模拟视觉机制的图像处理若干问题研究
|
摘要
人类视觉系统具有非常优秀的图像处理能力。本文以目前广泛认可的人类视觉信息处理流向为主线，参照视网膜、外侧膝状体、初级视皮层、高级视皮层以及更为抽象的大脑皮质等关键视觉信息处理区域的神经机制，提出了基于上述神经机制的若干种图像处理方法，并在实际图像的处理中显示了较好的效果。主要内容包括如下方面：
1．针对图像处理领域的颜色恒常问题，本文提出了两种计算模型。一个模型是基于视网膜（包括外侧膝状体）神经机制的颜色恒常计算模型。该模型模拟具有抑制亚区的视网膜神经节细胞非经典感受野特性及其颜色单拮抗机制，实现了图像处理中对色偏图像的颜色恒常。第二个模型是基于初级视皮层神经机制的颜色恒常计算模型。该模型分别从图像导数与非负稀疏编码两个角度模拟初级视皮层神经元感受野，实现色偏图像颜色恒常。通过对多个国际通行颜色恒常算法评估库的测试，上述两个模型均取得了与目前最具优势的颜色恒常技术方法相比拟的结果。在图像处理领域，上述模型表现出了潜在的应用价值；在神经科学领域，上述模型对理解皮层下神经元以及初级视皮层神经元对颜色恒常的作用提供了计算理论上的依据。
2．人类视觉神经系统具有等级层次性和双向连接性，具有特征检测和学习能力等特性。在系统层次的视觉信息处理过程的启发下，本文提出一种小波域的多尺度马尔可夫随机场模型模拟视觉系统的上述特性。具体而言，该模型用小波变换实现视觉系统输入图像的稀疏表达，用多尺度马尔可夫随机场表征图像的全局拓扑特征；用金字塔结构所展示的多尺度信息处理能力模拟视觉系统的等级层次性；用自底向上和自顶向下两种信息流模拟视觉系统各层之间的双向连接性；用模型计算中的迭代过程模拟无监督学习机制；用不同的参数设置模拟不同的视觉任务，从而实现真实生物医学图像的区域分割和边缘检测功能。
3．针对图像增强问题，我们以模拟大脑节律现象的Wilson-Cowan双节点耦合振子模型为基础，选取使该模型产生极限环振荡条件的参数，采用连续灰度阶图像块作为输入，兴奋性亚群节点响应作为图像增强的输出，做出刺激响应曲线，发现该曲线与图像处理领域中用于图像增强的Gamma校正曲线相似，说明Wilson-Cowan双节点耦合振子模型可以作为一种新的图像增强方法。由于此前对图像增强的视觉机制解释，是以中心外周相互作用的感受野模型为基础的，本工作表明，图像增强还可以神经元群的振荡机制来解释，或者说，本工作为传统图像处理方法中的Gamma增强方法提供了一种神经机制上的解释。将新方法与基于感受野模型的Retinex算法对比，表现出了更好的图像增强性能。
Human visual system (HVS) possesses very excellent image processing abilities.Based on the extensive acceptant visual information processing flows, this papermimicks neural mechanisms of retina, lateral geniculate nucleus, visual cortex and moreabstract cerebral cortex，and propose some image processing methods equipped with theabove neural mechanisms to face some practical image processing problems. It mainlyinvolves:
1. We propose two models to solve the color constancy problems. One modelnamed “single-opponent cell with non-classical receptive field (nCRF)”(SONRF), it isproposed as a potential mechanism underlying image color constancy at the level ofretinal ganglion (RG) cells and lateral geniculate nucleus (LGN) neurons. This modelsimulates the properties of inhibitory interactions among the subunits of the nCRF (i.e.,disinhibitory effects) and the inhibitory modulation of the subunits to the center with thecolor opponent mechanism of red-green, green-red and blue-yellow. Another model, bymimicking receptive fields of the primary visual cortical neurons from the views ofimage derivative and non-negative sparse coding, is a color constancy model combiningwith the image derivative framework and non-negative sparse coding. We employcommonly used color image databases to quantitatively evaluate these two models,which gave the comparable results as the state-of-the-art non-biologically inspired colorconstancy algorithms. In the view of image processing, these results demonstrate theutility and potential applications of algorithms inspired by biological mechanisms incomputer vision and other realms of image processing. In the view of neuroscience,those models provide supports for the notion of subcortical neurons and primary visualcortex’s roles on the capacity of color constancy.
2. As HVS has the properties of feature detection abilities, hierarchy, bidirectionalconnection, and self-learning mechanisms, etc, we propose a multiscale Markov randomfield model in the wavelet domain by simulating some functions of HVS for imagesegmentation. Concretely, for an input scene, using wavelet transforms, our model provides its sparse representations to mimic feature detection abilities, and using thepyramid framework, our model mimics hierarchy. In the framework of our model, thereare two information flows imitating bidirectional connection. For example, a bottom-upprocedure is adopted to extract input features and a top-down procedure is used toprovide feedback controls. Moreover, iterations are the simulation of self-learningmechanisms. In addition, setted by different parameters, our model is able to excuatedifferent biomedical image segmentation tasks, such as edge detection and regionsegmentation with pixels classification.
3. A model mimicking cortex rhythms is adopted to achieve image enhancement.This model is based on the coupled Wilson-Cowan oscillators with double nodes. Theinputs are images to be enhanced and the outputs are node responses of the excitedsubpopulation. As image experiments show, the method is able to be used in imageenhancement. Meanwhile, we found that if image patches with continuous gray valuesare employed as stimulus, the response curves are similar with the classical Gammacorrection curves that are used in image enhancement. This fact on one side providesevidence of the image enhancement ability of the proposed method, on the other side, itprovides the neural mechanism, oscillation of the neural population, of the classicalGamma correction method. Numerically compared with the receptive field model basedclassical center-surround Retinex algorithm, the new method shows better results.
1．针对图像处理领域的颜色恒常问题，本文提出了两种计算模型。一个模型是基于视网膜（包括外侧膝状体）神经机制的颜色恒常计算模型。该模型模拟具有抑制亚区的视网膜神经节细胞非经典感受野特性及其颜色单拮抗机制，实现了图像处理中对色偏图像的颜色恒常。第二个模型是基于初级视皮层神经机制的颜色恒常计算模型。该模型分别从图像导数与非负稀疏编码两个角度模拟初级视皮层神经元感受野，实现色偏图像颜色恒常。通过对多个国际通行颜色恒常算法评估库的测试，上述两个模型均取得了与目前最具优势的颜色恒常技术方法相比拟的结果。在图像处理领域，上述模型表现出了潜在的应用价值；在神经科学领域，上述模型对理解皮层下神经元以及初级视皮层神经元对颜色恒常的作用提供了计算理论上的依据。
2．人类视觉神经系统具有等级层次性和双向连接性，具有特征检测和学习能力等特性。在系统层次的视觉信息处理过程的启发下，本文提出一种小波域的多尺度马尔可夫随机场模型模拟视觉系统的上述特性。具体而言，该模型用小波变换实现视觉系统输入图像的稀疏表达，用多尺度马尔可夫随机场表征图像的全局拓扑特征；用金字塔结构所展示的多尺度信息处理能力模拟视觉系统的等级层次性；用自底向上和自顶向下两种信息流模拟视觉系统各层之间的双向连接性；用模型计算中的迭代过程模拟无监督学习机制；用不同的参数设置模拟不同的视觉任务，从而实现真实生物医学图像的区域分割和边缘检测功能。
3．针对图像增强问题，我们以模拟大脑节律现象的Wilson-Cowan双节点耦合振子模型为基础，选取使该模型产生极限环振荡条件的参数，采用连续灰度阶图像块作为输入，兴奋性亚群节点响应作为图像增强的输出，做出刺激响应曲线，发现该曲线与图像处理领域中用于图像增强的Gamma校正曲线相似，说明Wilson-Cowan双节点耦合振子模型可以作为一种新的图像增强方法。由于此前对图像增强的视觉机制解释，是以中心外周相互作用的感受野模型为基础的，本工作表明，图像增强还可以神经元群的振荡机制来解释，或者说，本工作为传统图像处理方法中的Gamma增强方法提供了一种神经机制上的解释。将新方法与基于感受野模型的Retinex算法对比，表现出了更好的图像增强性能。
Human visual system (HVS) possesses very excellent image processing abilities.Based on the extensive acceptant visual information processing flows, this papermimicks neural mechanisms of retina, lateral geniculate nucleus, visual cortex and moreabstract cerebral cortex，and propose some image processing methods equipped with theabove neural mechanisms to face some practical image processing problems. It mainlyinvolves:
1. We propose two models to solve the color constancy problems. One modelnamed “single-opponent cell with non-classical receptive field (nCRF)”(SONRF), it isproposed as a potential mechanism underlying image color constancy at the level ofretinal ganglion (RG) cells and lateral geniculate nucleus (LGN) neurons. This modelsimulates the properties of inhibitory interactions among the subunits of the nCRF (i.e.,disinhibitory effects) and the inhibitory modulation of the subunits to the center with thecolor opponent mechanism of red-green, green-red and blue-yellow. Another model, bymimicking receptive fields of the primary visual cortical neurons from the views ofimage derivative and non-negative sparse coding, is a color constancy model combiningwith the image derivative framework and non-negative sparse coding. We employcommonly used color image databases to quantitatively evaluate these two models,which gave the comparable results as the state-of-the-art non-biologically inspired colorconstancy algorithms. In the view of image processing, these results demonstrate theutility and potential applications of algorithms inspired by biological mechanisms incomputer vision and other realms of image processing. In the view of neuroscience,those models provide supports for the notion of subcortical neurons and primary visualcortex’s roles on the capacity of color constancy.
2. As HVS has the properties of feature detection abilities, hierarchy, bidirectionalconnection, and self-learning mechanisms, etc, we propose a multiscale Markov randomfield model in the wavelet domain by simulating some functions of HVS for imagesegmentation. Concretely, for an input scene, using wavelet transforms, our model provides its sparse representations to mimic feature detection abilities, and using thepyramid framework, our model mimics hierarchy. In the framework of our model, thereare two information flows imitating bidirectional connection. For example, a bottom-upprocedure is adopted to extract input features and a top-down procedure is used toprovide feedback controls. Moreover, iterations are the simulation of self-learningmechanisms. In addition, setted by different parameters, our model is able to excuatedifferent biomedical image segmentation tasks, such as edge detection and regionsegmentation with pixels classification.
3. A model mimicking cortex rhythms is adopted to achieve image enhancement.This model is based on the coupled Wilson-Cowan oscillators with double nodes. Theinputs are images to be enhanced and the outputs are node responses of the excitedsubpopulation. As image experiments show, the method is able to be used in imageenhancement. Meanwhile, we found that if image patches with continuous gray valuesare employed as stimulus, the response curves are similar with the classical Gammacorrection curves that are used in image enhancement. This fact on one side providesevidence of the image enhancement ability of the proposed method, on the other side, itprovides the neural mechanism, oscillation of the neural population, of the classicalGamma correction method. Numerically compared with the receptive field model basedclassical center-surround Retinex algorithm, the new method shows better results.
引文
[1]徐科.神经生物学纲要.北京：科学出版社,2005,209
[2] R.W. Rodieck, J.J. Stone. Analysis of receptive fields of cat retina ganglion cells. J.Neurophysiol.,1965,28(9):833-849
[3] R.C. Gonzalez, R.E. Woods.数字图像处理(第二版).北京:电子工业出版社,2003,471-472
[4]马尔.视觉计算理论.北京:科学出版社,1988,60-62
[5] C. Li, X. Pei, Y. Zhow, et al. Role of the extensive area outside the x-cell receptive field inbrightness information transmission. Vision Res.,1991,31(9):1529-1540
[6] C. Li, Y. Zhow, X. Pei, et al. Extensive disinhibitory region beyond the classical receptivefield of cat retinal ganglion cells. Vision Res.,1992,32(2):219-228
[7]邱芳土,李朝义.同心圆感受野去抑制特性的数学模拟.生物物理学报,1995,11(2):214-220
[8]李朝义,邱芳土.视网膜神经节细胞空间传输特性的模拟.生物物理学报,1995,11(3):395-400
[9] A. Hyvarinen, J. Hurri, P. Hoyer. Natural image statistics. Belin: Springer,2009:16-18
[10]汪云九.神经信息学—神经系统的理论和模型.北京:高等教育出版社,2006,115
[11] C. Grigorescu, N. Petkov, M. A. Westenberg. Contour detection based on nonclassicalreceptive field inhibition. IEEE T Image Process.,2003,12(7):729-739
[12] J. Koenderink, A. van. Doorn. Representation of local geometry in the visual system. Biol.Cybern.,1987,55(6):367-375
[13] L. Gaudart, J. Crebassa, J. Petrakian. Wavelet transform in human visual channels. Appl.Opt.,1993,32(23):4119-4127
[14] B. A. Olshausen, D. J. Field. Emergence of simple-cell receptive field properties by learninga sparse code for natural images. Nature,1996,381(6):607-609
[15] A. J. Bell, T. J. Sejnowski. The ‘independent components’ of natural scenes are edge filters.Vision Res.,1997,37(23):3327-3338
[16] D. D. Lee, H. S. Seung. Learning the parts of objects by non-negative matrix factorization.Nature,1999,401(6755):788–791
[17] P.O. Hoyer. Modeling receptive fields with non-negative sparse coding. Neurocomputing,2003,52-54,547-552
[18] P. O. Hoyer. Non-negative matrix factorization with sparseness constraints. J. Mac. Learn.Res.,2004,5,1457-1469
[19] T.S. Lee, D. Mumford. Hierarchical bayesian inference in the visual cortex. J. Opt. Soc. Am.,2003,20(7):1434-1448
[20] T. Dean. A computational model of the cerebral cortex. Proceedings of Twentieth NationalConference on Artificial Intelligence (AAAI’05). Menlo Park: AAAI Press,2005,938–943
[21] D. George, J. Hawkins. A hierarchical Bayesian model of invariant pattern recognition in thevisual cortex.2005IEEE International Joint Conference on Neural Networks (IJCNN’05).Piscataway: IEEE Press,2005,1812-1817
[22] T. Serre, L. Wolf. Robust object recognition with cortex-like mechanisms. IEEE Trans.Pattern. Anal. Mach. Intell.,2007,29(3):411-426
[23] Y. Ichisugi. A Cerebral Cortex Model that Self-Organizes Conditional Probability Tables andExecutes Belief Propagation.2007International Joint Conference on Neural Networks(IJCNN2007), Vol.1:178-183
[24] D. George, J. Hawkins. Towards a mathematical theory of cortical micro-circuits. PLoSComput. Biol.,2009,5(10):1-26
[25] D. Heckerman, D. Geiger, D. Chickering. Learning Bayesian networks: The combination ofknowledge and statistical data. Mach. Learn.,1995,20(3):197-243
[26] S. Mallat, S. Zhong. Characterization of signals from multiscale edges. IEEE T. Pattern Anal.Mach. Intell.,1992,14(7):710-732
[27] W. Freeman. Spatial properties of an EEG event in the olfactory bulb and cortex.Electroenceph. Clin. Neurophysiol.,1978,44(5):586-605
[28] R. Eckhorn, R. Bauer, W. Jordan, et al. Coherent oscillations: A mechanism of featurelinking in the visual cortex? Biol. Cybern.,1988,60(2):265-280
[29] C. Von der Malsburg, W. Schneider. A neural cocktail-party processor. Biol. Cybern.,1986,54(1):29-40
[30] H. Wilson, J. Cowan. Excitatory and inhibitory interactions in localized populations ofmodel neurons. J. Biophys.,1972,12(1):1-24
[31] H. Wilson, J. Cowan. A mathematical theory of the functional dynamics of nervous tissue.Bio. Cybern.,1973,13(2):55-80
[32] A. Destexhe, T. Sejnowski. The Wilson-Cowan model,36years later. Bio. Cybern.,2009,101(1-2):1-2
[33]汪云九.神经信息学—神经系统的理论和模型.北京:高等教育出版社,2006,295
[34] J.M. Mendel, R.W. McLaren. Reinforcement-learning control and pattern recognitionsystems. Adaptive, Learning, and Pattern Recognition Systems: Theory and Applications.1970,66(1):287-318
[35] S. Haykin.神经网络原理.北京:机械工业出版社,2004,33-41
[36] Z. Kalal, J. Matas, K. Mikolajczyk. P-N Learning: Bootstrapping Binary Classifiers byStructural Constraints.2010International Conference on Computer Vision and PatternRecognition (CVPR2010),2010,49-56
[37] S.D. Hordley. Scene illuminant estimation: Past, present, and future. Color Res. Appl.,2006,31(4):303-314
[38] D.H. Brainard, W.T. Freeman. Bayesian color constancy. J. Opt. Soc. Am. A.,1997,14(7):1393-1411
[39] D.H. Brainard, P. Longere, P.B. Delahunt, et al. Bayesian model of human color constancy. J.Vision,2006,6:1267-1281
[40] G. Finlayson, S. Hordley, P. Hubel. Color by Correlation: A Simple, Unifying Framework forColor Constancy. IEEE T. Pattern Anal. Mach. Intell.,2001,23(11):1209-1221
[41] C. Rosenberg, T. Minka, A. Ladsariya. Bayesian color constancy with non-Gaussian models.In Advances in Neural Information Processing Systems, Cambridge, MA, MIT prss2003,23-28
[42] P. Gehler, C. Rother, A. Blake, et al. Bayesian Color Constancy Revisited. In Proceedings ofthe IEEE conference on computer vision and pattern recognition (CVPR2008),2008,1-8
[43] A. Chakrabarti, K. Hirakawa, T. Zickler. Color Constancy with Spatio-Spectral Statistical.IEEE Trans. Pattern Anal. Mach. Intell.,(to be published)
[44] D. Forsyth. A novel algorithm for color constancy. Int. J. Comput. Vision,1990,5(1):5-36
[45] G. Finlayson, S. Hordley. Improving gamut mapping color constancy. IEEE T. ImageProcess.,2000,9(10):1774-1783
[46] G. Finlayson, S. Hordley, I. Tastl. Gamut constrained illuminant estimation. Int, J. Comput.,Vision,2006,67(1):93–109
[47] A. Gijsenij, T. Gevers, J. van de Weijer. Generalized Gamut Mapping using ImageDerivative Structures for Color Constancy. Int. J. Comput. Vision,2010,86(2-3):127-139
[48] G. Buchsbaum. A spatial processor model for object color perception. J. Franklin I.,1980,310:1-26
[49] E. Land, J. McCann. Lightness and Retinex Theory. J. Opt. Soc. Am.,1971,61(1):1-11
[50] G. Finlayson, E. Trezzi. Shades of gray and colour constancy. Proc. IS&T/SID12th ColorImaging Conf.,2004:37–41
[51] J. van de Weijer，T. Gevers, A. Gijsenij. Edge-based Color Constancy. IEEE T. ImageProcess.,2007,16(9):2207-2214
[52] A. Gijsenij, T. Gevers. Color Constancy using Natural Image Statistics and Scene Semantics.IEEE T. Pattern Anal. Mach. Intell.,2011,33(4):687-698
[53] A. Gijsenij, T. Gevers. Color Constancy using Natural Image Statistics. Proc. Int. Conf.Computer Vision and Pattern Recognition (CVPR2007),2007,1-8
[54] S. Bianco, G. Ciocca, C. Cusano, et al. Automatic color constancy algorithm selection andcombination. Pattern Recogn.,2010,43(3):695-705
[55] S. Bianco, G. Ciocca, C. Cusano, et al. Improving Color Constancy Using Indoor–OutdoorImage Classification. IEEE T. Image Process.,2008,17(12):2381-2392
[56] M. Wu, J. Sun. Color constancy based on texture pyramid matching and regularized localregression. J. Opt. Soc. Am. A,2010,27(10):2097-2105
[57] V. Cardei, B. Funt, K. Barnard. Estimating the scene illumination chromaticity by using aneural network. J. Opt. Soc. Am. A.,2002,19(12):2374-2386
[58] J. Toro, B. Funt. A Multilinear Constraint on Dichromatic Planes for Illumination Estimation.IEEE T. Image Process.,2007,16(1):92-97
[59] E. Land. An alternative technique for the computation of the designator in the retinex theoryof color vision. P. Natl. Acad. Sci. USA.,1986,38(10):3078-3080
[60] E. Provenzi, C. Gatta, M. Fierro, et al. A Spatially Variant White Patch and Gray WorldMethod for Color Image Enhancement Driven by Local Contrast. IEEE T. Pattern Anal.Mach. Intell.,2008,30(10):1757-1770
[61] C. Huang, C. Lin. Bio-inspired computer fovea model based on hexagonal-type cellularneural networks. IEEE T. Circuits I.,2007,54(1):35-47
[62] H. Spitzer, S. Semo. Color constancy: A biological model and its application for still andvideo images. Pattern Recogn.,2002,35(8):1645-1659
[63] E. Land. Recent advances in retinex theory. Vision Res.,1990,26(1):7-21
[64] D. Brainard, B. Wandell. Analysis of the retinex theory of color vision. J. Opt. Soc. Am. A,1986,3(10):1651-1661
[65] E. Land. Recent advances in retinex theory and some implications for cortical computations:color vision and the natural image. Proc. Natl. Acad. Sci. USA,1983,80:5163-5169
[66] B.R. Conway. Color vision, cones, and color-coding in the cortex. Neuroscientist,2009,15(3):274-290
[67] R. Shapley, M. Hawken. Neural mechanisms for color perception in the primary visualcortex. Curr. Opin. Neurobiol.,2002,12:426-432
[68] C. Li, Y. Zhou, X. Pei, et al. Extensive disinhibitory region beyond the classical receptivefield of cat retinal ganglion cells. Vision Res.,1992,32(2):219-228
[69] O. Creutzfeldt, J. Crook, S. Kastner, et al. The neurophysiological correlates of colour andbrightness contrast in lateral geniculate neurons I. Exp. Brain Res.1991,87(1):3-21
[70] O. Creutzfeldt, S. Kastner, X. Pei, et al. The neurophysiological correlates of colour andbrightness contrast in lateral geniculate neurons II. Exp. Brain Res.1991,87(1):22-45
[71] M. Ebner. Color Constancy. Chichester: John Wiley&Sons Ltd,2007,39-63
[72] M. Lecca, S. Messelodi. Linking the von Kries model to Wien’s law for the estimation of anilluminant invariant image. Pattern Recogn. Lett.,2011,32(15):2086-2096
[73] J. Kraft, D. Brainard. Mechanisms of color constancy under nearly natural viewing. Proc.Natl. Acad. Sci. USA,1999,96(1):307-312
[74] R. Shapley. The importance of contrast for the activity of single neurons, the VEP andperception. Vision Res.,1986,26(1):45-62
[75] A. Valberg, B. Lange-Malecki.“Colour constancy” in Mondrian patterns: A partialcancellation of physical chromaticity shifts by simultaneous contrast. Vision Res.,1990,30(3):371-380
[76] J. McCann, S. McKee, T. Taylor. Quantitative studies in retinex theory a comparisonbetween theoretical predictions and observer responses to the “color mondrian” experiment.1976,16(5):445-458
[77] J. Cataliotti, A. Gilchrist. Local and global processes in surface lightness perception. Percept.Psychophys.,1995,57(2):125-135
[78] M. Kass, A. Witkin. Analyzing oriented patterns. Comput. Vis. Image Und.,1987,37(3):362–385
[79] K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descriptors. IEEE T.Pattern Anal. Mach. Intell.,2005,27(10):1615-1630
[80] L. Meylan, S. Susstrunk. High dynamic range image rendering with a retinex-based adaptivefilter. IEEE T. Image Process.,2006,15(9):2820-2830
[81] G. Buchsbaum, A. Gottschalk. Trichromacy opponent colours coding and optimum colourinformation transmission in the retina. Roy. Soc. Lond. B Biol. Sci.,1983,220:89-113
[82] C. Zeng, Y. Li, C. Li. Center–surround interaction with adaptive inhibition: A computationalmodel for contour detection. NeuroImage,2011,55(1):49-66
[83] F. Ciurea, B. Funt. A large image database for color constancy research. Proc. IS&T/SID’sColor Imaging Conference, The SunBurst Resort, Scottsdale, Arizona,2004,160-164
[84] W. Xiong, B. Funt. Stereo retinex. Image Vision Comput.,2009,27(1-2):178-188
[85] K. Barnard, B. Funt, V. Cardei. A Comparison of Computational Color ConstancyAlgorithms, Part One; Theory and Experiments with Synthetic Data. IEEE T. Image Process.,2002,11(9):972-984
[86] S.D. Hordley, G.D. Finlayson. Reevaluation of color constancy algorithm performance. J.Opt. Soc. Am. A USA,2006,23(5):1008-1020
[87] A Gijsenij, T Gevers, M. Lucassen. Perceptual analysis of distance measures for colorconstancy algorithms. J. Opt. Soc. Am. A. USA,2009,26(10):2243-2256
[88] D. Brainard. Hyperspectral Image Data. http://color.psych.ucsb.edu//hyperspectral/
[89] K. Barnard, L. Martin, A. Coath, B. Funt. A comparison of computational color constancyalgorithms---Part Two: Experiments with image data. IEEE T. Image Process.,2002,11(9):985-996
[90] K. Barnard, L. Martin, B. Funt, et al. A data set for colour research. Color Res. Appl.,2002,27(3):147-151
[91] L. Shi, B. Funt. Re-processed Version of the Gehler Color Constancy Dataset of568Images.accessed from http://www.cs.sfu.ca/~colour/data/
[92] B. Conway, D. Tsaob. Color-tuned neurons are spatially clustered according to colorpreference within alert macaque posterior inferior temporal cortex. P. Natl. Acad. Sci. USA.,2009,106(42):18034-18039
[93] M.T. Vanleeuwen, C. Joselevitch, I. Fahrenfort, et al. The contribution of the outer retina tocolor constancy: a general model for color constancy synthesized from primate and fish data.Visual Neurosci.,2007,24:277-290
[94] A. Choudhury, G. Medioni. Color constancy using denoising methods and cepstral analysis.ICIP'09Proceedings of the16th IEEE international conference on Image processing, Aalen,2009,1637-1640
[95] S. Solomon, P Lennie. The machinery of colour vision. Nat. Rev. Neurosci.,2007,8(4):276-286
[96] A. Rizzi, C. Gatta. A new algorithm for unsupervised global and local color correction.Pattern Recogn. Lett.,2003,24(11):1663-1677
[97] S. Lee. An Efficient Content-Based Image Enhancement in the Compressed Domain UsingRetinex Theory. IEEE T. Circ. Syst. Vid.,2007,17(2):199-213
[98] C. Zeng, Y. Li, C. Li. Center–surround interaction with adaptive inhibition: A computationalmodel for contour detection. NeuroImage,2011,55(1):49-66
[99]王守觉，丁兴号，廖英豪，等.一种新的仿生彩色图像增强方法.电子学报,2008,36(10):1970-1973
[100] A. Gijsenij, T. Gevers, J. van de Weijer. Computational Color Constancy: Survey andExperiments. IEEE T. Image Process.,2011,20(9):2475-2489
[101] L. Shi, B. Funt. Illumination Estimation via Non-Negative Matrix Factorization. Proc. AIC2007Color for Science and Industry, Midterm Meeting of the International ColorAssociation, Hangzhou,2007,1-5
[102] D. Field. Relations between the statistics of natural images and the response properties ofcortical cells. J. Opt. Soc.,1987,4(12):2379-2394
[103] L.D. Selemon，P.S. Goldman-Rakic. Longitudinal topography and interdigitation ofcorticostriatal projections in the rhesus monkey. J Neurosci.,1985,5(3):776
[104] W. Kropatsch, Y. Haxhimusa, Z. Pizlo, et al. Vision Pyramids that do not Grow too High.Pattern Recogn. Lett.,2005,26(3):319–337
[105] G. Lupyan, S. Thompson-Schill, D. Swingley. Conceptual Penetration of Visual Processing.Psychol. Sci.,2010,21(5):682-691
[106] M. Carrasco, B. McElree. Covert attention accelerates the rate of visual informationprocessing. P. Natl. Acad. Sci. USA,2001,98(9):5363-5367
[107] Q. Tang, N. Sang, T. Zhang. Extraction of salient contours from cluttered scenes. PatternRecogn.,2007,40(11):3100-3109
[108] T. Zanto, M. Rubens, A. Thangavel, A. Gazzaley. Causal role of the prefrontal cortex intop-down modulation of visual processing and working memory. Nat. Neurosci.,2011,14,(5):656–661
[109]汪云九.神经信息学－神经系统的理论和模型.北京:高等教育出版社,2006,103-105
[110]罗四维.视觉感知系统信息处理理论.北京:电子工业出版社,2006,7-9
[111] L. Shapiro, G. Stockman.计算机视觉.北京：机械工业出版社.2005,115
[112] K. Ghosh, S. Sarkar, K. Bhaumik. Understanding image structure from a new multi-scalerepresentation of higher order derivative filters. Image Vision Comput.,2007,25(8):1228-1238
[113] C. Kayser, W. Einhauser, P. Kongig. Processing of complex stimuli and nature scenes in thevisual cortex. Current Opinion in Neurobiol.,2004,14(4):468-473
[114] C. Kayser, W. Einhauser, P. Kongig. Responses to Natural Secenes in Cat V1. JNeurophysiol.,2003,90(3):1910-1920
[115] S. Munder, D. Gavrila. An Experimental Study on Pedestrian Classification. IEEE T.Pattern Anal. Mach. Intell.,2006,28(11):1863-1868
[116] C. Wohler, J. Anlauf. An adaptable Time-Delay Neural-Network Algorithm for ImageSequence Analysis. IEEE T. Neural Networ.,1999,10(6):1531-1536
[117] C. Perez, C. Salinas. Genetic Design of Biologically Inspired Receptive Fields for NeuralPattern Recognition. IEEE. T. Syst. Man Cy. B,2003,33(2):258-270
[118]朱舜山,齐翔林,汪云九.基于视觉编码的图像处理研究.生物物理学报,1996,12(2):297-309
[119] M. Perus, B. Horst, C. Loo. Bio-computation model of object recognition: Quantumhebbian processing with neurally-shaped gabor wavelets. BioSystems,2005,82(2):116-126
[120] U. Nuding, C. Zetzsche. Learning the selectivity of V2and V4neurons using non-linearmulti-layer wavelet networks. Biosystems,2007,89(1-3):273-279
[121]陈刚.应用数学和信号处理相遇.高校应用数学学报,1999,14(3):350-366
[122]陈武凡.小波分析及其在图像处理中的应用.北京：科学出版社.2003,152
[123] S. Geman, D. Geman. Stochastic relaxation, Gibbs distributions and the Bayesianrestoration of images. IEEE T. Patten. Anal. Mach. Intell.,1984,6(6):721-741
[124] W. Freeman, E. Pasztor, O. Carmichael. Learning low-level vision. Int. J. Comput. Vision,2000,40(1):24-47
[125] A. Fitzgiboon, Y. Wexler, A. Zisserman. Image-based rendering using image-based priors.Int. J. Comput. Vision,2005,63(2):24-47
[126] S. Zhu, Y. Wu. From local features to global perception---A perspective of Gestaltpsychology from Markov random field theory. Neurocomputing,1999,26-27(6):939-945
[127] S. Roth, M. Black. Fields of Experts: A framework for learning image priors. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2005),2005,860-867
[128] U. Koster, J. Lindgren, A. Hyvarinen. Estimating Markov Random Field Potentials forNatural Images. Lecture Notes in Computer Science (LNCS2009),2009,5441:515-522
[129] H. Noda, M. Shirazi, E. Kawaguchi. MRF-based texture segmentation using waveletdecomposed images. Pattern Recogn.,2002,35(4):771-782
[130]刘国英,茅力非,王雷光,等.基于小波域分层Markov模型的纹理分割.武汉大学学报(信息科学版),2009,34(5):531-534
[131]李旭超,朱善安,朱胜利.基于小波域层次Markov模型的图像分割.中国图象图形学报,2007,12(2):308-314
[132]杜馨瑜.基于Markov随机场的图像分割:[硕士学位论文].成都:电子科技大学,2007,31-36
[133]章毓晋.图像处理.北京：清华大学出版社.2006,365
[134] S. Li. Markov random field modeling in image analysis. Berlin: Springer-Verlag,2009,1-20
[135] C. Bouman, M. Shapiro. A Multiscale Random Field Model for Bayesian ImageSegmentation. IEEE T. Image Process.,1994,3(2):162-177
[136]刘国英,罗伦才,梅天灿,等.基于MRMRF的多光谱纹理影像分割方法.武汉大学学报(信息科学版),2008,33(9):963-966
[137]尼克尔斯.神经生物学—从神经元到脑(第4版).北京:科学出版社,2009,499-519
[138] R. Duda, P. Hart, D. Stock.模式分类（第2版）.北京:机械工业出版,2003,102-105
[139] A. Bronstein, M. Bronstein. Sparse ICA for blind separation of transmitted and reflectedimages. Int. J. Imag. Syst. Tech.,2005,15(1):84-91
[140] B. Olshausen, D. Field. Sparse coding of sensory input. Curr. Opin. Neurobiol.,2004,14(4):481-487
[141]F. Attneave. Some informational aspects of visual perception. Psychol. Revnt.,1954,61:183-193
[142]H. Barlow. Single units and sensation: a neuron doctrine for perceptual psychology?Perception,1972,1(4):371-394
[143] J. Daugman. Complete discrete2-D Gabor transform by neural networks for image analysisand compression. IEEE T. Acoust, Speech, Signal Process.,1988,36(7):1169-1179
[144] S. Grossberg, E. Mingolla. Neural dynamics of form perception: boundary completion,illusory figures, and neon color spreading. Psychol. Rev.,1990,92(2):173-211
[145] L. Glass, M. Mackey. From Clocks to Chaos: The Rhythms of Life. New York: PrincetonUniversity Press,1990,2-11
[146] E. Niedermeyer, F. da Silva. Electroencephalography: Basic Principles, ClinicalApplications and Related Fields. Baltimore: Williams and Wilkins Press,1998,135-140
[147] D. Wang. The time dimension for scene analysis. IEEE T. Neural Network,2005,16(6):1401-1426
[148] P. Strumi o, T. Durrani. Spiral waves in a2-Dmodel of fibrillating heart and a new way tobreak them. Med Science Mon,1996,2(4):495–504
[149] A. Destexhe, T. Sejnowski. The Wilson-Cowan model,36years later. Bio Cybern,2009,101(1-2):1-2
[150] P. Strumillo, M. Strzelecki. Application of Coupled Neural Oscillators for Image TextureSegmentation and Modeling of Biological Rhythms. Int J Appl Math Comput Sci,2006,16(4):513-523
[151] M. Bertalmío, J. Cowan. Implementing the Retinex algorithm with Wilson–Cowanequations. J. Physiol.,2009,103(1-2):69-72
[152] K. Panetta, E. Wharton, S. Agaian. Human Visual System-Based Image Enhancement andLogarithmic Contrast Measure. IEEE T. Syst. Man. Cy. B,2008,38(1):174-188
[153]冈萨雷斯.数字图像处理.北京:电子工业出版社,2003,63-66.
[154] S. Morfu, J. Comte. A Nonlinear Oscillators Network Devoted to Image Processing. Int. J.Bifurcat. Chaos,2004,14(4):1385-1394
[155] D. Jobson, Z. Rahman, G. Woodwell. Properties and performance of center/surroundretinex. IEEE T. Image Process.,1997,6(3):451-462
[156] V. Glezer, T. Tsherbach, V. Gauselman, et al. Linear and Non-Linear Properties of Simpleand Complex Receptive Fields in Area17of the Cat Visual Cortex. BioL. Cybernetics.,1980,37(4):195-208
[157] K. Purpura, E. Kaplan, R. Shapley. Background light and the contrast gain of primate P andM retinal ganglion cells. Proc. Natl. Acad. Sci. USA,1988,85(6):4534-4537
[158] J. von Hateren, A. van der Schaaf. Independent component filters of natural imagescompared with simple cells in primary visual cortex. Proc. R. Soc. Lond B,1998,265(10):359-366
[159] M. Latif, J. Chedjou, K. Kyamakya. The paradigm of Non-linear oscillators in imageprocessing. International Symposium on Theoretical Engineering (ISTET), Germany,2009,205-209
[160] K. Kyamakya, J. Chedjou, M. Latif, et al. A novel image processing approach combining a'coupled nonlinear oscillators'-based paradigm with cellular neural networks for dynamicrobust contrast enhancement. The12th International Workshop on Cellular NanoscaleNetworks and Their Applications (CNNA), Berkeley,2010,1-7
[161] Xinyu Du, Yongjie Li, Cheng Luo, et al. Elitist Restruction Genetic Algorithm Based onMarkov Random Field for Magnetic Resonance Image Segmentation. J. Electron. Sci.&Technol. Journal of Electronic Science and Technology,2012,10(1):83-87
[162] Xinyu Du, Yongjie Li, Dezhong Yao. A Support Vector Machine Based Algorithm forMagnetic Resonance Image Segmentation.2008Fourth International Conference on NaturalComputation (ICNC’08), Jinan,2008,3:49-53
[2] R.W. Rodieck, J.J. Stone. Analysis of receptive fields of cat retina ganglion cells. J.Neurophysiol.,1965,28(9):833-849
[3] R.C. Gonzalez, R.E. Woods.数字图像处理(第二版).北京:电子工业出版社,2003,471-472
[4]马尔.视觉计算理论.北京:科学出版社,1988,60-62
[5] C. Li, X. Pei, Y. Zhow, et al. Role of the extensive area outside the x-cell receptive field inbrightness information transmission. Vision Res.,1991,31(9):1529-1540
[6] C. Li, Y. Zhow, X. Pei, et al. Extensive disinhibitory region beyond the classical receptivefield of cat retinal ganglion cells. Vision Res.,1992,32(2):219-228
[7]邱芳土,李朝义.同心圆感受野去抑制特性的数学模拟.生物物理学报,1995,11(2):214-220
[8]李朝义,邱芳土.视网膜神经节细胞空间传输特性的模拟.生物物理学报,1995,11(3):395-400
[9] A. Hyvarinen, J. Hurri, P. Hoyer. Natural image statistics. Belin: Springer,2009:16-18
[10]汪云九.神经信息学—神经系统的理论和模型.北京:高等教育出版社,2006,115
[11] C. Grigorescu, N. Petkov, M. A. Westenberg. Contour detection based on nonclassicalreceptive field inhibition. IEEE T Image Process.,2003,12(7):729-739
[12] J. Koenderink, A. van. Doorn. Representation of local geometry in the visual system. Biol.Cybern.,1987,55(6):367-375
[13] L. Gaudart, J. Crebassa, J. Petrakian. Wavelet transform in human visual channels. Appl.Opt.,1993,32(23):4119-4127
[14] B. A. Olshausen, D. J. Field. Emergence of simple-cell receptive field properties by learninga sparse code for natural images. Nature,1996,381(6):607-609
[15] A. J. Bell, T. J. Sejnowski. The ‘independent components’ of natural scenes are edge filters.Vision Res.,1997,37(23):3327-3338
[16] D. D. Lee, H. S. Seung. Learning the parts of objects by non-negative matrix factorization.Nature,1999,401(6755):788–791
[17] P.O. Hoyer. Modeling receptive fields with non-negative sparse coding. Neurocomputing,2003,52-54,547-552
[18] P. O. Hoyer. Non-negative matrix factorization with sparseness constraints. J. Mac. Learn.Res.,2004,5,1457-1469
[19] T.S. Lee, D. Mumford. Hierarchical bayesian inference in the visual cortex. J. Opt. Soc. Am.,2003,20(7):1434-1448
[20] T. Dean. A computational model of the cerebral cortex. Proceedings of Twentieth NationalConference on Artificial Intelligence (AAAI’05). Menlo Park: AAAI Press,2005,938–943
[21] D. George, J. Hawkins. A hierarchical Bayesian model of invariant pattern recognition in thevisual cortex.2005IEEE International Joint Conference on Neural Networks (IJCNN’05).Piscataway: IEEE Press,2005,1812-1817
[22] T. Serre, L. Wolf. Robust object recognition with cortex-like mechanisms. IEEE Trans.Pattern. Anal. Mach. Intell.,2007,29(3):411-426
[23] Y. Ichisugi. A Cerebral Cortex Model that Self-Organizes Conditional Probability Tables andExecutes Belief Propagation.2007International Joint Conference on Neural Networks(IJCNN2007), Vol.1:178-183
[24] D. George, J. Hawkins. Towards a mathematical theory of cortical micro-circuits. PLoSComput. Biol.,2009,5(10):1-26
[25] D. Heckerman, D. Geiger, D. Chickering. Learning Bayesian networks: The combination ofknowledge and statistical data. Mach. Learn.,1995,20(3):197-243
[26] S. Mallat, S. Zhong. Characterization of signals from multiscale edges. IEEE T. Pattern Anal.Mach. Intell.,1992,14(7):710-732
[27] W. Freeman. Spatial properties of an EEG event in the olfactory bulb and cortex.Electroenceph. Clin. Neurophysiol.,1978,44(5):586-605
[28] R. Eckhorn, R. Bauer, W. Jordan, et al. Coherent oscillations: A mechanism of featurelinking in the visual cortex? Biol. Cybern.,1988,60(2):265-280
[29] C. Von der Malsburg, W. Schneider. A neural cocktail-party processor. Biol. Cybern.,1986,54(1):29-40
[30] H. Wilson, J. Cowan. Excitatory and inhibitory interactions in localized populations ofmodel neurons. J. Biophys.,1972,12(1):1-24
[31] H. Wilson, J. Cowan. A mathematical theory of the functional dynamics of nervous tissue.Bio. Cybern.,1973,13(2):55-80
[32] A. Destexhe, T. Sejnowski. The Wilson-Cowan model,36years later. Bio. Cybern.,2009,101(1-2):1-2
[33]汪云九.神经信息学—神经系统的理论和模型.北京:高等教育出版社,2006,295
[34] J.M. Mendel, R.W. McLaren. Reinforcement-learning control and pattern recognitionsystems. Adaptive, Learning, and Pattern Recognition Systems: Theory and Applications.1970,66(1):287-318
[35] S. Haykin.神经网络原理.北京:机械工业出版社,2004,33-41
[36] Z. Kalal, J. Matas, K. Mikolajczyk. P-N Learning: Bootstrapping Binary Classifiers byStructural Constraints.2010International Conference on Computer Vision and PatternRecognition (CVPR2010),2010,49-56
[37] S.D. Hordley. Scene illuminant estimation: Past, present, and future. Color Res. Appl.,2006,31(4):303-314
[38] D.H. Brainard, W.T. Freeman. Bayesian color constancy. J. Opt. Soc. Am. A.,1997,14(7):1393-1411
[39] D.H. Brainard, P. Longere, P.B. Delahunt, et al. Bayesian model of human color constancy. J.Vision,2006,6:1267-1281
[40] G. Finlayson, S. Hordley, P. Hubel. Color by Correlation: A Simple, Unifying Framework forColor Constancy. IEEE T. Pattern Anal. Mach. Intell.,2001,23(11):1209-1221
[41] C. Rosenberg, T. Minka, A. Ladsariya. Bayesian color constancy with non-Gaussian models.In Advances in Neural Information Processing Systems, Cambridge, MA, MIT prss2003,23-28
[42] P. Gehler, C. Rother, A. Blake, et al. Bayesian Color Constancy Revisited. In Proceedings ofthe IEEE conference on computer vision and pattern recognition (CVPR2008),2008,1-8
[43] A. Chakrabarti, K. Hirakawa, T. Zickler. Color Constancy with Spatio-Spectral Statistical.IEEE Trans. Pattern Anal. Mach. Intell.,(to be published)
[44] D. Forsyth. A novel algorithm for color constancy. Int. J. Comput. Vision,1990,5(1):5-36
[45] G. Finlayson, S. Hordley. Improving gamut mapping color constancy. IEEE T. ImageProcess.,2000,9(10):1774-1783
[46] G. Finlayson, S. Hordley, I. Tastl. Gamut constrained illuminant estimation. Int, J. Comput.,Vision,2006,67(1):93–109
[47] A. Gijsenij, T. Gevers, J. van de Weijer. Generalized Gamut Mapping using ImageDerivative Structures for Color Constancy. Int. J. Comput. Vision,2010,86(2-3):127-139
[48] G. Buchsbaum. A spatial processor model for object color perception. J. Franklin I.,1980,310:1-26
[49] E. Land, J. McCann. Lightness and Retinex Theory. J. Opt. Soc. Am.,1971,61(1):1-11
[50] G. Finlayson, E. Trezzi. Shades of gray and colour constancy. Proc. IS&T/SID12th ColorImaging Conf.,2004:37–41
[51] J. van de Weijer，T. Gevers, A. Gijsenij. Edge-based Color Constancy. IEEE T. ImageProcess.,2007,16(9):2207-2214
[52] A. Gijsenij, T. Gevers. Color Constancy using Natural Image Statistics and Scene Semantics.IEEE T. Pattern Anal. Mach. Intell.,2011,33(4):687-698
[53] A. Gijsenij, T. Gevers. Color Constancy using Natural Image Statistics. Proc. Int. Conf.Computer Vision and Pattern Recognition (CVPR2007),2007,1-8
[54] S. Bianco, G. Ciocca, C. Cusano, et al. Automatic color constancy algorithm selection andcombination. Pattern Recogn.,2010,43(3):695-705
[55] S. Bianco, G. Ciocca, C. Cusano, et al. Improving Color Constancy Using Indoor–OutdoorImage Classification. IEEE T. Image Process.,2008,17(12):2381-2392
[56] M. Wu, J. Sun. Color constancy based on texture pyramid matching and regularized localregression. J. Opt. Soc. Am. A,2010,27(10):2097-2105
[57] V. Cardei, B. Funt, K. Barnard. Estimating the scene illumination chromaticity by using aneural network. J. Opt. Soc. Am. A.,2002,19(12):2374-2386
[58] J. Toro, B. Funt. A Multilinear Constraint on Dichromatic Planes for Illumination Estimation.IEEE T. Image Process.,2007,16(1):92-97
[59] E. Land. An alternative technique for the computation of the designator in the retinex theoryof color vision. P. Natl. Acad. Sci. USA.,1986,38(10):3078-3080
[60] E. Provenzi, C. Gatta, M. Fierro, et al. A Spatially Variant White Patch and Gray WorldMethod for Color Image Enhancement Driven by Local Contrast. IEEE T. Pattern Anal.Mach. Intell.,2008,30(10):1757-1770
[61] C. Huang, C. Lin. Bio-inspired computer fovea model based on hexagonal-type cellularneural networks. IEEE T. Circuits I.,2007,54(1):35-47
[62] H. Spitzer, S. Semo. Color constancy: A biological model and its application for still andvideo images. Pattern Recogn.,2002,35(8):1645-1659
[63] E. Land. Recent advances in retinex theory. Vision Res.,1990,26(1):7-21
[64] D. Brainard, B. Wandell. Analysis of the retinex theory of color vision. J. Opt. Soc. Am. A,1986,3(10):1651-1661
[65] E. Land. Recent advances in retinex theory and some implications for cortical computations:color vision and the natural image. Proc. Natl. Acad. Sci. USA,1983,80:5163-5169
[66] B.R. Conway. Color vision, cones, and color-coding in the cortex. Neuroscientist,2009,15(3):274-290
[67] R. Shapley, M. Hawken. Neural mechanisms for color perception in the primary visualcortex. Curr. Opin. Neurobiol.,2002,12:426-432
[68] C. Li, Y. Zhou, X. Pei, et al. Extensive disinhibitory region beyond the classical receptivefield of cat retinal ganglion cells. Vision Res.,1992,32(2):219-228
[69] O. Creutzfeldt, J. Crook, S. Kastner, et al. The neurophysiological correlates of colour andbrightness contrast in lateral geniculate neurons I. Exp. Brain Res.1991,87(1):3-21
[70] O. Creutzfeldt, S. Kastner, X. Pei, et al. The neurophysiological correlates of colour andbrightness contrast in lateral geniculate neurons II. Exp. Brain Res.1991,87(1):22-45
[71] M. Ebner. Color Constancy. Chichester: John Wiley&Sons Ltd,2007,39-63
[72] M. Lecca, S. Messelodi. Linking the von Kries model to Wien’s law for the estimation of anilluminant invariant image. Pattern Recogn. Lett.,2011,32(15):2086-2096
[73] J. Kraft, D. Brainard. Mechanisms of color constancy under nearly natural viewing. Proc.Natl. Acad. Sci. USA,1999,96(1):307-312
[74] R. Shapley. The importance of contrast for the activity of single neurons, the VEP andperception. Vision Res.,1986,26(1):45-62
[75] A. Valberg, B. Lange-Malecki.“Colour constancy” in Mondrian patterns: A partialcancellation of physical chromaticity shifts by simultaneous contrast. Vision Res.,1990,30(3):371-380
[76] J. McCann, S. McKee, T. Taylor. Quantitative studies in retinex theory a comparisonbetween theoretical predictions and observer responses to the “color mondrian” experiment.1976,16(5):445-458
[77] J. Cataliotti, A. Gilchrist. Local and global processes in surface lightness perception. Percept.Psychophys.,1995,57(2):125-135
[78] M. Kass, A. Witkin. Analyzing oriented patterns. Comput. Vis. Image Und.,1987,37(3):362–385
[79] K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descriptors. IEEE T.Pattern Anal. Mach. Intell.,2005,27(10):1615-1630
[80] L. Meylan, S. Susstrunk. High dynamic range image rendering with a retinex-based adaptivefilter. IEEE T. Image Process.,2006,15(9):2820-2830
[81] G. Buchsbaum, A. Gottschalk. Trichromacy opponent colours coding and optimum colourinformation transmission in the retina. Roy. Soc. Lond. B Biol. Sci.,1983,220:89-113
[82] C. Zeng, Y. Li, C. Li. Center–surround interaction with adaptive inhibition: A computationalmodel for contour detection. NeuroImage,2011,55(1):49-66
[83] F. Ciurea, B. Funt. A large image database for color constancy research. Proc. IS&T/SID’sColor Imaging Conference, The SunBurst Resort, Scottsdale, Arizona,2004,160-164
[84] W. Xiong, B. Funt. Stereo retinex. Image Vision Comput.,2009,27(1-2):178-188
[85] K. Barnard, B. Funt, V. Cardei. A Comparison of Computational Color ConstancyAlgorithms, Part One; Theory and Experiments with Synthetic Data. IEEE T. Image Process.,2002,11(9):972-984
[86] S.D. Hordley, G.D. Finlayson. Reevaluation of color constancy algorithm performance. J.Opt. Soc. Am. A USA,2006,23(5):1008-1020
[87] A Gijsenij, T Gevers, M. Lucassen. Perceptual analysis of distance measures for colorconstancy algorithms. J. Opt. Soc. Am. A. USA,2009,26(10):2243-2256
[88] D. Brainard. Hyperspectral Image Data. http://color.psych.ucsb.edu//hyperspectral/
[89] K. Barnard, L. Martin, A. Coath, B. Funt. A comparison of computational color constancyalgorithms---Part Two: Experiments with image data. IEEE T. Image Process.,2002,11(9):985-996
[90] K. Barnard, L. Martin, B. Funt, et al. A data set for colour research. Color Res. Appl.,2002,27(3):147-151
[91] L. Shi, B. Funt. Re-processed Version of the Gehler Color Constancy Dataset of568Images.accessed from http://www.cs.sfu.ca/~colour/data/
[92] B. Conway, D. Tsaob. Color-tuned neurons are spatially clustered according to colorpreference within alert macaque posterior inferior temporal cortex. P. Natl. Acad. Sci. USA.,2009,106(42):18034-18039
[93] M.T. Vanleeuwen, C. Joselevitch, I. Fahrenfort, et al. The contribution of the outer retina tocolor constancy: a general model for color constancy synthesized from primate and fish data.Visual Neurosci.,2007,24:277-290
[94] A. Choudhury, G. Medioni. Color constancy using denoising methods and cepstral analysis.ICIP'09Proceedings of the16th IEEE international conference on Image processing, Aalen,2009,1637-1640
[95] S. Solomon, P Lennie. The machinery of colour vision. Nat. Rev. Neurosci.,2007,8(4):276-286
[96] A. Rizzi, C. Gatta. A new algorithm for unsupervised global and local color correction.Pattern Recogn. Lett.,2003,24(11):1663-1677
[97] S. Lee. An Efficient Content-Based Image Enhancement in the Compressed Domain UsingRetinex Theory. IEEE T. Circ. Syst. Vid.,2007,17(2):199-213
[98] C. Zeng, Y. Li, C. Li. Center–surround interaction with adaptive inhibition: A computationalmodel for contour detection. NeuroImage,2011,55(1):49-66
[99]王守觉，丁兴号，廖英豪，等.一种新的仿生彩色图像增强方法.电子学报,2008,36(10):1970-1973
[100] A. Gijsenij, T. Gevers, J. van de Weijer. Computational Color Constancy: Survey andExperiments. IEEE T. Image Process.,2011,20(9):2475-2489
[101] L. Shi, B. Funt. Illumination Estimation via Non-Negative Matrix Factorization. Proc. AIC2007Color for Science and Industry, Midterm Meeting of the International ColorAssociation, Hangzhou,2007,1-5
[102] D. Field. Relations between the statistics of natural images and the response properties ofcortical cells. J. Opt. Soc.,1987,4(12):2379-2394
[103] L.D. Selemon，P.S. Goldman-Rakic. Longitudinal topography and interdigitation ofcorticostriatal projections in the rhesus monkey. J Neurosci.,1985,5(3):776
[104] W. Kropatsch, Y. Haxhimusa, Z. Pizlo, et al. Vision Pyramids that do not Grow too High.Pattern Recogn. Lett.,2005,26(3):319–337
[105] G. Lupyan, S. Thompson-Schill, D. Swingley. Conceptual Penetration of Visual Processing.Psychol. Sci.,2010,21(5):682-691
[106] M. Carrasco, B. McElree. Covert attention accelerates the rate of visual informationprocessing. P. Natl. Acad. Sci. USA,2001,98(9):5363-5367
[107] Q. Tang, N. Sang, T. Zhang. Extraction of salient contours from cluttered scenes. PatternRecogn.,2007,40(11):3100-3109
[108] T. Zanto, M. Rubens, A. Thangavel, A. Gazzaley. Causal role of the prefrontal cortex intop-down modulation of visual processing and working memory. Nat. Neurosci.,2011,14,(5):656–661
[109]汪云九.神经信息学－神经系统的理论和模型.北京:高等教育出版社,2006,103-105
[110]罗四维.视觉感知系统信息处理理论.北京:电子工业出版社,2006,7-9
[111] L. Shapiro, G. Stockman.计算机视觉.北京：机械工业出版社.2005,115
[112] K. Ghosh, S. Sarkar, K. Bhaumik. Understanding image structure from a new multi-scalerepresentation of higher order derivative filters. Image Vision Comput.,2007,25(8):1228-1238
[113] C. Kayser, W. Einhauser, P. Kongig. Processing of complex stimuli and nature scenes in thevisual cortex. Current Opinion in Neurobiol.,2004,14(4):468-473
[114] C. Kayser, W. Einhauser, P. Kongig. Responses to Natural Secenes in Cat V1. JNeurophysiol.,2003,90(3):1910-1920
[115] S. Munder, D. Gavrila. An Experimental Study on Pedestrian Classification. IEEE T.Pattern Anal. Mach. Intell.,2006,28(11):1863-1868
[116] C. Wohler, J. Anlauf. An adaptable Time-Delay Neural-Network Algorithm for ImageSequence Analysis. IEEE T. Neural Networ.,1999,10(6):1531-1536
[117] C. Perez, C. Salinas. Genetic Design of Biologically Inspired Receptive Fields for NeuralPattern Recognition. IEEE. T. Syst. Man Cy. B,2003,33(2):258-270
[118]朱舜山,齐翔林,汪云九.基于视觉编码的图像处理研究.生物物理学报,1996,12(2):297-309
[119] M. Perus, B. Horst, C. Loo. Bio-computation model of object recognition: Quantumhebbian processing with neurally-shaped gabor wavelets. BioSystems,2005,82(2):116-126
[120] U. Nuding, C. Zetzsche. Learning the selectivity of V2and V4neurons using non-linearmulti-layer wavelet networks. Biosystems,2007,89(1-3):273-279
[121]陈刚.应用数学和信号处理相遇.高校应用数学学报,1999,14(3):350-366
[122]陈武凡.小波分析及其在图像处理中的应用.北京：科学出版社.2003,152
[123] S. Geman, D. Geman. Stochastic relaxation, Gibbs distributions and the Bayesianrestoration of images. IEEE T. Patten. Anal. Mach. Intell.,1984,6(6):721-741
[124] W. Freeman, E. Pasztor, O. Carmichael. Learning low-level vision. Int. J. Comput. Vision,2000,40(1):24-47
[125] A. Fitzgiboon, Y. Wexler, A. Zisserman. Image-based rendering using image-based priors.Int. J. Comput. Vision,2005,63(2):24-47
[126] S. Zhu, Y. Wu. From local features to global perception---A perspective of Gestaltpsychology from Markov random field theory. Neurocomputing,1999,26-27(6):939-945
[127] S. Roth, M. Black. Fields of Experts: A framework for learning image priors. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2005),2005,860-867
[128] U. Koster, J. Lindgren, A. Hyvarinen. Estimating Markov Random Field Potentials forNatural Images. Lecture Notes in Computer Science (LNCS2009),2009,5441:515-522
[129] H. Noda, M. Shirazi, E. Kawaguchi. MRF-based texture segmentation using waveletdecomposed images. Pattern Recogn.,2002,35(4):771-782
[130]刘国英,茅力非,王雷光,等.基于小波域分层Markov模型的纹理分割.武汉大学学报(信息科学版),2009,34(5):531-534
[131]李旭超,朱善安,朱胜利.基于小波域层次Markov模型的图像分割.中国图象图形学报,2007,12(2):308-314
[132]杜馨瑜.基于Markov随机场的图像分割:[硕士学位论文].成都:电子科技大学,2007,31-36
[133]章毓晋.图像处理.北京：清华大学出版社.2006,365
[134] S. Li. Markov random field modeling in image analysis. Berlin: Springer-Verlag,2009,1-20
[135] C. Bouman, M. Shapiro. A Multiscale Random Field Model for Bayesian ImageSegmentation. IEEE T. Image Process.,1994,3(2):162-177
[136]刘国英,罗伦才,梅天灿,等.基于MRMRF的多光谱纹理影像分割方法.武汉大学学报(信息科学版),2008,33(9):963-966
[137]尼克尔斯.神经生物学—从神经元到脑(第4版).北京:科学出版社,2009,499-519
[138] R. Duda, P. Hart, D. Stock.模式分类（第2版）.北京:机械工业出版,2003,102-105
[139] A. Bronstein, M. Bronstein. Sparse ICA for blind separation of transmitted and reflectedimages. Int. J. Imag. Syst. Tech.,2005,15(1):84-91
[140] B. Olshausen, D. Field. Sparse coding of sensory input. Curr. Opin. Neurobiol.,2004,14(4):481-487
[141]F. Attneave. Some informational aspects of visual perception. Psychol. Revnt.,1954,61:183-193
[142]H. Barlow. Single units and sensation: a neuron doctrine for perceptual psychology?Perception,1972,1(4):371-394
[143] J. Daugman. Complete discrete2-D Gabor transform by neural networks for image analysisand compression. IEEE T. Acoust, Speech, Signal Process.,1988,36(7):1169-1179
[144] S. Grossberg, E. Mingolla. Neural dynamics of form perception: boundary completion,illusory figures, and neon color spreading. Psychol. Rev.,1990,92(2):173-211
[145] L. Glass, M. Mackey. From Clocks to Chaos: The Rhythms of Life. New York: PrincetonUniversity Press,1990,2-11
[146] E. Niedermeyer, F. da Silva. Electroencephalography: Basic Principles, ClinicalApplications and Related Fields. Baltimore: Williams and Wilkins Press,1998,135-140
[147] D. Wang. The time dimension for scene analysis. IEEE T. Neural Network,2005,16(6):1401-1426
[148] P. Strumi o, T. Durrani. Spiral waves in a2-Dmodel of fibrillating heart and a new way tobreak them. Med Science Mon,1996,2(4):495–504
[149] A. Destexhe, T. Sejnowski. The Wilson-Cowan model,36years later. Bio Cybern,2009,101(1-2):1-2
[150] P. Strumillo, M. Strzelecki. Application of Coupled Neural Oscillators for Image TextureSegmentation and Modeling of Biological Rhythms. Int J Appl Math Comput Sci,2006,16(4):513-523
[151] M. Bertalmío, J. Cowan. Implementing the Retinex algorithm with Wilson–Cowanequations. J. Physiol.,2009,103(1-2):69-72
[152] K. Panetta, E. Wharton, S. Agaian. Human Visual System-Based Image Enhancement andLogarithmic Contrast Measure. IEEE T. Syst. Man. Cy. B,2008,38(1):174-188
[153]冈萨雷斯.数字图像处理.北京:电子工业出版社,2003,63-66.
[154] S. Morfu, J. Comte. A Nonlinear Oscillators Network Devoted to Image Processing. Int. J.Bifurcat. Chaos,2004,14(4):1385-1394
[155] D. Jobson, Z. Rahman, G. Woodwell. Properties and performance of center/surroundretinex. IEEE T. Image Process.,1997,6(3):451-462
[156] V. Glezer, T. Tsherbach, V. Gauselman, et al. Linear and Non-Linear Properties of Simpleand Complex Receptive Fields in Area17of the Cat Visual Cortex. BioL. Cybernetics.,1980,37(4):195-208
[157] K. Purpura, E. Kaplan, R. Shapley. Background light and the contrast gain of primate P andM retinal ganglion cells. Proc. Natl. Acad. Sci. USA,1988,85(6):4534-4537
[158] J. von Hateren, A. van der Schaaf. Independent component filters of natural imagescompared with simple cells in primary visual cortex. Proc. R. Soc. Lond B,1998,265(10):359-366
[159] M. Latif, J. Chedjou, K. Kyamakya. The paradigm of Non-linear oscillators in imageprocessing. International Symposium on Theoretical Engineering (ISTET), Germany,2009,205-209
[160] K. Kyamakya, J. Chedjou, M. Latif, et al. A novel image processing approach combining a'coupled nonlinear oscillators'-based paradigm with cellular neural networks for dynamicrobust contrast enhancement. The12th International Workshop on Cellular NanoscaleNetworks and Their Applications (CNNA), Berkeley,2010,1-7
[161] Xinyu Du, Yongjie Li, Cheng Luo, et al. Elitist Restruction Genetic Algorithm Based onMarkov Random Field for Magnetic Resonance Image Segmentation. J. Electron. Sci.&Technol. Journal of Electronic Science and Technology,2012,10(1):83-87
[162] Xinyu Du, Yongjie Li, Dezhong Yao. A Support Vector Machine Based Algorithm forMagnetic Resonance Image Segmentation.2008Fourth International Conference on NaturalComputation (ICNC’08), Jinan,2008,3:49-53