基于生物视觉感知机制的图像理解技术研究
|
摘要
场景理解是计算机视觉中具有挑战性的难点问题，是相关视觉应用的关键环节。动物能迅速地对所处的场景做出判断并响应，准确获取目标对象的位置和类型，这是目前最先进的计算机视觉系统无法媲美的。本文以认知生理学和心理学的研究成果为基础，从图像理解与认知学的相互关系入手，根据动物视觉感知系统中的重要结构和功能机理研究图像理解的关键技术。
本文首先深入研究了人类视觉的认知生理学结构和视觉感知机制。视网膜是视觉信息的起始点，主要存在三种细胞获取视野中不同的图像特征信息，通过LGN中的对应通道传送至初级视皮层的V1区域。视觉皮层中的腹侧通路用来形成感受和进行对象识别，分别经历了Vl、V2、V3或V4（中颖叶区）、顶叶皮层（OPC）或下颖叶皮层（IT）的视觉信息传递过程；背部通路处理动作和其它的空间信息；各层次之间存在着前向、水平和反馈的交互作用。因此人类的视觉感知系统不仅具有层次型结构特点，还具有侧抑制和反馈的特性，可以实现快速有效的视觉感知。
其次重点研究了基于视皮层感知机制的彩色图像分割模型。提出了一种基于多特征的层次化彩色图像感知分割模型，该方法有效的利用图像的亮度空间分布、细节信息以及颜色空间信息，对图像进行初次分割，并利用BPNN模型对多特征分割结果进行融合选择，得到最终的分割结果。另外，结合Trickle-down视觉理论，研究了结合自底向上和自顶向下的BU&TD彩色图像分割模型，使用特定类特征片段实现了自顶向下的分割，更好的模拟了视觉机制的反馈过程。
此外，本文在对现有生物激励目标识别模型进行深入分析的基础上，提出了生物激励的多特征场景分类模型，模型包括两个阶段的处理过程，首先模拟生物低级视觉区域，并行独立的提取图像的三种属性进行场景分类，然后根据三个分割结果进行二次分类，以提高分类的准确性；结合OFC的预测机制和场景上下文信息，研究了基于生物视觉机制的BU&TD目标识别模型，模型在训练阶段建立特定类目标图像的LSF库和GIST特征库，系统自动学习目标的先验知识和上下文信息，在测试阶段，提取输入图像低频特征、上下文特征分别映射到PHC和OFC做出预测，再结合高频细节特征完成目标的识别过程。
最后对本文的研究特色进行了描述，对本文的研究工作进行了总结，分析了各模型的实验结果，指出了模型的优点和缺点，并对下一步的工作进行了展望。
As a great challenge for state-of-the-art systems, scene understanding plays animportant role in computer vision. Animals, however, can quickly arrive at ahypothesis about its main parts so that an appropriate reaction （e.g., escape） isimmediately possible when they are confronted by a visual scene. Based on thecognitive physiology and psychology research results, considering the correlationbetween image understanding and cognitive sciences, according to the structure andmechanism of animal visual perception, some models of image understanding areresearched in this paper.
There are ventral and dorsal visual pathways in the human visual system, Objectrecognition in cortex is thought to be mediated by the ventral visual pathway. Threeparallel pathways, within the early stages of visual information processing, wereestablished in the retina and preserved in the lateral geniculate nucleus (LGN). Thethree pathways were then rearranged into three concurrent streams running throughdifferent compartments of area V1and V2. The V1and V2integrate the informationabout the input and output to V3, V4, and inferotemporal cortex, IT. Based onphysiological experiments in monkeys, IT has been postulated to play a central role inobject recognition. IT in turn is a major source of input to PFC involved in linkingperception to memory. The Mapping of computational architecture to visual areas, withlateral competition and feedback, is hierarchy.
To segment an object from its background image for advanced vision processing, anovel bio-inspired general framework for image segmentation in complex naturescenes is investigated, which is a hierarchical system that mimics the organization oflayered early visual area in primate visual cortex. The proposed methodology consistsof two typical stages: the first stage is a parallel modular structure including threesegmenting operators based on color feature, form feature and texture feature, each ofwhich solves the segmentation problem independently for the same input. Theyimplement the similar computing as the parvocellular, the magnocellular and koniocellular pathway in LGN from the retina to the primary visual cortex. Then, afusion operation, multiple feature fusion segmentation, integrates these three featuresegmentations together through the backpropagation neuron network in the last stage,which simulates the operation of area following the LGN in primary visual cortex.Another model closely follows the computation of trickle-up and trickle-downprocessing in primate visual pathways. The trickle-down path from the frontal cortex tothe lower level visual areas, predicts incoming stimuli, based on the prior knowledgeof the classes; the computation model of this pathway includes mainly a coveringoperator, which covers the result of the trickle-up with the fragments of specific class.As two important computations in the trickle-down stage, associate method andoptimal method base on Bayesian inference are discussed to improve the performanceof the model also. The proposed approaches is applied to several segmentationexperiments of many single objects in clustering conditions, the result shows that theapproaches are capable of competing with state-of-the-art systems.
The early visual area of the animal can perform a great combine function integratingmultiple features of the image to solve the challenges “where” and “what” in the scene.A model for scene image classification is presented in this work; it extends thehierarchical feed-forward model of the visual cortex. Firstly, each of three paths ofclassification uses one image property （i.e. shape, edge or color based features）independently. Then, a single classifier assigns the category of an image based on theprobability distributions of the previous outputs. Experiments show that the modelboosts the classification accuracy over the shape based model. Meanwhile, theproposed approach achieves a high accuracy comparable to other reported methods onpublicly available color image dataset. The second model for object perception mimicsthe computation of trickle-up and trickle-down process in primate visual pathway. Theinformation of high spatial frequency in an image is extracted and optimized to keepthe invariability and selectivity of an object in the trickle-up process. In parallel, thetrickle-down computation is facilitated by the low spatial frequency components topredict the possible objects and most likely context. The object recognition iscompleted by the detailed information through the trickle-up process and thesecontext-and gist-based predictions from trickle-down process. Based on the priorknowledge of the objects and scenes, several recognition experiments demonstrate that the proposed approach is good at object recognition. In addition to its relevance forcomputer vision, the success of this approach suggests a plausibility method for thecombination of forward and backward processes for object perception and sceneidentification in computer vision.
Finally, the merits and disadvantages of the models above are analyzed; the futurework is referred in the last of this paper.
本文首先深入研究了人类视觉的认知生理学结构和视觉感知机制。视网膜是视觉信息的起始点，主要存在三种细胞获取视野中不同的图像特征信息，通过LGN中的对应通道传送至初级视皮层的V1区域。视觉皮层中的腹侧通路用来形成感受和进行对象识别，分别经历了Vl、V2、V3或V4（中颖叶区）、顶叶皮层（OPC）或下颖叶皮层（IT）的视觉信息传递过程；背部通路处理动作和其它的空间信息；各层次之间存在着前向、水平和反馈的交互作用。因此人类的视觉感知系统不仅具有层次型结构特点，还具有侧抑制和反馈的特性，可以实现快速有效的视觉感知。
其次重点研究了基于视皮层感知机制的彩色图像分割模型。提出了一种基于多特征的层次化彩色图像感知分割模型，该方法有效的利用图像的亮度空间分布、细节信息以及颜色空间信息，对图像进行初次分割，并利用BPNN模型对多特征分割结果进行融合选择，得到最终的分割结果。另外，结合Trickle-down视觉理论，研究了结合自底向上和自顶向下的BU&TD彩色图像分割模型，使用特定类特征片段实现了自顶向下的分割，更好的模拟了视觉机制的反馈过程。
此外，本文在对现有生物激励目标识别模型进行深入分析的基础上，提出了生物激励的多特征场景分类模型，模型包括两个阶段的处理过程，首先模拟生物低级视觉区域，并行独立的提取图像的三种属性进行场景分类，然后根据三个分割结果进行二次分类，以提高分类的准确性；结合OFC的预测机制和场景上下文信息，研究了基于生物视觉机制的BU&TD目标识别模型，模型在训练阶段建立特定类目标图像的LSF库和GIST特征库，系统自动学习目标的先验知识和上下文信息，在测试阶段，提取输入图像低频特征、上下文特征分别映射到PHC和OFC做出预测，再结合高频细节特征完成目标的识别过程。
最后对本文的研究特色进行了描述，对本文的研究工作进行了总结，分析了各模型的实验结果，指出了模型的优点和缺点，并对下一步的工作进行了展望。
As a great challenge for state-of-the-art systems, scene understanding plays animportant role in computer vision. Animals, however, can quickly arrive at ahypothesis about its main parts so that an appropriate reaction （e.g., escape） isimmediately possible when they are confronted by a visual scene. Based on thecognitive physiology and psychology research results, considering the correlationbetween image understanding and cognitive sciences, according to the structure andmechanism of animal visual perception, some models of image understanding areresearched in this paper.
There are ventral and dorsal visual pathways in the human visual system, Objectrecognition in cortex is thought to be mediated by the ventral visual pathway. Threeparallel pathways, within the early stages of visual information processing, wereestablished in the retina and preserved in the lateral geniculate nucleus (LGN). Thethree pathways were then rearranged into three concurrent streams running throughdifferent compartments of area V1and V2. The V1and V2integrate the informationabout the input and output to V3, V4, and inferotemporal cortex, IT. Based onphysiological experiments in monkeys, IT has been postulated to play a central role inobject recognition. IT in turn is a major source of input to PFC involved in linkingperception to memory. The Mapping of computational architecture to visual areas, withlateral competition and feedback, is hierarchy.
To segment an object from its background image for advanced vision processing, anovel bio-inspired general framework for image segmentation in complex naturescenes is investigated, which is a hierarchical system that mimics the organization oflayered early visual area in primate visual cortex. The proposed methodology consistsof two typical stages: the first stage is a parallel modular structure including threesegmenting operators based on color feature, form feature and texture feature, each ofwhich solves the segmentation problem independently for the same input. Theyimplement the similar computing as the parvocellular, the magnocellular and koniocellular pathway in LGN from the retina to the primary visual cortex. Then, afusion operation, multiple feature fusion segmentation, integrates these three featuresegmentations together through the backpropagation neuron network in the last stage,which simulates the operation of area following the LGN in primary visual cortex.Another model closely follows the computation of trickle-up and trickle-downprocessing in primate visual pathways. The trickle-down path from the frontal cortex tothe lower level visual areas, predicts incoming stimuli, based on the prior knowledgeof the classes; the computation model of this pathway includes mainly a coveringoperator, which covers the result of the trickle-up with the fragments of specific class.As two important computations in the trickle-down stage, associate method andoptimal method base on Bayesian inference are discussed to improve the performanceof the model also. The proposed approaches is applied to several segmentationexperiments of many single objects in clustering conditions, the result shows that theapproaches are capable of competing with state-of-the-art systems.
The early visual area of the animal can perform a great combine function integratingmultiple features of the image to solve the challenges “where” and “what” in the scene.A model for scene image classification is presented in this work; it extends thehierarchical feed-forward model of the visual cortex. Firstly, each of three paths ofclassification uses one image property （i.e. shape, edge or color based features）independently. Then, a single classifier assigns the category of an image based on theprobability distributions of the previous outputs. Experiments show that the modelboosts the classification accuracy over the shape based model. Meanwhile, theproposed approach achieves a high accuracy comparable to other reported methods onpublicly available color image dataset. The second model for object perception mimicsthe computation of trickle-up and trickle-down process in primate visual pathway. Theinformation of high spatial frequency in an image is extracted and optimized to keepthe invariability and selectivity of an object in the trickle-up process. In parallel, thetrickle-down computation is facilitated by the low spatial frequency components topredict the possible objects and most likely context. The object recognition iscompleted by the detailed information through the trickle-up process and thesecontext-and gist-based predictions from trickle-down process. Based on the priorknowledge of the objects and scenes, several recognition experiments demonstrate that the proposed approach is good at object recognition. In addition to its relevance forcomputer vision, the success of this approach suggests a plausibility method for thecombination of forward and backward processes for object perception and sceneidentification in computer vision.
Finally, the merits and disadvantages of the models above are analyzed; the futurework is referred in the last of this paper.
引文
[1] R.Tadeusiewicz. M. R. Ogiela. The new concept in computer vision: Automatic understandingof the images. Artificial Intelligence and Soft Computing, ICAISC,2004,133-144
[2] S. D. Van Hooser. Similarity and diversity in visual cortex: Is there a unifying theory ofcortical computation? Neuroscientist,2007,13(6):639-656
[3] K. Friston. A theory of cortical responses. Philosophical transactions of the royal society ofLondon Series B biological sciences.2005,360(1456):815-836
[4]谢昭.图像理解的关键问题和方法研究：[博士学位论文].合肥:合肥工业大学,2007
[5]乐宋进，武和雷，胡泳芬.图像分割算法的研究现状与展望.南昌水专学报，2004，23(2):15-20
[6]宋焕生，刘春阳，吴成柯．多尺度脊边缘及其在图像目标分割中的应用．自动化学报，1999,25(6):12-15
[7]张静，王宏刚，王涌天．一种边缘提取的图像分割方法．光学技术，2001，27(5):24-426
[8]林峰，刘政凯．基于图像分割的人眼边缘提取方法研究．计算机应用研究，2000，8(3):100-103
[9]殷德奎，张保民，柏连发．一种热图像的多模板边缘检测方法．南京理工大学学报，1999，23(1):16-20
[10]张斌，朱正中．基于边缘轮廓信息的多源遥感图像分割．中国图像图形学报，2003，3(5):830-835
[11]王字生，陈纯．一种基于积分变换的边缘检测算法．中国图像图形学报，2002，7(2):145-149
[12]梁毅军，贺朋令，蔡元龙．用于图像边缘检测的BD模式及其快速算法，模式识别与人工智能，1998，11(4):434-441
[13]周凌翔，顾伟康．最佳边缘检测的准则与算子．模式识别与人工智能，1998，11(1):54-61
[14]彭丽.基于边缘信息的阈值图像分割：[硕士学位论文].长沙：中南大学,2009
[15]严学强，叶秀清，刘济林．基于量化图像直方图的最大熵阈值处理算法．模式识别与人工智能，1998，11(3):352-358
[16]薛景浩，章毓晋．基于最大类间后验交叉熵的阈值化分割算法．中国图像图形学报，1999，10(6):111-114
[17]付忠良．基于图像差距度量的阈值选取方法．计算机研究与发展，2001，38(5)：563-567
[18]华长发，范建平，高传善．基于二维熵阈值的图像分割及其快速算法．模式识别与人工智能，2000，l3(1):42-45
[19]赵雪松，陈淑珍．综合全局二值比与边缘检测的图像分割方法．计算机辅助设计与图形学学报，2001,13(2):118-121
[20]任明武，杨静宇，孙涵．一种基于边缘模式的直方图构造新方法．计算机研究与发展，2001，38(8):972-976
[21] Chen Zi-kuan, Tao Yang, Chen Xin，et a1．Wavelet Based Adaptive Thresholding Method forImage Segmentation．Optical Engineering,2001,40(5):868-874
[22]王培珍，杜培明．一种用于多阈值图像自动分割的混台遗传算法．中国图像图形学报，2000,5(1):44-47
[23]黎恒，赖声礼．基于小波变换和动态聚类的图像分割方法．华南理工大学学报1999,27(8):54-58
[24]杨波，徐光．基于分形持征的自然景物图像分割方法．中国图像图形学报，1999,4(1)：7-11
[25]陈志彬,邱天爽.一种基于FCM和Level Set的MRI医学图像分割方法.电子学报,2008,36(9):1733-1736
[26]梅雪,夏良正,李久贤.一种基于变分水平集的红外图像分割算法.电子与信息学报,2008,30(7):1700-1702
[27]曹宗杰,闵锐,庞伶俐,皮亦鸣.基于统计模型的变分水平集SAR图像分割方法.电子与信息学报,2008,30(12):2862-2866
[28]刁智多,张冬妍,曹军．基于遗传算法和数学形态学的木材分选图像分割研究．自动化技术与应用，2012，31(1):59-62
[29]罗述谦，唐宇．基于有偏场的适配模糊聚类分割算法．中国图像图形学报，1999，7(2):111-114
[30]薛景浩，章毓晋，林行刚等．一种新的图像模糊散度阈值比分割算法．清华大学学报（自然科学版），1999,30(1):12-16
[31]陈燕新，戚飞虎．基于竞争Hopfied网络的自动聚类图像分割方法，模式识别与人工智能，1998，11(2):215-221
[32]何伟，蒋加伏，齐琦.基于粗糙集理论和神经网络的图像分割方法.计算机工程与应用，2009,45(1):188-190
[33]魏志成，周激流．一种新的图像分割自适应算法的研究，中国图像图形学报，2000,5(3):216-220
[34] J. C. Olivo．Automatic Threshold Selection Using the Wavelet Transform CVGIP．GraphicalModels and Image Process，1994，56(5):357-370．
[35]靳华，王晓丹，赵荣椿．树型小波变换在纹理分析中的应用．计算机应用研究，2001,12(3):91-93．
[36]贾天旭，郑南宁，张元亮．Shannon小波包解自适应Gabor滤波器设计及其在纹理分割中的应用．电子学报，1998，26(10):31-40．
[37]黄双萍.通用视觉目标识别的关键技术研究：[博士学位论文].广州：华南理工大学,2011
[38] Jia Deng, Wei Dong, Richard Soche, Li-Jia Li, Kai Li, Li Fei-Fei. ImageNet: A Large-ScaleHierarchical Image Database. In Computer Vision and Pattern Recognition,2009,248-255
[39] G. Griffin, A. Holub. P. Perona. Caltech-256Object Category Dataset. California Institute ofTechnology,2007
[40] S. A. Nene. S. K. Nayar and H. Murase. Columbia Object Image Library (COIL-100).Technical Report CUCS-006-96, February,1996
[41] Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatialenvelope. International Journal of Computer Vision,2001,42(3):145–175
[42] L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories.Proc. of IEEE Computer Vision and Pattern Recognition,2005,524–531
[43] L. Fei-Fei, R. Fergus, A. Torralba. Recognizing and Learning Object Categories. IEEEComputer Vision and Pattern Recognition,2007,346-352
[44] S. Lazebnik, C. Schmid, J. Ponce. Beyond bags of features: Spatial pyramid matching forrecognizing natural scene categories. IEEE Conference on Computer Vision and PatternRecognition,2006,2169-2178
[45] C. Corinna, V. Vapnik. Support-Vector Networks. Machine Learning,1995,20(3):273-297
[46]钱乐乐.基于视觉层次感知机制的图像理解方法研究：[博士学位论文].合肥：合肥工业大学,2009，5-14
[47] M. Riesenhuber, T. Poggio. Hierarchical models of object recognition in cortex, NatureNeuroscience,1999,2(11):1019-1025
[48]唐奇伶.基于初级视皮层感知机制的轮廓与边界检测：[博士学位论文].武汉：华中科技大学,2007
[49]王哲.基于初级视觉机制的图像编码模型研究：[博士学位论文].北京：北京交通大学,2011
[50]高常鑫.基于上下文的目标检测与识别方法研究：[博士学位论文].武汉：华中科技大学,2010
[51]郑庆庆.纹理特征提取及其在图像分割中的应用研究：[博士学位论文].武汉：华中科技大学,2011
[52]李燕.视觉感知中的闭合轮廓提取方法研究：[博士学位论文].北京：北京交通大学,2011
[53]王丰年.基于视觉注意的运动目标跟踪系统：[博士学位论文].杭州：杭州电子科技大学,2010
[54]魏龙生.视觉信息处理中注意机制计算模型研究：[博士学位论文].武汉：华中科技大学,2011
[55]田明辉.视觉注意机制建模及其应用研究：[博士学位论文].合肥：中国科学技术大学,2010
[56]李凌.视觉注意的神经机制研究：[博士学位论文].成都：电子科技大学,2009
[57]雷旭.基于贝叶斯理论的EEG-fMRI融合技术研究：[博士学位论文].成都：电子科技大学,2011
[58]罗程.多模态神经成像技术在特发性全面性癫痫中的应用研究：[博士学位论文].成都：电子科技大学,2011
[59] C. R. Huang, C. S. Chen, P. C. Chung. Contrast context histogram-a discriminating localdescriptor for image matching.18th International Conference on Pattern Recognition,2006,4:53-56
[60] Yann LeCun, Fu Jie Huang, Léon Bottou. Learning Methods for Generic Object Recognitionwith Invariance to Pose and Lighting. IEEE Conference on Computer Vision and PatternRecognition,2004,2:97-104
[61] I. Kypraios, R. Young, P. Birch, C. Chatwin. Object recognition within cluttered scenesemploying a hybrid optical neural network filter. Optical Engineering,2004,20(43):1839-1842
[62] Carsten Steger. Occlusion, Clutter and Illumination Invariant Object Recognition.International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences,2002,34:345-350
[63] C. Steger. Similarity measures for occlusion, clutter and illumination invariant objectrecognition. Pattern Recognition,2001,148-154
[64] T. Ojala, M. Pietikinen, D. Harwood. Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions. International Conference onPattern Recognition,1994,582-585
[65] D. Lowe. Object recognition from local scale-invariant feature. International Conference onComputer Vision,1999,1150-1157
[66] D. Lowe. Distinctive Image Features from Scale-Invariant Keypoints. International Journal ofComputer vision,2004,60(2):91-110
[67] K. Mikolajczyk. C. Schmid. A performance evaluation of local descriptors. IEEE Transactionson Pattern Analysis and Machine Intelligence,2005,27(10):1615–1630
[68] Y. Ke. Sukthankar. Pca-sift: A more distinctive representation for local image descriptors. InIEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR2004,511-517
[69] K. Mikolajczyk, C. Schmid. A performance evaluation of local descriptors. IEEE Transactionson Pattern Analysis and Machine Intelligence,2005,27(10):31–47
[70] E. A.Koen, D. S. van, G. Theo, G. M. Cees Snoek. Evaluating Color Descriptors for Object andScene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1582-1596
[71] N. Dalal, B. Triggs. Histograms of oriented gradients for human detection. IEEE Conferenceon Computer Vision and Pattern Recognition,2005,886–893
[72] T. Ojala, M. Pietikinen, D. Harwood. Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions. International Conference onPattern Recognition,1994,582-585
[73] T. Ojala, M. Pietikinen, D. Harwood. A Comparative Study of Texture Measures withClassification Based on Feature Distributions. In Pattern Recognition,1996,29(1):51-59
[74] T. Ojala. M. Pietikinen. Multiresolution gray-scale and rotation invariant texture classificationwith local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,2(2):971-987
[75] T. Ahonen, A. Hadid, M. Pietikinen. Face Recognition with Local Binary Patterns. EuropeanConference on Computer Vision,2004,469-481
[76] X. Wang, T.X.Han, S. Yan. An HOG-LBP Human Detector with Partial Occlusion Handling.Computer Vision,2009IEEE12th International Conference on Computer Vision,2009,32-39
[77] C. Siagian, L. Itti. Gist: A Mobile Robotics Application of Context-Based Vision in OutdoorEnvironment, IEEE Computer Society Conference on Computer Vision and PatternRecognition (CVPRW'05),2005
[78] H. Yu, M. Li, H. Zhang, J. Feng. Color texture moments for content-based image retrieval.International Conference on Image Processing,2002,3:929–932
[79] N. V. Vapnik.统计学习理论.许建华，张学工译.中国，北京:电子工业出版社，2004
[80] M. J. Swain, D. H. Ballard. Color indexing. Intemational Journal of ComPuter Vision,1991,7(l):11-32
[81] E. Barla, F. Franceschi, F. Odone et al. Image kernels. In: proceedings of the First Internationalworkshop on Pattem Recognition with Support Vector Machines. Springer-verlag,2002,83-96
[82] C. S. Fowlkes, E. Belongie, E. Chung et al. Spectral grouping using the Nystrom method,2004,26(2):214-225
[83] J. Zhang, J. M. Marszalek, S. Lazebnik et al. Local features and kernels for classification oftexture and object categories: a comprehensive study. Interactional Journal of ComputerVision,2007,73(2):213-38
[84] Y. Rubne, C.Tomasi, C. L. Guibas. The earth mover’s distance as a metric for image retrieval.International Journal of Computer Vision,2000,40(2):99-121
[85] E. D. Rumelhart, E. G. Hinton, J. R. Williams. Learning representations by back-propagatingerrors. Nature,1986,323(6088):533–536
[86]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
[87] D. Marr. Vision: A computational investigation into the human representation and processingof visual information, San Francisco, CA: W.H. Freeman,1982
[88] T. Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman, T. Poggio. A Theory of ObjectRecognition: Computations and Circuits in the Feed forward Path of the Ventral Stream inPrimate Visual Cortex. AI Memo2005-036/CBCL Memo259, Massachusetts Inst. ofTechnology, Cambridge,2005
[89] S. D. Van Hooser. Similarity and diversity in visual cortex: Is there a unifying theory ofcortical computation? Neuroscientist,2007,13(6):639-656
[90] D. H. Hubel, T.N. Wiesel. Functional architecture of macaque monkey visual cortex. In: Proc.R. Soc. Lond,1977,198:1-59
[91]孙昊,郭爱克.视觉颜色感受野的自组织生成.中国科学(B辑),1995,25（11）:1178-1185
[92] Grossberg, E. Mingolla, W. Ross. Visual brain and visual perception: how does the cortexdo perceptual grouping? Trends in Neurosciences,1997,20(3):106-109
[93] S. C. Yen, L. H. Finkel. Extraction of Perceptually Salient Contours by Striate CorticalNetworks. Vision Res,1998,38(5):719-741
[94] S. C. Yen, L. H. Finkel. Salient contour extraction by temporal binding in a cortically-basednetwork. In: Jordan. Mozer. Petsche. Eds, Advances in Neural Information ProcessingSystems10, MIT Press, Cambridge, MA,1998,235-241
[95]寿天德.视觉信息处理的脑机制.上海:上海科技教育出版社，1997
[96] D. Perrot, M. Oral. Neurophysiology of shape Processing. Image and Vision Computation,1993,11(6):317-333
[97] M. M. Gupta, K. K. George. Neural-vision systems: Principles and applications. IEEE Press,1994
[98] Wallis, E. T. Rolls. A model of invariant Object recognition in the visual system. Progress inNeurobiology,1997,51:167-194
[99] S. Behnke, R.Rojas. Neural abstraction Pyramid: A hierarchical image understandingarchitecture. In Proceedings of IJCNN,1998,98(2):820-825
[100] S. Behnke, Hebbian. Learning and competition in the neural abstraction Pyramid. In:Proceedings of UCNN, Washington. DC. USA,1999,2:1356-1361
[101] Y. LeCun, L. Bottou, Y. Beng, P. Haffhef. Gradient-based learning applied to documentrecognition. Proceedings of the IEEE,1998,86(11):2278-2324
[102] B. Mel. Seemore: Combining color, shape and texture histogramming in a neutrally inspiredapproach to visual object recognition. Neural Computation,1997,9(4):777-804
[103] T. Poggio, S. Edelman. A network that learns to recognize3D objects. Nature,1990,343(6255):263-266
[104] M. Riesenhuber, T. Poggio. Neural mechanisms of object recognition. Current Opinion inNeurobiology,2002,12(2):162-168
[105] T. Serre, L. Wolf. S. M. Bilesehi. Maximilian and Tomaso Poggio. Robust Object recognitionwith Cortex-like Mechanisms. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(3):411-26
[106] J. Muteh, G. L. David. Multiclass objects Recognition with sparse, localized Features. InProceedings of CVPR,2006, l:11-18.
[107] S. M. Bileschi, L. Wolf. A unified system for object detection, texture recognition, and contextanalysis-based on the standard model feature set. In British Machine Vision Conference(BMVC),2005.
[108] S. M. Bileschi. Street scenes: Towards Scene Understanding in Still Images. PhD thesis. MIT,2006.
[109] R. N. Rao, D. H. Ballard. Dynamic model of visual recognition predicts neural responseproperties in the visual cortex. Neural Computation,1997,9(4):721-763
[110] W. Ross, S. Grossberg, E. Mingolla. Visual cortical mechanisms of perceptual grouping:interacting layers, networks, columns and maps. Neural Networks,2000,13(6):57-588
[111] M. C. Potter. Short-term conceptual memory for pictures. Journal of Experimental Psychology:Human Learning and Memory,1976,2:509-522
[112] A.oliva. Gist of the scene. In: Itti. L. Rees. G. and Tsotsos. J.K.(Eds). Neurobiology ofAttention, Elsevier,2005,251-256
[113] K. K. Sung, T. Poggio. Finding Human Faces with a Gaussian Mixture Distribution-basedFace Model. In: Proceedings of Second Asian Conference on Computer Vision, Singapore,1995
[114] B. Heisele, T. Serre, T. Poggio. A Component-based Framework for Face Detection andIdentification. International Journal of Computer Vision,2007,74(2):167-181
[115] S. K. Paleta. A Review on Image Segmentation Techniques. Patten Recognition,1993,26(9):1277-1294
[116] W. Skarbek, A. Kosehan. Color Image Segmentation-A Survey. Technical report.10587,Berlin. Germany. Tech. Univ. of Berlin, Oct.1994
[117] J. Min, W. B. Kevin. Improved range image segmentation by analyzing surface fit patterns.Computer vision and image understanding,2005,97(2):242-258
[118] S. Treue. Neural correlates of attention in primate visual cortex. Trends in Neuroscience,2001,24(5):295-300
[119] M. Bar. The proactive brain-using analogies and associations to generate predictions. Trendsin Cognitive Sciences,2007,11(7):280-289
[120] G. D. Field, E. J. Chichilnisky. Information processing in the primate retina: circuitry andcoding. Annual review of neuroscience,2007,30:1-30
[121] M. O. Gewaltig, U. Kǒrner, E. Kǒrner. A model of surface detection and orientation tuning inprimate visual cortex. Neurocomputing,2003,52:519-524
[122] D. Thibaud，B. Ryad. Bio-inspired model of visual information encoding for localization: fromthe retina to the lateral geniculate nucleus. Journal of integrative neuroscience,2007,6(3):477-509
[123] X. Xiangmin, A. B. Bonds, A. Viven. Modeling receptive-field structure of koniocellular,magnocellular and parvocellular LGN cells in the owl monkey. Visual Neuroscience,2002,19(6):703-711
[124] W. Kuo-Lung, Y. Miin-Shen. Mean shift-based clustering，Pattern recognition,2007,40(11):3035-3052
[125] S. Jianbo, M. Jitendra. Normalized cuts and image segmentation. IEEE transactions on patternanalysis and machine intelligence,2000,22(8):888-905
[126] J. A. Sethian. Level set methods and fast marching methods. Cambridge: CambridgeUniversity Press,1999
[127] J. A. Norato, M. P. Bendsoe, R. B. Haber, D. A. Tortorelli. A topological derivative methodfor topology optimization. Structural and multidisciplinary optimization,2007,33(4):375-386
[128] A.Larrabide, A. Novotny, R. A. Feijò, E. Taroco. Topological derivative as a tool for imageprocessing: Image segmentation. Technical report. Laboratòrio Nacional de ComputacáoCientifica,2006.
[129] P. F. Felzenszwalb, D. P. Huttenlocher. Efficient Graph-Based image segmentation.International Journal of Computer Vision,2004,59(2):167-181
[130] X. Han, C. Xu, J. Prince. A topology preserving level set method for geometric deformablemodels. IEEE Transactions on pattern analysis and machine intelligence,2003,25(6):755-768
[131] H. T. Nguyen, M. Worring, R. van den Boomgaard. Watersnakes: Energy-driven watershedsegmentation. IEEE transactions on pattern analysis and machine intelligence,2003,25(3):330-342
[132] C. Yuhua, G. Liqun, L. Shun, T. Lei. Wavelet-based watershed for image segmentationalgorithm. Proceedings of the world congress on intelligent control and automation (WCICA),2006,2:9595-9599
[133] T. Xcheng, H. Erlend, V. B. Nickolay et al. Level set methods for watershed imagesegmentation. Lecture notes in computer science,2007,4485:178-190
[134] B. Andrè, L. L. Joshua. Watershed-based segmentation and region merging. Computer visionand image understanding,2000,77(3):317-370
[135] S. H. C. Hendry, R. C. Reid. The koniocellular pathway in primate vision. Annual review ofneuroscience,2000,23:127-153
[136] M. Treisman, G. Gelade. A feature-integration theory of attention. Cognitive psychology,1980,12(1):97-136
[137] D. W. Jacobs, D. Weinshall,Y. Gdalyahu. Classification with nonmetric distances: Imageretrieval and class representation. IEEE transactions on pattern analysis and machineintelligence,2000,22(6):583-600
[138] K. Jain, D. Zongker. Representation and recognition of handwritten digits using deformabletemplates. IEEE transactions on pattern analysis and machine intelligence,1997,19(12):1386-1391.
[139] V. Grau, A. U. J. Mewes, M. Alcaniz, R. Kikinis, S. K. Warfield. Improved watershedtransform for medical image segmentation using prior information. IEEE Transactions onImage processing,2004,23(4):447-458.
[140] M. Martinez, P. Mittrapiyanuruk, A. C. Kak. On combining graph-partitioning withnon-parametric clustering for image segmentation. Computer vision and image understanding,2004,95(1):72-85.
[141] E. Borenstein, E. Sharon, S. Ullman. Combining top-down and bottom-up segmentation.Proceedings of the IEEE conference on computer vision and pattern recognition workshop onperceptual organization in computer vision,2004,46-54.
[142] E. Borenstein, S. Ullman. Class-specific, top-down segmentation. Proceeding of the Europeanconference on computer vision,2002.
[143] M. Bar, K. S. Kassam, A. S. Ghuman et al. Top-down facilitation of visual recognition.Proceedings of the national academy of sciences of the United States of America,2006,103(2):449-454.
[144] A.Kveraga, S. Ghuman, M. Bar. Top-down predictions in the cognitive brain. Brain andcognition,2007,65(2):145-168.
[145] O'Shea, V. Walsh. Cognitive Neuroscience: trickle-town theories of vision. Current biology,2006,16(6): R206-R209.
[146] V. Caselles, F. Catte, T. Coll, F. Dibos. A geometric model for active contours in imageprocessing. Numerische mathematic,1993,66:1-31.
[147] R. Malladi, J. Sethian, B. Vemuri. Shape modeling with front propagation: A level setapproach. IEEE transactions on pattern analysis and machine intelligence,1995,17(2):158-175.
[148] E. Bernstein, Y. Amit. Part-based statistical models for object classification and detection.IEEE computer society conference on computer vision and pattern recognition,2005,2:734-740
[149] J. Winn, N. Jojic. Locus: Learning object classes with unsupervised segmentation.Proceedings of the IEEE international conference on computer vision,2005,1:756-763
[150] X. Ren, C. Fowlkes, J. Malik. Scale-invariant contour completion using conditional randomfields. Computer vision,2005,1:1214-1221.
[151] L. Zhao, S. Davis. Closely coupled object detection and segmentation. Proceedings of theIEEE international conference on computer vision,2005,1
[152] M. Bar. A cortical mechanism for triggering top-down facilitation in visual object recognition.Journal of cognitive neuroscience,2003,15(4):600-609
[153] D. Kersten, P. Mamassian, A. Yuille. Object perception as Bayesian inference. Annual reviewof psychology,2004,55:271-304
[154] G. D. Lowe. Distinctive image features from scale-invariant keypoints. International journal ofcomputer vision,2004,60(2):91-110
[155] J. Canny. A computational approach to edge detection. IEEE transaction pattern analysis andmachine intelligence,1986,8:679-714
[156] R. P. M. Rao. Bayesian inference and attentional modulation in the visual cortex. Cognitiveneuroscience and neuropsychology,2005,16(16):1843-1848.
[157] P. Mamassian. Bayesian inference of form and shape. Perception,2005,34:20-21
[158] Z. Tu. Image segmentation by data-driven Markov chain Monte Carlo. IEEE Transactions onpattern analysis and machine intelligence,2002,24(5):657-673
[159] D. I. Fine, A. MacLeod, G. M. Boynton. Visual segmentation based on the luminance andchromaticity statistics of natural scenes. Journal of vision,2003,3(1):1283-91.
[160] K. Udupa, V. R. LeBlanc, H. Schmidt et al. Methodology for evaluating image segmentationalgorithms. Proceeding SPIE on medical imaging,2002,4684:266-277
[161] S. R. Picard. Indoor-outdoor image classification. In IEEE Int. Workshop on Content-basedAccess of Image and Video Databases,1998
[162] M. Vailaya, A. K. Figueiredo et al. Content-based hierarchical classification of vacationimages. In IEEE Conf. on Multimedia Computing and Systems,1999,1:518-523
[163] M. Pietikainen, T. Maenpaa, J. Viertola. Color Texture Classification with Color Histogramand Local Binary Patterns. Proc.2nd International Workshop on Texture Analysis andSynthesis,2002.
[164] M. M. Gorkani, R.W. Picard. Texture orientation for sorting photos “at a glance”. In IEEE Intl.Conf. on Pattern Recognition,1994,1:459–464
[165] Vogel, B. Schiele. Semantic modeling of natural scenes for content-based image retrieval.International Journal of Computer Vision,2007,72(2):133-157
[166] Bosch, A. Zisserman, X. Muoz. Scene classification using a hybrid generative/discriminativeapproach. IEEE Trans. Pattern Analysis and Machine Intelligent,2008,30(04):712–727
[167] S. Lazebnik, C. Schmid, J. Ponce. Beyond bags features: spatial pyramid matching forrecognizing natural scene categories. In IEEE Intl. Conf. on Computer Vision and PatternRecognition,2006
[168] S. Thorpe, D. Fize, C. Marlot. Speed of processing in the human visual system. Nature,1996,381:520-22
[169] V. Goffaux, C. Jacques, A. Mouraux, A. Oliva, P.G. Schyns, B. Rossion. Diagnostic colorscontribute to early stages of scene categorization: behavioral and neurophysiologicalevidences. Visual Cognition,2005,12:878-892
[170] D. Hubel, T. Wiesel. Receptive fields of single neurons in the cat's striate cortex, J.Physiol,1959,148:574-591
[171] S. Mallat, W. L. Wang. Singularity detection and processing with wavelets. IEEE Transactionson Information Theory,1992,38(2):617-689
[172]马春梅.赵景秀.一种新的基于小波变换的边缘检测算法.计算技术与自动化,2009,28(4):103-106
[173] CBCL. http://cbcl.mit.edu/software-datasets/standardmodel/index.html
[174] S. Dongjin, T. Dacheng. Biologically inspired feature manifold for scene classification. inIEEE Transactions on Image Processing,2010
[175] Y. Terashimain, Scene Classification with a Biologically Inspired Method, dspace mit edu,2009
[176] C.Siagian. L.ittiin. Rapid biologically-inspired scene classification using features shared withvisual attention. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007
[177] J. Aiweng, W. Chunheng, X. Baihua. D. Ruwe. A New Biologically Inspired Feature forScene Image Classification.201020th International Conference on Pattern Recognition,2010
[178] B. Heisele, T. Serre, T. Poggio. A Component-based Framework for Face Detection andIdentification. International Journal of Computer Vision,2007,74(2):167-181
[179] J. J. DiCarlo, D. D. Cox. Untangling invariant object recognition. Trends in cognitive sciences,2007,11(8):333-341
[180] H. Zhang, A. C. Berg, M. Maire, J. Malik. Svm-knn: discriminative nearest neighborclassification for visual category recognition. IEEE computer society conference on Computervision and pattern recognition,2006,2:2126-2136
[181] G. Wang, F. Li, Y. Zhang. Using dependent regions for object categorization in a generativeframework. IEEE computer society conference on computer vision and pattern recognition,2006,2:1597-1604
[182] J. Mutch, G. D. Lowe. Multiclass object recognition with sparse, localized features. IEEEcomputer society conference on computer vision and pattern recognition,2006,1:11-18
[183] Grauman, T. Darrell. Pyramid match kernels: Discriminative classification with sets of imagefeatures (version2). Cambridge (Massachusetts): MIT technical report CSAIL-TR-2006–020.
[184] Y. LeCun, D. G. Lowe, J. Malik et al. Object recognition. Computer vision. The caltech101: aresponse to pinto et al. PLoS Computational biology,2008
[185] T. Serre, G. Kreiman, M. Kouh, C. Cadieu, U. Knoblich, T. Poggio. A quantitative theory ofimmediate visual recognition. Progress in Brain Research,2007,165:33-56
[186] R. J. Peters, L. Itti. Beyond bottom-up: Incorporating task-dependent influences into acomputational model of spatial attention. In: Proc. IEEE Conference on Computer Vision andPattern Recognition (CVPR),2007.1-8.
[187] D. H. Hubel, T. N.Wiesel. Receptive fields and functional architecture of monkey striatecortex. J. Physiol,1968,195:215–243
[188]王慧.空间和目标注意协同工作的视觉注意计算机模型研究：[博士学位论文]，吉林：吉林大学,2010.
[189] K. Kawasaki, D. L. Sheinberg. Learning to recognize visual objects with microstimulation ininferior temporal cortex. Journal of Neurophysiology,2008,100(1):197-211
[190] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection withDiscriminatively Trained Part Based Models. IEEE Transactions on Pattern Analysis andMachine Intelligence,2010,32(9):1627-164
[191] J. C.Myung, A Torralba, A.S Willsky. A Tree-Based Context Model for Object Recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):240-252
[192] J. Yang, Y. Tian, L. Duan, T. Huang, W.G. Group-Sensitive Multiple Kernel Learning forObject Recognition. IEEE Transactions on Image Processing,2012,21(5):2838–2852
[193] M. Ulrich, C. Wiedemann, C. Steger. Combining Scale-Space and Similarity-Based AspectGraphs for Fast3D Object Recognition. IEEE Transactions on Pattern Analysis and MachineIntelligence,2011,99:1-14
[194] V. Subbaroyan, S.Karthik. Feature fusion for multiple view object recognition based onWavelet Transform.2011International Conference on Nanoscience, Engineering andTechnology,2011, pp:494-496
[2] S. D. Van Hooser. Similarity and diversity in visual cortex: Is there a unifying theory ofcortical computation? Neuroscientist,2007,13(6):639-656
[3] K. Friston. A theory of cortical responses. Philosophical transactions of the royal society ofLondon Series B biological sciences.2005,360(1456):815-836
[4]谢昭.图像理解的关键问题和方法研究：[博士学位论文].合肥:合肥工业大学,2007
[5]乐宋进，武和雷，胡泳芬.图像分割算法的研究现状与展望.南昌水专学报，2004，23(2):15-20
[6]宋焕生，刘春阳，吴成柯．多尺度脊边缘及其在图像目标分割中的应用．自动化学报，1999,25(6):12-15
[7]张静，王宏刚，王涌天．一种边缘提取的图像分割方法．光学技术，2001，27(5):24-426
[8]林峰，刘政凯．基于图像分割的人眼边缘提取方法研究．计算机应用研究，2000，8(3):100-103
[9]殷德奎，张保民，柏连发．一种热图像的多模板边缘检测方法．南京理工大学学报，1999，23(1):16-20
[10]张斌，朱正中．基于边缘轮廓信息的多源遥感图像分割．中国图像图形学报，2003，3(5):830-835
[11]王字生，陈纯．一种基于积分变换的边缘检测算法．中国图像图形学报，2002，7(2):145-149
[12]梁毅军，贺朋令，蔡元龙．用于图像边缘检测的BD模式及其快速算法，模式识别与人工智能，1998，11(4):434-441
[13]周凌翔，顾伟康．最佳边缘检测的准则与算子．模式识别与人工智能，1998，11(1):54-61
[14]彭丽.基于边缘信息的阈值图像分割：[硕士学位论文].长沙：中南大学,2009
[15]严学强，叶秀清，刘济林．基于量化图像直方图的最大熵阈值处理算法．模式识别与人工智能，1998，11(3):352-358
[16]薛景浩，章毓晋．基于最大类间后验交叉熵的阈值化分割算法．中国图像图形学报，1999，10(6):111-114
[17]付忠良．基于图像差距度量的阈值选取方法．计算机研究与发展，2001，38(5)：563-567
[18]华长发，范建平，高传善．基于二维熵阈值的图像分割及其快速算法．模式识别与人工智能，2000，l3(1):42-45
[19]赵雪松，陈淑珍．综合全局二值比与边缘检测的图像分割方法．计算机辅助设计与图形学学报，2001,13(2):118-121
[20]任明武，杨静宇，孙涵．一种基于边缘模式的直方图构造新方法．计算机研究与发展，2001，38(8):972-976
[21] Chen Zi-kuan, Tao Yang, Chen Xin，et a1．Wavelet Based Adaptive Thresholding Method forImage Segmentation．Optical Engineering,2001,40(5):868-874
[22]王培珍，杜培明．一种用于多阈值图像自动分割的混台遗传算法．中国图像图形学报，2000,5(1):44-47
[23]黎恒，赖声礼．基于小波变换和动态聚类的图像分割方法．华南理工大学学报1999,27(8):54-58
[24]杨波，徐光．基于分形持征的自然景物图像分割方法．中国图像图形学报，1999,4(1)：7-11
[25]陈志彬,邱天爽.一种基于FCM和Level Set的MRI医学图像分割方法.电子学报,2008,36(9):1733-1736
[26]梅雪,夏良正,李久贤.一种基于变分水平集的红外图像分割算法.电子与信息学报,2008,30(7):1700-1702
[27]曹宗杰,闵锐,庞伶俐,皮亦鸣.基于统计模型的变分水平集SAR图像分割方法.电子与信息学报,2008,30(12):2862-2866
[28]刁智多,张冬妍,曹军．基于遗传算法和数学形态学的木材分选图像分割研究．自动化技术与应用，2012，31(1):59-62
[29]罗述谦，唐宇．基于有偏场的适配模糊聚类分割算法．中国图像图形学报，1999，7(2):111-114
[30]薛景浩，章毓晋，林行刚等．一种新的图像模糊散度阈值比分割算法．清华大学学报（自然科学版），1999,30(1):12-16
[31]陈燕新，戚飞虎．基于竞争Hopfied网络的自动聚类图像分割方法，模式识别与人工智能，1998，11(2):215-221
[32]何伟，蒋加伏，齐琦.基于粗糙集理论和神经网络的图像分割方法.计算机工程与应用，2009,45(1):188-190
[33]魏志成，周激流．一种新的图像分割自适应算法的研究，中国图像图形学报，2000,5(3):216-220
[34] J. C. Olivo．Automatic Threshold Selection Using the Wavelet Transform CVGIP．GraphicalModels and Image Process，1994，56(5):357-370．
[35]靳华，王晓丹，赵荣椿．树型小波变换在纹理分析中的应用．计算机应用研究，2001,12(3):91-93．
[36]贾天旭，郑南宁，张元亮．Shannon小波包解自适应Gabor滤波器设计及其在纹理分割中的应用．电子学报，1998，26(10):31-40．
[37]黄双萍.通用视觉目标识别的关键技术研究：[博士学位论文].广州：华南理工大学,2011
[38] Jia Deng, Wei Dong, Richard Soche, Li-Jia Li, Kai Li, Li Fei-Fei. ImageNet: A Large-ScaleHierarchical Image Database. In Computer Vision and Pattern Recognition,2009,248-255
[39] G. Griffin, A. Holub. P. Perona. Caltech-256Object Category Dataset. California Institute ofTechnology,2007
[40] S. A. Nene. S. K. Nayar and H. Murase. Columbia Object Image Library (COIL-100).Technical Report CUCS-006-96, February,1996
[41] Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatialenvelope. International Journal of Computer Vision,2001,42(3):145–175
[42] L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories.Proc. of IEEE Computer Vision and Pattern Recognition,2005,524–531
[43] L. Fei-Fei, R. Fergus, A. Torralba. Recognizing and Learning Object Categories. IEEEComputer Vision and Pattern Recognition,2007,346-352
[44] S. Lazebnik, C. Schmid, J. Ponce. Beyond bags of features: Spatial pyramid matching forrecognizing natural scene categories. IEEE Conference on Computer Vision and PatternRecognition,2006,2169-2178
[45] C. Corinna, V. Vapnik. Support-Vector Networks. Machine Learning,1995,20(3):273-297
[46]钱乐乐.基于视觉层次感知机制的图像理解方法研究：[博士学位论文].合肥：合肥工业大学,2009，5-14
[47] M. Riesenhuber, T. Poggio. Hierarchical models of object recognition in cortex, NatureNeuroscience,1999,2(11):1019-1025
[48]唐奇伶.基于初级视皮层感知机制的轮廓与边界检测：[博士学位论文].武汉：华中科技大学,2007
[49]王哲.基于初级视觉机制的图像编码模型研究：[博士学位论文].北京：北京交通大学,2011
[50]高常鑫.基于上下文的目标检测与识别方法研究：[博士学位论文].武汉：华中科技大学,2010
[51]郑庆庆.纹理特征提取及其在图像分割中的应用研究：[博士学位论文].武汉：华中科技大学,2011
[52]李燕.视觉感知中的闭合轮廓提取方法研究：[博士学位论文].北京：北京交通大学,2011
[53]王丰年.基于视觉注意的运动目标跟踪系统：[博士学位论文].杭州：杭州电子科技大学,2010
[54]魏龙生.视觉信息处理中注意机制计算模型研究：[博士学位论文].武汉：华中科技大学,2011
[55]田明辉.视觉注意机制建模及其应用研究：[博士学位论文].合肥：中国科学技术大学,2010
[56]李凌.视觉注意的神经机制研究：[博士学位论文].成都：电子科技大学,2009
[57]雷旭.基于贝叶斯理论的EEG-fMRI融合技术研究：[博士学位论文].成都：电子科技大学,2011
[58]罗程.多模态神经成像技术在特发性全面性癫痫中的应用研究：[博士学位论文].成都：电子科技大学,2011
[59] C. R. Huang, C. S. Chen, P. C. Chung. Contrast context histogram-a discriminating localdescriptor for image matching.18th International Conference on Pattern Recognition,2006,4:53-56
[60] Yann LeCun, Fu Jie Huang, Léon Bottou. Learning Methods for Generic Object Recognitionwith Invariance to Pose and Lighting. IEEE Conference on Computer Vision and PatternRecognition,2004,2:97-104
[61] I. Kypraios, R. Young, P. Birch, C. Chatwin. Object recognition within cluttered scenesemploying a hybrid optical neural network filter. Optical Engineering,2004,20(43):1839-1842
[62] Carsten Steger. Occlusion, Clutter and Illumination Invariant Object Recognition.International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences,2002,34:345-350
[63] C. Steger. Similarity measures for occlusion, clutter and illumination invariant objectrecognition. Pattern Recognition,2001,148-154
[64] T. Ojala, M. Pietikinen, D. Harwood. Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions. International Conference onPattern Recognition,1994,582-585
[65] D. Lowe. Object recognition from local scale-invariant feature. International Conference onComputer Vision,1999,1150-1157
[66] D. Lowe. Distinctive Image Features from Scale-Invariant Keypoints. International Journal ofComputer vision,2004,60(2):91-110
[67] K. Mikolajczyk. C. Schmid. A performance evaluation of local descriptors. IEEE Transactionson Pattern Analysis and Machine Intelligence,2005,27(10):1615–1630
[68] Y. Ke. Sukthankar. Pca-sift: A more distinctive representation for local image descriptors. InIEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR2004,511-517
[69] K. Mikolajczyk, C. Schmid. A performance evaluation of local descriptors. IEEE Transactionson Pattern Analysis and Machine Intelligence,2005,27(10):31–47
[70] E. A.Koen, D. S. van, G. Theo, G. M. Cees Snoek. Evaluating Color Descriptors for Object andScene Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1582-1596
[71] N. Dalal, B. Triggs. Histograms of oriented gradients for human detection. IEEE Conferenceon Computer Vision and Pattern Recognition,2005,886–893
[72] T. Ojala, M. Pietikinen, D. Harwood. Performance evaluation of texture measures withclassification based on Kullback discrimination of distributions. International Conference onPattern Recognition,1994,582-585
[73] T. Ojala, M. Pietikinen, D. Harwood. A Comparative Study of Texture Measures withClassification Based on Feature Distributions. In Pattern Recognition,1996,29(1):51-59
[74] T. Ojala. M. Pietikinen. Multiresolution gray-scale and rotation invariant texture classificationwith local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,2(2):971-987
[75] T. Ahonen, A. Hadid, M. Pietikinen. Face Recognition with Local Binary Patterns. EuropeanConference on Computer Vision,2004,469-481
[76] X. Wang, T.X.Han, S. Yan. An HOG-LBP Human Detector with Partial Occlusion Handling.Computer Vision,2009IEEE12th International Conference on Computer Vision,2009,32-39
[77] C. Siagian, L. Itti. Gist: A Mobile Robotics Application of Context-Based Vision in OutdoorEnvironment, IEEE Computer Society Conference on Computer Vision and PatternRecognition (CVPRW'05),2005
[78] H. Yu, M. Li, H. Zhang, J. Feng. Color texture moments for content-based image retrieval.International Conference on Image Processing,2002,3:929–932
[79] N. V. Vapnik.统计学习理论.许建华，张学工译.中国，北京:电子工业出版社，2004
[80] M. J. Swain, D. H. Ballard. Color indexing. Intemational Journal of ComPuter Vision,1991,7(l):11-32
[81] E. Barla, F. Franceschi, F. Odone et al. Image kernels. In: proceedings of the First Internationalworkshop on Pattem Recognition with Support Vector Machines. Springer-verlag,2002,83-96
[82] C. S. Fowlkes, E. Belongie, E. Chung et al. Spectral grouping using the Nystrom method,2004,26(2):214-225
[83] J. Zhang, J. M. Marszalek, S. Lazebnik et al. Local features and kernels for classification oftexture and object categories: a comprehensive study. Interactional Journal of ComputerVision,2007,73(2):213-38
[84] Y. Rubne, C.Tomasi, C. L. Guibas. The earth mover’s distance as a metric for image retrieval.International Journal of Computer Vision,2000,40(2):99-121
[85] E. D. Rumelhart, E. G. Hinton, J. R. Williams. Learning representations by back-propagatingerrors. Nature,1986,323(6088):533–536
[86]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
[87] D. Marr. Vision: A computational investigation into the human representation and processingof visual information, San Francisco, CA: W.H. Freeman,1982
[88] T. Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman, T. Poggio. A Theory of ObjectRecognition: Computations and Circuits in the Feed forward Path of the Ventral Stream inPrimate Visual Cortex. AI Memo2005-036/CBCL Memo259, Massachusetts Inst. ofTechnology, Cambridge,2005
[89] S. D. Van Hooser. Similarity and diversity in visual cortex: Is there a unifying theory ofcortical computation? Neuroscientist,2007,13(6):639-656
[90] D. H. Hubel, T.N. Wiesel. Functional architecture of macaque monkey visual cortex. In: Proc.R. Soc. Lond,1977,198:1-59
[91]孙昊,郭爱克.视觉颜色感受野的自组织生成.中国科学(B辑),1995,25（11）:1178-1185
[92] Grossberg, E. Mingolla, W. Ross. Visual brain and visual perception: how does the cortexdo perceptual grouping? Trends in Neurosciences,1997,20(3):106-109
[93] S. C. Yen, L. H. Finkel. Extraction of Perceptually Salient Contours by Striate CorticalNetworks. Vision Res,1998,38(5):719-741
[94] S. C. Yen, L. H. Finkel. Salient contour extraction by temporal binding in a cortically-basednetwork. In: Jordan. Mozer. Petsche. Eds, Advances in Neural Information ProcessingSystems10, MIT Press, Cambridge, MA,1998,235-241
[95]寿天德.视觉信息处理的脑机制.上海:上海科技教育出版社，1997
[96] D. Perrot, M. Oral. Neurophysiology of shape Processing. Image and Vision Computation,1993,11(6):317-333
[97] M. M. Gupta, K. K. George. Neural-vision systems: Principles and applications. IEEE Press,1994
[98] Wallis, E. T. Rolls. A model of invariant Object recognition in the visual system. Progress inNeurobiology,1997,51:167-194
[99] S. Behnke, R.Rojas. Neural abstraction Pyramid: A hierarchical image understandingarchitecture. In Proceedings of IJCNN,1998,98(2):820-825
[100] S. Behnke, Hebbian. Learning and competition in the neural abstraction Pyramid. In:Proceedings of UCNN, Washington. DC. USA,1999,2:1356-1361
[101] Y. LeCun, L. Bottou, Y. Beng, P. Haffhef. Gradient-based learning applied to documentrecognition. Proceedings of the IEEE,1998,86(11):2278-2324
[102] B. Mel. Seemore: Combining color, shape and texture histogramming in a neutrally inspiredapproach to visual object recognition. Neural Computation,1997,9(4):777-804
[103] T. Poggio, S. Edelman. A network that learns to recognize3D objects. Nature,1990,343(6255):263-266
[104] M. Riesenhuber, T. Poggio. Neural mechanisms of object recognition. Current Opinion inNeurobiology,2002,12(2):162-168
[105] T. Serre, L. Wolf. S. M. Bilesehi. Maximilian and Tomaso Poggio. Robust Object recognitionwith Cortex-like Mechanisms. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(3):411-26
[106] J. Muteh, G. L. David. Multiclass objects Recognition with sparse, localized Features. InProceedings of CVPR,2006, l:11-18.
[107] S. M. Bileschi, L. Wolf. A unified system for object detection, texture recognition, and contextanalysis-based on the standard model feature set. In British Machine Vision Conference(BMVC),2005.
[108] S. M. Bileschi. Street scenes: Towards Scene Understanding in Still Images. PhD thesis. MIT,2006.
[109] R. N. Rao, D. H. Ballard. Dynamic model of visual recognition predicts neural responseproperties in the visual cortex. Neural Computation,1997,9(4):721-763
[110] W. Ross, S. Grossberg, E. Mingolla. Visual cortical mechanisms of perceptual grouping:interacting layers, networks, columns and maps. Neural Networks,2000,13(6):57-588
[111] M. C. Potter. Short-term conceptual memory for pictures. Journal of Experimental Psychology:Human Learning and Memory,1976,2:509-522
[112] A.oliva. Gist of the scene. In: Itti. L. Rees. G. and Tsotsos. J.K.(Eds). Neurobiology ofAttention, Elsevier,2005,251-256
[113] K. K. Sung, T. Poggio. Finding Human Faces with a Gaussian Mixture Distribution-basedFace Model. In: Proceedings of Second Asian Conference on Computer Vision, Singapore,1995
[114] B. Heisele, T. Serre, T. Poggio. A Component-based Framework for Face Detection andIdentification. International Journal of Computer Vision,2007,74(2):167-181
[115] S. K. Paleta. A Review on Image Segmentation Techniques. Patten Recognition,1993,26(9):1277-1294
[116] W. Skarbek, A. Kosehan. Color Image Segmentation-A Survey. Technical report.10587,Berlin. Germany. Tech. Univ. of Berlin, Oct.1994
[117] J. Min, W. B. Kevin. Improved range image segmentation by analyzing surface fit patterns.Computer vision and image understanding,2005,97(2):242-258
[118] S. Treue. Neural correlates of attention in primate visual cortex. Trends in Neuroscience,2001,24(5):295-300
[119] M. Bar. The proactive brain-using analogies and associations to generate predictions. Trendsin Cognitive Sciences,2007,11(7):280-289
[120] G. D. Field, E. J. Chichilnisky. Information processing in the primate retina: circuitry andcoding. Annual review of neuroscience,2007,30:1-30
[121] M. O. Gewaltig, U. Kǒrner, E. Kǒrner. A model of surface detection and orientation tuning inprimate visual cortex. Neurocomputing,2003,52:519-524
[122] D. Thibaud，B. Ryad. Bio-inspired model of visual information encoding for localization: fromthe retina to the lateral geniculate nucleus. Journal of integrative neuroscience,2007,6(3):477-509
[123] X. Xiangmin, A. B. Bonds, A. Viven. Modeling receptive-field structure of koniocellular,magnocellular and parvocellular LGN cells in the owl monkey. Visual Neuroscience,2002,19(6):703-711
[124] W. Kuo-Lung, Y. Miin-Shen. Mean shift-based clustering，Pattern recognition,2007,40(11):3035-3052
[125] S. Jianbo, M. Jitendra. Normalized cuts and image segmentation. IEEE transactions on patternanalysis and machine intelligence,2000,22(8):888-905
[126] J. A. Sethian. Level set methods and fast marching methods. Cambridge: CambridgeUniversity Press,1999
[127] J. A. Norato, M. P. Bendsoe, R. B. Haber, D. A. Tortorelli. A topological derivative methodfor topology optimization. Structural and multidisciplinary optimization,2007,33(4):375-386
[128] A.Larrabide, A. Novotny, R. A. Feijò, E. Taroco. Topological derivative as a tool for imageprocessing: Image segmentation. Technical report. Laboratòrio Nacional de ComputacáoCientifica,2006.
[129] P. F. Felzenszwalb, D. P. Huttenlocher. Efficient Graph-Based image segmentation.International Journal of Computer Vision,2004,59(2):167-181
[130] X. Han, C. Xu, J. Prince. A topology preserving level set method for geometric deformablemodels. IEEE Transactions on pattern analysis and machine intelligence,2003,25(6):755-768
[131] H. T. Nguyen, M. Worring, R. van den Boomgaard. Watersnakes: Energy-driven watershedsegmentation. IEEE transactions on pattern analysis and machine intelligence,2003,25(3):330-342
[132] C. Yuhua, G. Liqun, L. Shun, T. Lei. Wavelet-based watershed for image segmentationalgorithm. Proceedings of the world congress on intelligent control and automation (WCICA),2006,2:9595-9599
[133] T. Xcheng, H. Erlend, V. B. Nickolay et al. Level set methods for watershed imagesegmentation. Lecture notes in computer science,2007,4485:178-190
[134] B. Andrè, L. L. Joshua. Watershed-based segmentation and region merging. Computer visionand image understanding,2000,77(3):317-370
[135] S. H. C. Hendry, R. C. Reid. The koniocellular pathway in primate vision. Annual review ofneuroscience,2000,23:127-153
[136] M. Treisman, G. Gelade. A feature-integration theory of attention. Cognitive psychology,1980,12(1):97-136
[137] D. W. Jacobs, D. Weinshall,Y. Gdalyahu. Classification with nonmetric distances: Imageretrieval and class representation. IEEE transactions on pattern analysis and machineintelligence,2000,22(6):583-600
[138] K. Jain, D. Zongker. Representation and recognition of handwritten digits using deformabletemplates. IEEE transactions on pattern analysis and machine intelligence,1997,19(12):1386-1391.
[139] V. Grau, A. U. J. Mewes, M. Alcaniz, R. Kikinis, S. K. Warfield. Improved watershedtransform for medical image segmentation using prior information. IEEE Transactions onImage processing,2004,23(4):447-458.
[140] M. Martinez, P. Mittrapiyanuruk, A. C. Kak. On combining graph-partitioning withnon-parametric clustering for image segmentation. Computer vision and image understanding,2004,95(1):72-85.
[141] E. Borenstein, E. Sharon, S. Ullman. Combining top-down and bottom-up segmentation.Proceedings of the IEEE conference on computer vision and pattern recognition workshop onperceptual organization in computer vision,2004,46-54.
[142] E. Borenstein, S. Ullman. Class-specific, top-down segmentation. Proceeding of the Europeanconference on computer vision,2002.
[143] M. Bar, K. S. Kassam, A. S. Ghuman et al. Top-down facilitation of visual recognition.Proceedings of the national academy of sciences of the United States of America,2006,103(2):449-454.
[144] A.Kveraga, S. Ghuman, M. Bar. Top-down predictions in the cognitive brain. Brain andcognition,2007,65(2):145-168.
[145] O'Shea, V. Walsh. Cognitive Neuroscience: trickle-town theories of vision. Current biology,2006,16(6): R206-R209.
[146] V. Caselles, F. Catte, T. Coll, F. Dibos. A geometric model for active contours in imageprocessing. Numerische mathematic,1993,66:1-31.
[147] R. Malladi, J. Sethian, B. Vemuri. Shape modeling with front propagation: A level setapproach. IEEE transactions on pattern analysis and machine intelligence,1995,17(2):158-175.
[148] E. Bernstein, Y. Amit. Part-based statistical models for object classification and detection.IEEE computer society conference on computer vision and pattern recognition,2005,2:734-740
[149] J. Winn, N. Jojic. Locus: Learning object classes with unsupervised segmentation.Proceedings of the IEEE international conference on computer vision,2005,1:756-763
[150] X. Ren, C. Fowlkes, J. Malik. Scale-invariant contour completion using conditional randomfields. Computer vision,2005,1:1214-1221.
[151] L. Zhao, S. Davis. Closely coupled object detection and segmentation. Proceedings of theIEEE international conference on computer vision,2005,1
[152] M. Bar. A cortical mechanism for triggering top-down facilitation in visual object recognition.Journal of cognitive neuroscience,2003,15(4):600-609
[153] D. Kersten, P. Mamassian, A. Yuille. Object perception as Bayesian inference. Annual reviewof psychology,2004,55:271-304
[154] G. D. Lowe. Distinctive image features from scale-invariant keypoints. International journal ofcomputer vision,2004,60(2):91-110
[155] J. Canny. A computational approach to edge detection. IEEE transaction pattern analysis andmachine intelligence,1986,8:679-714
[156] R. P. M. Rao. Bayesian inference and attentional modulation in the visual cortex. Cognitiveneuroscience and neuropsychology,2005,16(16):1843-1848.
[157] P. Mamassian. Bayesian inference of form and shape. Perception,2005,34:20-21
[158] Z. Tu. Image segmentation by data-driven Markov chain Monte Carlo. IEEE Transactions onpattern analysis and machine intelligence,2002,24(5):657-673
[159] D. I. Fine, A. MacLeod, G. M. Boynton. Visual segmentation based on the luminance andchromaticity statistics of natural scenes. Journal of vision,2003,3(1):1283-91.
[160] K. Udupa, V. R. LeBlanc, H. Schmidt et al. Methodology for evaluating image segmentationalgorithms. Proceeding SPIE on medical imaging,2002,4684:266-277
[161] S. R. Picard. Indoor-outdoor image classification. In IEEE Int. Workshop on Content-basedAccess of Image and Video Databases,1998
[162] M. Vailaya, A. K. Figueiredo et al. Content-based hierarchical classification of vacationimages. In IEEE Conf. on Multimedia Computing and Systems,1999,1:518-523
[163] M. Pietikainen, T. Maenpaa, J. Viertola. Color Texture Classification with Color Histogramand Local Binary Patterns. Proc.2nd International Workshop on Texture Analysis andSynthesis,2002.
[164] M. M. Gorkani, R.W. Picard. Texture orientation for sorting photos “at a glance”. In IEEE Intl.Conf. on Pattern Recognition,1994,1:459–464
[165] Vogel, B. Schiele. Semantic modeling of natural scenes for content-based image retrieval.International Journal of Computer Vision,2007,72(2):133-157
[166] Bosch, A. Zisserman, X. Muoz. Scene classification using a hybrid generative/discriminativeapproach. IEEE Trans. Pattern Analysis and Machine Intelligent,2008,30(04):712–727
[167] S. Lazebnik, C. Schmid, J. Ponce. Beyond bags features: spatial pyramid matching forrecognizing natural scene categories. In IEEE Intl. Conf. on Computer Vision and PatternRecognition,2006
[168] S. Thorpe, D. Fize, C. Marlot. Speed of processing in the human visual system. Nature,1996,381:520-22
[169] V. Goffaux, C. Jacques, A. Mouraux, A. Oliva, P.G. Schyns, B. Rossion. Diagnostic colorscontribute to early stages of scene categorization: behavioral and neurophysiologicalevidences. Visual Cognition,2005,12:878-892
[170] D. Hubel, T. Wiesel. Receptive fields of single neurons in the cat's striate cortex, J.Physiol,1959,148:574-591
[171] S. Mallat, W. L. Wang. Singularity detection and processing with wavelets. IEEE Transactionson Information Theory,1992,38(2):617-689
[172]马春梅.赵景秀.一种新的基于小波变换的边缘检测算法.计算技术与自动化,2009,28(4):103-106
[173] CBCL. http://cbcl.mit.edu/software-datasets/standardmodel/index.html
[174] S. Dongjin, T. Dacheng. Biologically inspired feature manifold for scene classification. inIEEE Transactions on Image Processing,2010
[175] Y. Terashimain, Scene Classification with a Biologically Inspired Method, dspace mit edu,2009
[176] C.Siagian. L.ittiin. Rapid biologically-inspired scene classification using features shared withvisual attention. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007
[177] J. Aiweng, W. Chunheng, X. Baihua. D. Ruwe. A New Biologically Inspired Feature forScene Image Classification.201020th International Conference on Pattern Recognition,2010
[178] B. Heisele, T. Serre, T. Poggio. A Component-based Framework for Face Detection andIdentification. International Journal of Computer Vision,2007,74(2):167-181
[179] J. J. DiCarlo, D. D. Cox. Untangling invariant object recognition. Trends in cognitive sciences,2007,11(8):333-341
[180] H. Zhang, A. C. Berg, M. Maire, J. Malik. Svm-knn: discriminative nearest neighborclassification for visual category recognition. IEEE computer society conference on Computervision and pattern recognition,2006,2:2126-2136
[181] G. Wang, F. Li, Y. Zhang. Using dependent regions for object categorization in a generativeframework. IEEE computer society conference on computer vision and pattern recognition,2006,2:1597-1604
[182] J. Mutch, G. D. Lowe. Multiclass object recognition with sparse, localized features. IEEEcomputer society conference on computer vision and pattern recognition,2006,1:11-18
[183] Grauman, T. Darrell. Pyramid match kernels: Discriminative classification with sets of imagefeatures (version2). Cambridge (Massachusetts): MIT technical report CSAIL-TR-2006–020.
[184] Y. LeCun, D. G. Lowe, J. Malik et al. Object recognition. Computer vision. The caltech101: aresponse to pinto et al. PLoS Computational biology,2008
[185] T. Serre, G. Kreiman, M. Kouh, C. Cadieu, U. Knoblich, T. Poggio. A quantitative theory ofimmediate visual recognition. Progress in Brain Research,2007,165:33-56
[186] R. J. Peters, L. Itti. Beyond bottom-up: Incorporating task-dependent influences into acomputational model of spatial attention. In: Proc. IEEE Conference on Computer Vision andPattern Recognition (CVPR),2007.1-8.
[187] D. H. Hubel, T. N.Wiesel. Receptive fields and functional architecture of monkey striatecortex. J. Physiol,1968,195:215–243
[188]王慧.空间和目标注意协同工作的视觉注意计算机模型研究：[博士学位论文]，吉林：吉林大学,2010.
[189] K. Kawasaki, D. L. Sheinberg. Learning to recognize visual objects with microstimulation ininferior temporal cortex. Journal of Neurophysiology,2008,100(1):197-211
[190] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection withDiscriminatively Trained Part Based Models. IEEE Transactions on Pattern Analysis andMachine Intelligence,2010,32(9):1627-164
[191] J. C.Myung, A Torralba, A.S Willsky. A Tree-Based Context Model for Object Recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(2):240-252
[192] J. Yang, Y. Tian, L. Duan, T. Huang, W.G. Group-Sensitive Multiple Kernel Learning forObject Recognition. IEEE Transactions on Image Processing,2012,21(5):2838–2852
[193] M. Ulrich, C. Wiedemann, C. Steger. Combining Scale-Space and Similarity-Based AspectGraphs for Fast3D Object Recognition. IEEE Transactions on Pattern Analysis and MachineIntelligence,2011,99:1-14
[194] V. Subbaroyan, S.Karthik. Feature fusion for multiple view object recognition based onWavelet Transform.2011International Conference on Nanoscience, Engineering andTechnology,2011, pp:494-496