-Based Intellignet Information And Engineering Systems, PT 2, Proceedings Lecture Notes In Artificial Intelligence,2003,2774:147-154.
[33]T. Kohonen. A Computational Model of Visual Attention. Proceedings of the International Joint Conference on Neural Networks,2003,4:3238-3243.
[34]冯松鹤.面向感知的图像检索及自动标注算法研究.北京交通大学博士论文.2009
[35]刘伟.图像检索中若干问题研究.浙江大学博士论文.2007
[36]陈嘉威.视觉注意计算模型的研究及其应用.厦门大学博士论文.2009
[37]单列.视觉注意机制的若干关键技术及应用研究.中国科技大学博士论文.2008
[38]L.Itti. Models of bottom-up and top-down visual attention. Dissertation (Ph.D.), California Institute of Technology.2000
[39]W. Dirk. Interactions of visual attention and object recognition:computational modeling, algorithms, and psychophysics. Dissertation (Ph.D.), California Institute of Technology. 2006
[40]D.S. Gao. A discriminant hypothesis for visual saliency:computational principles, biological plausibility and applications in computer vision. Dissertation (Ph.D.), University of California.2008
[41]K. Fukunaga. Introduction to Statistical Pattern Recognition. New York:Academic Press. Inc.2nd ed.1990.
[42]边肇棋,张学工.模式识别(第二版).北京：清华大学出版社,2000
[43]J. B.Tenenbaum, V. Silva, J. C.Langford. A global geometr is framework for nonlinear dimensionality reduction. Science,2000,290(5500):2319-2323.
[44]J. Wang, Z. Zhang, H.Zha. Adaptive Manifold Learning. Advances in Neural Information. Processing Systems,2004
[45]V.Silva, J.Tenenbaum, Global versus Local Methods in Nonlinear Dimensionality Reduction. Advances in Neural Information Processing Systems,2003,15:705-712
[46]K.Weinberger, B.Packer, L.Saul. Nonlinear Dimensionality Reduction by Semidefinite Programming and Kernel Matrix Factorization. Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics,2005
[47]J.Zhang, L.He, Z.Zhou. Analyzing Magnification Factors and Principal Spread Directions in Manifold Learning. Proceedings of the 9th Online World Conference on Soft Computing in Industrial Applications (WSC9),2004
[48]何力,张军平,周志华.基于放大因子和延伸方向研究流形学习算法.计算机学报,2005,28(12)：2000-2009
[49]詹德川,周志华.基于集成的流形学习可视化.计算机研究与发展,2005,2(1)：1533-1537
[50]J. Park, Z. Zhang, H. Zha. Local Smoothing for Manifold Learning. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004, 452-459
[51]Z. Zhang, H. Zha. Local Linear Smoothing for Nonlinear Manifold Learning. Technical report. Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA,2003.
[52]Y. Bengio, O. Delalleau, N. Le Roux. Learning Eigenfunctions Links Spectral Embedding and Kernel PCA. Neural Computation,2004,16(10):2197-219.
[53]A. Tversky, D. Kahneman. Extension versus intuitive reasoning:The conjunction fallacy in probability judgment, Psychological Review 1983,90(4):293-315.
[54]J.Ham, D.Lee, S.Mika, A Kernel View of the Dimensionality Reduction of Manifolds. Proceedings of ACM International Proceeding Series. ACM Press New York, NY, USA, 2004.
[55]X.Yang, H. Fh, H.Zha. Semi-Supervised Nonlinear Dimensionality Reduction. Proceedings of the 23rd international conference on Machine learning. ACM Press New York, NY, USA,2006.1065-1072
[56]D. Ridder, O. Kouropteva, O. Okun. Supervised Locally Linear Embedding. Proceedings of Joint International Conference on ICANN/ICONIP,2003:333-341.
[57]X. Geng, D. Zhan, Z. Zhou, Supervised Nonlinear Dimensionality Reduction for Visualization and Classification. IEEE Trans. on Systems, Man, and Cybernetics-Part B: Cybernetics,2005,35(6):1098-1107.
[58]C. Li, J.Guo, Supervised Isomap with Explicit Mapping. Proceedings of First International Conference on Innovative Computing, Information and Control,2006
[59]H. Li, W.Chen, I.Shen, Supervised Local Tangent Space Alignment for Classification. Proceedings of International Joint Conference on Artificial Intelligence,2005.1620
[60]M. Belkin, P. Niyogi, Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation,2003,15(6):1373-1396
[61]X.F. He, P.Niyogi. Locality Preserving Projections. Proceedings of Advances in Neural Information Processing Systems 16,2003
[62]E. Kokiopoulou, Y. Saad. Orthogonal Neighborhood Preserving Projections. Proceedings of IEEE International Conference on Data Mining,2005.234-241.
[63]X.F. He, D. Cai, S.C.Yan. Neighborhood Preserving Embedding. Proceedings of the 10th IEEE International Conference on Computer Vision,2005.1208-1213.
[64]T. Zhang, J. Yang, D. Zhao, Linear Local Tangent Space Alignment and Application to Face Recognition. NeuroComputing,2007,70(7-9):1547-1553
[65]J.Yang, D. Zhang, J.Y. Yang, Globally Maximizing, Locally Minimizing:Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics. IEEE Trans. on Pattern Analysis and Machine Intelligence,2007,9(4):650-664
[66]K.R. Cave, J.M. Wolfe. Modeling the role of parallel processing in visual search. Cognitive Psychology,1990,22(2):225-271.
[67]F. Van Der Velde, M. De Kamps, G.T. Van Der Kleij, CLAM:Closed-loop attention model for visual search. Neurocomputing,2004,58-60:607-612.
[68]F. Simone, B. Gerriet, R. Erich. Goal-directed search with a top-down modulated computational attention system. Lecture Notes in Computer Science, v 3663, Pattern Recognition:27th DAGM Symposium:Proceedings,2005,117-124.
[69]K.W. Lee, H. Buxton, J. F. Feng. Cue-guided search:A computational model of selective attention. IEEE Trans. on Neural Networks,2005,16(4):910-924
[70]G. Herzog, P. Wazinski. Visual Translator:linking perceptions and natural language descriptions, Artificial Intelligence Review,1994,8(2-3):175-187
[71]P. Laar van de, T.Heskes, S.Gielen. Task-dependent learning of attention. Neural Networks,1997,10(6):981-992
[72]I. A. Rybak, V. I. Gusakova, A.V. Golovan, L.N. Podladchikova, N.A. Shevtsova. A model of attention-guided visual perception and recognition. Vsion Research,1998, 38(15-16):2387-2400
[73]N.M. Oliver, B. Rosario, A. Pentland. A bayesian computer vision system for modeling human interactions. IEEE Trans. on Pattern Analysis and Machine Intelligence,2000, 22(8):831-843
[74]R.D. Rimey, C.M. Brown. Selective attention as sequential behavior:modeling eye movements with an augmented hidden markov model. Proceedings:DARPA Image Understanding Workshop,1990,840-849
[75]A.A. Salah, E. Alpaydin, L. Akarun. A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence,2002,24(3):420-425
[76]V. Navalpakkam, L. Itti. A goal oriented attention guidance model. Lecture Notes in Computer Science,2002,2525:453-461
[77]V. Navalpakkam, L. Itti. An integrated model of top-down and bottom-up attention for optimal object detection, In:Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2006,2049-2056
[78]F. H. Hamker, M. Zirnsak, D. Calow. The spatial reentry hypothesis of perisaccadic visual perception, Journal of Psychophysiology 2005,19 (2):121-131
[79]桑农,李正龙,张天序.人类视觉注意机制在目标检测中的应用.红外与激光工程,2004,33(1)：38-42
[80]王岳环,张天序.实时红外小目标预检测中注意机制分析.华中科技大学学报,2001,29(11)：53～55
[81]王岳环,曾南志,张天序.红外舰船检测中注意力机制的并行实现.红外线与激光工程,2001,30(6)：401～404
[82]王岳环,曾南志,张天序.基于注意机制的实时红外舰船检测.中国图象图形学报,2003,8(3)：241～245
[83]A.Samal, P.A. Iyengar. Automatic recognition and analysis of human faces and facial expressions:a survey. Pattern Recognition,1992,25(1):65-77.
[84]R. Chellappa, C.L. Wilson, S. Sirohey. Human and machine recognition of faces:a survey. Proc. IEEE,1995,83(5):705-740.
[86]A. Rosenfeld. Survey:Image analysis and computer vision:1995, Computer Vision and Image Understanding,1996,66(3):568-612.
[87]M.A. Grudin. On internal representations in face recognition systems, Pattern ecognition, 2000,33(10):1161-1177.
[88]A. Pentland. Looking at people:sensing for ubiquitous and wearable computing. IEEE Trans. on Pattern Analysis and Machine Intelligence.2000,22(1):107-119.
[89]周杰,卢春雨,张长水,李衍达.人脸识别方法综述.电子学报,2000,28(4)：102-106.
[90]I. Craw, N. Costen, T. Kato, How should we represent faces for automatic recognition? IEEE Trans. on Pattern Analysis and Machine Intelligence.1999,21(8):725-736
[91]R.Baron. Mechanisms of human facial recognition. Int. J. Man-Machine Studies,1989, (15)2:283-310.
[92]V.Bruce. Recognizing faces. London:Erlbaum,1988.
[93]M.Bichsel. Perceiving and recognizing faces, Mind and Language,1990,342-364.
[94]H. Ellis. Aspects of face processing, Dordrecht:Nijhoff.1986.
[95]荆晓远.模式分类技术在人脸识别中的应用.博士学位论文.南京理工大学,1998.
[96]洪子泉,杨静宇.基于奇异值特征和统计模型的人像识别算法.计算机研究与发展,1994,31(3)：60-65.
[97]洪子泉.基于代数方法的图象特征抽取和识别.博士学位论文.南京理工大学,1990.
[98]洪子泉,杨静宇.用于图象识别的图象代数特征抽取.自动化学报,1992,18(2)：232-238
[99]Z.Q. Hong. Algebraic feature extraction of image for recognition. Pattern Recognition,1991,24(3):211-219
[100]J. Duchene, S, Leclercq. An optimal Transformation for discriminant and principal component analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence,1988, 10(6):978-983
[101]Z.Q. Hong, J.Y. Yang. Optimal discriminant plane for a small number of samples and design method of classifier on the plane. Pattern Recognition,1991,24(4):317-324
[102]K. Liu,Y. Q. Chen, J. Y. Yang. Algebraic feature extraction for image recognition based on an optimal discriminant criterion. Pattern Recognition,1993,26(6):903-911
[103]郭跃飞,姜志华,杨静宇一种新的代数特征抽取方法及人脸识别.南京理工大学学报,1997,21(5)：387-390.
[104]黄修武,杨静宇,郭跃飞.基于隶属度的人脸图象特征抽取和识别.电子学报,1998,26(5)：89-92.
[105]黄修武,郭跃飞,杨静宇.基于代数方法的图像特征抽取和识别.南京理工大学学报,1998,22(1)：1-5.
[106]黄修武.基于代数方法的人脸图象特征提取与识别.博士学位论文.南京理工大学,1998.
[107]周志华,皇甫杰,张宏江,陈祖翰.基于神经网络集成的多视角人脸识别.计算机研究与发展,2001,38(10)：1204-1210
[108]J. Yang, D. Zhang, J.Y. Yang, Two-dimensional PCA:A new approach to appearance based face representation and recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence,2004,26(1):131-137
[109]D. Sagarmay, Y.C. Zhang. An overview of content based image retrieval techniques. Advanced Information Networking and Applications,2004, (2)1:59-64
[110]R.Hutchings, W. Mayol-Cuevas. Building Recognition for mobile Deviecs: Incorporating Postional Information with Visual Features, CSTR-06-017, Computer Science, University of Bristol,2005
[111]C.Harris, M.Stephens. A combined corner and edge detector, in:Alvey vision Conf., 1988, pp.147-151
[112]Q.Iqbal, J.K.Aggarwall. Applying perceptual grouping to content-based image retrieval: building images. IEEE Conf. Comput. Vision Pattern Recognition,1999,1:42-48
[113]A. Stassopoulou. Building detection using bayesian networks.IEEE Trans. on Pattern Analysis and Machine Intelligence,2000,83(5):705-740
[114]Y. Li, L.G. Shapiro. Consistent line clusters for building recognition in CBIR..IEEE Int. Conf. Pattern Recognition,2002,3:952～956
[115]D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Computer Vision,2004,60(2):169～191
[116]G. Fritz, C. Seifert, M. Kumar, L. Paletta. Building detection from mobile imagery using informatives SIFT descriptors, in:SCIA,2005, pp.629-638
[117]W. Zhang, J. Kosecka. Hierarchical building recognition. Int. J. Image and Vision Computing,2007,25:704～716
[118]J. Li, N.M. Allinson. Subspace learning-based dimensionality reduction in building recognition. Int. J. Neurocomputing,2009,73(1-3):324～330
[119]M.S. Lewiciki, T.J. Sejnowski. Coding time-varying signals using spare shiftinvariant representations. In:Kearns M S, Solla S A, Cohn D A, eds. Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press,1999
[120]杨健.线性投影分析的理论与算法及其在特征抽取中的应用研究.南京理工大学博士论文.2002
[121]H.B. Barlow, Single units and sensation:a neuron doctrine for perceptual psychology? Perception,1972,1:371～394
[122]C. Von der Malsburg, W. Schneider. A neural cocktail-party processor. Biology Cybernetics,1986,54(1):29～40
[123]J. G. Daugman. Complete discrete 2-D Gabor transforms by networks for image analysis and compression. IEEE Trans. ASSP,1988,36(1):169～179
[124]K.Hammouda, E.Jernigan. Texture Segmentation Using Gabor Filters. University of Waterloo, Ontario, Canada,2000.
[125]D. Marr, H.K. Nishihara. Representation and recognition of the spatial organization of three dimensional shapes. A.I. Memo 416, The Artificial Intelligence Lab., MIT,1977, 1-33.
[126]I. Biederman. Recognition-by-Components:a theory of human image understanding. Psychological Review,1987,94(2):115～147
[127]A. Levy, M. Lindenbaum. Sequential Karhunen-Loeve basis extraction and its application to images. IEEE Trans. on Image Processing, vol.9,1371-1374,2000
[128]Aapo Hyvarinen and Erkki Oja. Independent Component Analysis:Algorithms and Applications. Neural Networks,2000,13(4-S):411～430.
[129]卫立波.基于谱图的视觉注意模型研究.硕士论文.重庆.重庆大学,2010.
[130]X.F. He, D. Cai, J. W. Han. Learning a Maximum Margin Subspace for Image Retrieval. IEEE Trans. on Knowledge and Data Engineering,2008,20(2):189-201.
[131]H.T. Chen, H.W. Chang, T.L. Liu. Local Discriminant Embedding and Its Variants. IEEE Conf. Computer Vision and Pattern Recognition,2005,2:846-853
[132]R.O. Duda, P.E. Hart, D.G. Stork. Pattern Classification, John Wiley & Sons, second ed., 2001
[133]H. F. Li, T. Jiang, K. Zhang. Efficient and robust feature extraction by maximum margin criterion. IEEE Trans. on Neural Networks,2006,17(1):157-165
[134]J. M. Keller, M. R. Gray, J.A. Givern. A fuzzy k-nearest neighbour algorithm. IEEE Trans. Syst. Man Cybernet.1985,15(4):580-585
[135]http://archive.ics.uci.edu/ml
[136]L. Itti, C. Koch. Feature combination strategies for saliency-based visual attention systems. Electronic Imaging 2001,10(1):161-169
[137]A. Shashua. S. Ullman, Structural Saliency:The Detection of Globally Salient Structures Using a Locally Connected Network. IEEE Trans. on Pattern Analysis and Machine Intelligence,1988; 17(1):90-94
[138]P.L. Rosin. Edges:Saliency Measures and Automatic Thresholding. Machine Vision and Applications 1997; 9(4):139-159
[139]A. Shashua, S.Ullman. Structural saliency:the detection of globally salient structures using a locally connected network".IEEE Trans. on Pattern Analysis and Machine Intelligence 1988; 7(1):90-94
[140]S. Wang, T. Kubota, J. M. Siskind. Salient boundary detection using ratio contour. Neural Information Processing System Conference (NIPS) 2003. Vancouver, Canada
[141]C. siagian, L. Itti. Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans. on Pattern Analysis and Machine Intelligence 2007, 29(2):300-312
[142]J. Li, Nigel M. Allinson. Subspace learning-based dimensionality reduction in building recognition. Int. J. Neurocomputing 2009,73(1-3):324-330
[143]W. Zhang, J. Kosecka. Hierarchical building recognition. Int. J. Image and Vision Computing 2007,25(5):704-716
[144]A. Oliva, P. G., Schyns. Coarse blobs or fine edges? Evidence that information diagnosticity changes the perception of complex visual stimuli. Cognitive Psychonolgy 1997,34(1):72-107
[145]A. Oliva, A. Torralba. Modeling the shape of the scene:A holistic representation of the spatial envelope. Int. J. Computer vision 2001,42(3):145-175
[146]A. Oliva. Gist of scene. In Neurobiology of Attention, L.Itti, G. Rees and J.K. Tsotsos(Eds.), Elsevier, San Diego, CA 2005,251-256
[147]S.C. Chong. A. Treisman, Representation of statistical properties. Int. J. Vision Research 2003,43(4):393-404
[148]D. Marr, E.C. Hildreth. Theory of edge detection, Proceeding of the Royal Society of London. Series B, Biological Sciences 1980,207(1167):187-217.
[149]A. Shashua, S. Ullman. Structural saliency:the detection of globally salient structures using a locally connected network. IEEE. Conf. Comput. Vision 1988; 321-327.
[150]Y. Sugase, S. Ueno, K. Kawano. Global and fine information coded by single neurons in the temporal visual cortex, Nature 1999,400(6747):869-873.
[151]C. Ackerman, L. Itti. Robot Steering with Spectral Image Information. IEEE trans. Robotics 2005,21(2):247-251.
[152]D.C. Tao, X.L. Li, X.D. Wu, S.J. Maybank. Geometric Mean for Subspace Selection. IEEE trans. on Pattern Analysis and Machine Intelligence,2009,31(2):260-274
[153]W. Bian, D.C. Tao. Harmonic Mean for Subspace Selection. IEEE Int. Conf,19th ICPR, 2008
[154]T.H. Zhang, D.C. Tao, X.L. Li, J. Yang. Patch Alignment for Dimensionality Reduction. IEEE Trans. Knowl. Data Eng.2009,21(9):1299-1313
[155]T.Y. Zhou, D.C. Tao, X.D. Wu. Manifold elastic net:a unified framework for sparse dimension reduction. Data Mining and Knowledge Discovery,2010,22(3):340-371
[156]H. Li, T. Jiang, K. Zhang. Efficient and robust feature extraction by maximum margin criterion. IEEE Trans. on Neural Networks 2006,17 (1):1157-1165
[157]F.X. Song, D. Zhang, D.Y Mei, Z. Guo. A multiple maximum scatter difference discriminant criterion for facial feature extraction. IEEE Trans. on systems, man, and cybernetics-part B:Cybernetics 2007,33 (6):1599-1566
[158]http://eeepro.shef.ac.uk/building/dataset.rar
[159]R. Epstein, A. Harris, D. Stanley, N. Kanwisher. The parahippocampal place area: Perception, encoding, or memory retrieval?, Neuron,2000,23:115-125.
[160]B. Olshausen, D. Field, Sparse coding with an overcomplete basis set:A strategy employed by V1?, Vision Research 1997,37:3311-3325.
[161]T. Serre. Learning a dictionary of shape-components in visual cortex:Comparison with neurons, humans and machines, Dissertation(P.h.D), MIT,2006.
[162]D.D. Lee, H.S. Seung. Learning the parts of objects by non-negative matrix factorization. Nature 1999,401(21):788-792.
[163]D.J. Song, D.C. Tao. Biologically inspired feature manifold for scene classification, IEEE Trans. on Image Processing 2010,19(1):174-184.
[164]W. John, Y. Allen, G. Arvind, S. Shankar, Y. Ma. Robust Face Recognition via Sparse Representation. IEEE Trans. on Pattern Analysis and Machine Intelligence,2009, 31(2):210-227.
[165]L.S. Qiao, S.C. Chen, X.Y. Tan. Sparsity preserving projections with applications to face recognition, Pattern Recognition 2010,43(1):331-341.
[167]R. Epstein, N. Kanwisher, A cortical representation of the local visual environment, Nature 1998,392(6676):598-601.