复杂场景中目标识别与分类的仿生原理和方法
|
摘要
图像理解是以图像为研究对象，以人类知识为核心，主要研究图像中有什么目标、目标之间的相互关系、图像是什么场景以及如何应用场景的一门科学。其主要研究方向有场景中目标的分类与识别、场景描述与理解两个方面。其中，目标识别是为了对场景进行更好的解释，是场景描述与理解的基础，具有主动性。场景描述与理解为目标识别提供先验信息，可以指导目标识别。从本质上说，图像理解源于计算机视觉，但也融合了人工智能和认知学领域的知识信息，是与计算机视觉、人工智能和认知学相互关联又相互独立的研究领域。目标识别作为图像理解的基础，已应用于身份确定、智能交通管理、机动车辆检测等领域。目标识别的任务是使计算机具有对视觉图像进行复杂背景下检测、识别目标并进行分类的能力。但目前用于目标识别的模板匹配、边缘检测和统计等方法都缺乏生物视觉系统的智能性。
自20世纪90年代开始，王守觉院士研究分析了人类认识事物的过程，总结出了同源样本的连续性规律，并称之为同源连续性原理，然后将此原理应用到模式识别中，提出了仿生模式识别方法，并由此形成了高维空间仿生信息学理论，该理论的提出为如何利用计算机解决形象思维问题开辟了一个新途径。本文从研究生物视觉系统的工作机理出发，结合王守觉院士关于高维空间仿生信息学的相关理论，构建相应的计算机模型，研究了图像理解中的目标识别与分类问题，针对不同场景提出了多种目标分类与识别方法。实验结果表明，本文提出的复杂场景中目标的特征提取模型以及在此基础上提出的仿生识别与分类方法有效可行。本文的主要工作总结如下。
（1）应用神经生物学知识，对物体识别中涉及的各个脑区分别建模，提出了一种基于视皮层不变性识别机制的类表象仿生构建方法；并利用真实图像组成的训练集和测试集对模型和算法进行测试。结果表明，该方法可以在这些样本上建立有效的深层表征并在其上完成类表象的构建。
（2）利用心理学中表象的形成与知觉信息处理过程具有很强相似性的特点，本文将表象系统与视知觉系统建立连接，找到识别活动中各层细胞的活动状态，认为表象的构建来源于识别活动中习得的多个神经元集群的活跃状态，并把其作为表象构建的来源和基础——表象基。通过对识别活动中视皮层各脑区细胞的活动状态进行分别建模，并在其上进行高层次的模式记忆和分析，实现了表象基的提取。
（3）结合神经生物学关于视皮层研究的最新成果，将物体识别中的不变性问题引入表象式深层表征的目标范畴确定中。利用腹部视觉通路中细胞的“形状调谐”以及“范畴调谐”的特点，对视皮层细胞的特异性和不变性进行了权衡。
（4）利用Bag of words模型构造了Codebook高维空间，利用高维形象几何理论，将图像向量映射成Codebook空间中的样本点，并根据仿生信息学的同源连续性原理，使用BP神经网络分类器找到不同类别目标在Codebook空间中的最佳划分，从而提出了一种复杂场景中特定目标的仿生识别与分类方法；并基于该方法设计了不含隐层和含有一个隐层的BP神经网络仿生分类器，通过实验探讨了影响分类器识别准确率的若干因素及其变化规律，并将本文方法与传统方法得到的实验结果进行对比，证明了论文中提出方法的有效性。
（5）在研究了人类视觉系统处理机制的基础上，首先利用方向梯度描述符（HOG）建立了图像的鲁棒表示；然后，根据人类视觉系统的并行处理机制和仿生信息学理论，提出了基于HOG+SVM和HOG+RBPNN的两种人体行为仿生识别与分类方法。利用针对识别与分类方法的评价指标对本文方法进行了评价，最后，与目前常用方法进行了比较，结果表明，在针对静态图像中人体行为的分类与识别效果方面，本文方法对差别较大的行为的识别效果好于常用方法，对相似行为的识别效果还有待于进一步提高。
综上所述，本文基于人类视觉系统和高维空间仿生信息学理论，提出的复杂场景中目标的仿生识别与分类算法，可为其他目标识别方法和高维空间仿生信息学的研究提供借鉴。
Image Understanding (IU) is to study images based on human knowledge, whichfocuses on what are objects in the image, the relationship between objects, what is scene inthe image and how to apply the scene. It mainly includes two parts: object classification andrecognition in a scene, and scene description and understanding. Object recognition has theinitiative and is the base of scene description and understanding, which is to make scene beexplained well. Scene description and understanding provide the apriori information forobject recognition, which can guide the object recognition. In essence, IU derives fromcomputer vision, while combining the knowledge of artificial intelligence and cognitivescience. It has the close relation with computer vision, artificial intelligence and cognitivescience, but it is independent of them. As the base of IU, object recognition has been appliedin many fields, such as identity determination, intelligent transport management, vehicledetection, etc. Object recognition aims to make computer capable of detecting visual image,recognizing object and classifying object in complex scene. At present, there are manymethods of object recognition, such as template matching, edge detection, statistic methodand so on. However, they lack of intelligence compared with biological visual system.
Since the1990s, Professor Shoujue Wang has studied the recognition process of human,and summarized the principle of continuity in homologous samples, called as the principle ofhomology—continuity. He applied this principle to pattern recognition and put forwardbiomimetic pattern recognition and the theory of Multi-Dimensional Space BiomimeticInformatics, which provides a new route for solving imagery thinking problems by computer.In this paper, based on the mechanism of biological visual system and combining the theoryof Multi-Dimensional Space Biomimetic Informatics, object classification and recognition inIU are studied, and the corresponding computer models are constructed. Several methods ofobject recognition are proposed for different scenes. Experimental results show the feature extracting model of object in complex scene and the method of biomimetic classification andrecognition proposed in this paper are effective and feasible.
(1) Based on the knowledge of neurobiology, the model of each cerebral regioninvolved in recognizing is established respectively and a biomimetic construction method ofcategory mental imagery based on the recognition mechanism of visual cortex of humanbrain is proposed. The model and algorithm are tested using training set and test setcomposed of real images. The results show that this method can establish valid deeprepresentation of these samples, based on which the biomimetic construction of categorymental imagery can be achieved.
(2) The mental imagery in psychology has strong comparability with cognitiveinformation processing. In this paper, mental imagery system is linked with visual cognitivesystem, and the activity status of cells in each brain region in recognition process is found. Itis considered that the establishment of mental imagery derives from the activity status ofmany nerve cells acquired in recognition process, which is the source and base of mentalimagery construction, called as imagery basis. By the activity status of cells and their modememory and analysis in depth, imagery basis is extracted.
(3) Combining the hot research results of neurobiology on visual cortex, the invariancein object recognition is introduced to determine the object category of deep presentation ofmental imagery. The shape tuning and category tuning characteristic of cells in ventral visualpathway are employed to weigh the specificity and invariance of visual cortex cells.
(4) Codebook multidimensional space is constructed using Bag of words model. Imagevectors are projected to sample points in Codebook multidimensional space. Based on theprinciple of homology continuity in multidimensional space biomimetic informatics, theoptimal classification of different kinds of objects in Codebook multidimensional space isobtained using neural network classifier. A biomimetic classification and recognition methodof specific object in complex scene is proposed. Experiments are performed to investigatethe factors influencing the performance of classifier and their variation. The experimentalresults obtained by this method are compared with those obtained by the traditional methods, and results show the method proposed in this paper is valid and feasible.
(5) The robust representation of image is established by Histogram of Oriented Gradient(HOG). According to the processing mechanism of human visual system and the theory ofmultidimensional space biomimetic informatics, two biomimetic classification andrecognition methods of human behavior are proposed, which are based on HOG+SVM andHOG+RBPNN respectively. The methods proposed in this paper are evaluated and comparedwith other commonly used methods. Results show that, for the classification and recognitionof human behavior in still image, the proposed methods have better performance inrecognizing different kinds of behavior, but the performance in recognizing similar behaviorsstill needs improvement.
To sum up, a biomimetic classification and recognition method of specific object incomplex scene is proposed based on the processing mechanism of human visual system andthe theory of multidimensional space biomimetic informatics, which can provide a referencefor the research on other object recognition methods and multidimensional space biomimeticinformatics.
自20世纪90年代开始，王守觉院士研究分析了人类认识事物的过程，总结出了同源样本的连续性规律，并称之为同源连续性原理，然后将此原理应用到模式识别中，提出了仿生模式识别方法，并由此形成了高维空间仿生信息学理论，该理论的提出为如何利用计算机解决形象思维问题开辟了一个新途径。本文从研究生物视觉系统的工作机理出发，结合王守觉院士关于高维空间仿生信息学的相关理论，构建相应的计算机模型，研究了图像理解中的目标识别与分类问题，针对不同场景提出了多种目标分类与识别方法。实验结果表明，本文提出的复杂场景中目标的特征提取模型以及在此基础上提出的仿生识别与分类方法有效可行。本文的主要工作总结如下。
（1）应用神经生物学知识，对物体识别中涉及的各个脑区分别建模，提出了一种基于视皮层不变性识别机制的类表象仿生构建方法；并利用真实图像组成的训练集和测试集对模型和算法进行测试。结果表明，该方法可以在这些样本上建立有效的深层表征并在其上完成类表象的构建。
（2）利用心理学中表象的形成与知觉信息处理过程具有很强相似性的特点，本文将表象系统与视知觉系统建立连接，找到识别活动中各层细胞的活动状态，认为表象的构建来源于识别活动中习得的多个神经元集群的活跃状态，并把其作为表象构建的来源和基础——表象基。通过对识别活动中视皮层各脑区细胞的活动状态进行分别建模，并在其上进行高层次的模式记忆和分析，实现了表象基的提取。
（3）结合神经生物学关于视皮层研究的最新成果，将物体识别中的不变性问题引入表象式深层表征的目标范畴确定中。利用腹部视觉通路中细胞的“形状调谐”以及“范畴调谐”的特点，对视皮层细胞的特异性和不变性进行了权衡。
（4）利用Bag of words模型构造了Codebook高维空间，利用高维形象几何理论，将图像向量映射成Codebook空间中的样本点，并根据仿生信息学的同源连续性原理，使用BP神经网络分类器找到不同类别目标在Codebook空间中的最佳划分，从而提出了一种复杂场景中特定目标的仿生识别与分类方法；并基于该方法设计了不含隐层和含有一个隐层的BP神经网络仿生分类器，通过实验探讨了影响分类器识别准确率的若干因素及其变化规律，并将本文方法与传统方法得到的实验结果进行对比，证明了论文中提出方法的有效性。
（5）在研究了人类视觉系统处理机制的基础上，首先利用方向梯度描述符（HOG）建立了图像的鲁棒表示；然后，根据人类视觉系统的并行处理机制和仿生信息学理论，提出了基于HOG+SVM和HOG+RBPNN的两种人体行为仿生识别与分类方法。利用针对识别与分类方法的评价指标对本文方法进行了评价，最后，与目前常用方法进行了比较，结果表明，在针对静态图像中人体行为的分类与识别效果方面，本文方法对差别较大的行为的识别效果好于常用方法，对相似行为的识别效果还有待于进一步提高。
综上所述，本文基于人类视觉系统和高维空间仿生信息学理论，提出的复杂场景中目标的仿生识别与分类算法，可为其他目标识别方法和高维空间仿生信息学的研究提供借鉴。
Image Understanding (IU) is to study images based on human knowledge, whichfocuses on what are objects in the image, the relationship between objects, what is scene inthe image and how to apply the scene. It mainly includes two parts: object classification andrecognition in a scene, and scene description and understanding. Object recognition has theinitiative and is the base of scene description and understanding, which is to make scene beexplained well. Scene description and understanding provide the apriori information forobject recognition, which can guide the object recognition. In essence, IU derives fromcomputer vision, while combining the knowledge of artificial intelligence and cognitivescience. It has the close relation with computer vision, artificial intelligence and cognitivescience, but it is independent of them. As the base of IU, object recognition has been appliedin many fields, such as identity determination, intelligent transport management, vehicledetection, etc. Object recognition aims to make computer capable of detecting visual image,recognizing object and classifying object in complex scene. At present, there are manymethods of object recognition, such as template matching, edge detection, statistic methodand so on. However, they lack of intelligence compared with biological visual system.
Since the1990s, Professor Shoujue Wang has studied the recognition process of human,and summarized the principle of continuity in homologous samples, called as the principle ofhomology—continuity. He applied this principle to pattern recognition and put forwardbiomimetic pattern recognition and the theory of Multi-Dimensional Space BiomimeticInformatics, which provides a new route for solving imagery thinking problems by computer.In this paper, based on the mechanism of biological visual system and combining the theoryof Multi-Dimensional Space Biomimetic Informatics, object classification and recognition inIU are studied, and the corresponding computer models are constructed. Several methods ofobject recognition are proposed for different scenes. Experimental results show the feature extracting model of object in complex scene and the method of biomimetic classification andrecognition proposed in this paper are effective and feasible.
(1) Based on the knowledge of neurobiology, the model of each cerebral regioninvolved in recognizing is established respectively and a biomimetic construction method ofcategory mental imagery based on the recognition mechanism of visual cortex of humanbrain is proposed. The model and algorithm are tested using training set and test setcomposed of real images. The results show that this method can establish valid deeprepresentation of these samples, based on which the biomimetic construction of categorymental imagery can be achieved.
(2) The mental imagery in psychology has strong comparability with cognitiveinformation processing. In this paper, mental imagery system is linked with visual cognitivesystem, and the activity status of cells in each brain region in recognition process is found. Itis considered that the establishment of mental imagery derives from the activity status ofmany nerve cells acquired in recognition process, which is the source and base of mentalimagery construction, called as imagery basis. By the activity status of cells and their modememory and analysis in depth, imagery basis is extracted.
(3) Combining the hot research results of neurobiology on visual cortex, the invariancein object recognition is introduced to determine the object category of deep presentation ofmental imagery. The shape tuning and category tuning characteristic of cells in ventral visualpathway are employed to weigh the specificity and invariance of visual cortex cells.
(4) Codebook multidimensional space is constructed using Bag of words model. Imagevectors are projected to sample points in Codebook multidimensional space. Based on theprinciple of homology continuity in multidimensional space biomimetic informatics, theoptimal classification of different kinds of objects in Codebook multidimensional space isobtained using neural network classifier. A biomimetic classification and recognition methodof specific object in complex scene is proposed. Experiments are performed to investigatethe factors influencing the performance of classifier and their variation. The experimentalresults obtained by this method are compared with those obtained by the traditional methods, and results show the method proposed in this paper is valid and feasible.
(5) The robust representation of image is established by Histogram of Oriented Gradient(HOG). According to the processing mechanism of human visual system and the theory ofmultidimensional space biomimetic informatics, two biomimetic classification andrecognition methods of human behavior are proposed, which are based on HOG+SVM andHOG+RBPNN respectively. The methods proposed in this paper are evaluated and comparedwith other commonly used methods. Results show that, for the classification and recognitionof human behavior in still image, the proposed methods have better performance inrecognizing different kinds of behavior, but the performance in recognizing similar behaviorsstill needs improvement.
To sum up, a biomimetic classification and recognition method of specific object incomplex scene is proposed based on the processing mechanism of human visual system andthe theory of multidimensional space biomimetic informatics, which can provide a referencefor the research on other object recognition methods and multidimensional space biomimeticinformatics.
引文
[1]张会章.基于视觉感知的图像理解方法研究[D].西安：西北工业大学计算机学院,2003.
[2] Hemrnna Kop-Borotsehnig, Axel Pinz. A new concept for active fusion in imageunderstanding applying fuzzy set theory[C]//Proceedings of the Fifth IEEEInternational Conference on Fuzzy Systems,1996,2:793-799.
[3]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社，2000.
[4] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[5] Stephen Se, David G Lowe, James J Little. Vision-based global localization andmapping for mobile robotics [J]. IEEE Transactions on Robotics,2005,21(3):364-375.
[6]艾海舟.图像处理、分析和机器视觉[M].北京：清华大学出版社.
[7] Tabatabaee H, Milani Fard A, Jafariani H. A novel human identifier system usingretina image and fuzzy clustering approach[C]//Proceedings of the2nd IEEEInternational Conference on Information and Communication Technologies(ICTTA'06), Damascus, Syria,2006:1031-1036.
[8]韩双焕.笔式用户界面中手势的可用性设计和识别研究[D].北京：中国科学院研究生院软件研究所,2005.
[9]张艳河.基于视觉感知的产品品牌个性识别研究[J].杭州：浙江大学计算机科学与技术学院,2008.
[10] Rosch E. Mervis C B. Family resemblances: Studies in the internal structure ofcategories [J]. Cognitive Psychology,1975,7:573-605.
[11]高依旻.网络科技用户的信息搜索行为研究[D].南京:南京理工大学,2004.
[12] Vailaya A, Figueiredo A, Jain A, et al. Image classification for content-basedindexing [J]. IEEE Transactions on Image Processing,2001,10(1):117-130.
[13]高隽,谢昭.图像理解理论和方法[M].北京:科学出版社,2009.
[14]章毓晋.图像工程[M].2版.北京:清华大学出版社,2007.
[15] Jain A K, Hong L, Bolle R. On-line fingerprint verification [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,1997,19(4):302-313.
[16]王守觉.仿生模式识别(拓扑模式识别)——一种模式识别新模型的理论与应用[J].电子学报,2002,30(10):1417-1420.
[17]王丹.多维多分辨仿生识别方法研究[D].长春:吉林大学生物与农业工程学院,2011.
[18]王守觉.高维空间仿生信息学入门[M].北京：国防工业出版社,2008.
[19] Jain K. Handbook of Face Recognition[M]. Springer, New York,2004.
[20] Maltoni D, Maio D, Jain A K, et al. Handbook of Fingerprint Recognition[M].Springer Verlag,2003.
[21]王素利.基于认知机理的智能造字之结构描述研究[J].广州：华南理工大学计算机科学与工程学院,2008.
[22] Ficarra E, Benini L, Macii E, et al. Automated DNA fragments recognition andsizing through AFM image processing [J]. IEEE Transactions on InformationTechnology in Biomedicine,2005,9(4):508-517.
[23] Zhang D, Shu W. Two novel characteristic in palmprint verification: datum pointinvariance and line matching [J]. Pattern Recognition,1999,32(4):691-702.
[24] Zhang D, Kong W K, You J, et al. Online palmprint identification[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(9):104-105.
[25]王惠锋,孙正兴,王箭.语义图像检索研究进展[J].计算机研究与发展，2002,39(5):513-524.
[26] Michelle R. Greene, Aude Oliva. Recognition of natural scenes from globalproperties: Seeing the forest without representing the trees [J]. CognitivePsychology,2009,58(2):137-176.
[27] Chang E, Goh K, Sychay G, et al. Cbsa: content-based soft annotation formultimodal image retrieval using bayes point machines, IEEE Transactions onCircuits and Systems for Video Technology Special Issue on Conceptual andDynamical Aspects of Multimedia Content Description,2006,13(1):26-38.
[28] Phillips P J, Moon H, Rizvi S A, et al. The FERET evaluation methodology forface-recognition algorithms [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,22(10):1090-1104.
[29]王树根.基于认知心理学的模式识别模型框架[J].武汉大学学报(信息科学版),2002,27(5):543-547.
[30] Yu S, Tan D, Tan T. A framework for evaluating the effect of view angle, clothingand carrying condition on gait recognition [C]. International Conference on PatternRecognition(ICPR'06),2006,4:441-444.
[31] Aran O, Akarun L. A multi-class classification strategy for Fisher scores:Application to signer independent sign language recognition [J]. PatternRecognition,2010,43:1776-1788
[32]罗云，章毓晋，高永英.基于分析的图像有意义区域提取[J].计算机学报,2000,23(12):1313-1319.
[33]席学强,王润生.一个针对遥感图像特定目标的自动识别系统[J].遥感技术与应用,2000,15(3):179-183.
[34] Zhao T, Liang Z H, Zhang D, et al. Interest filter vs. interest operator: Facerecognition using fisher linear discriminant based on interest filter representation[J]. Pattern Recognition Letters,2008,29(13):1849-1857.
[35] Jain A K, Prabhakar S, Hong L, et al. Filter bank-based fingerprint matching [J].IEEE Transaction on Image Processing,2000,9(5):846-859.
[36]杨国为,王守觉,刘扬阳.仿生模式识别的两个关键技术问题研究[J].电子学报,2008,32(12):2490-2492.
[37]邢延,张天序,复杂背景下基于知识的目标识别算法研究[J].模式识别与人工智能,1995,8(3):237-242.
[38]叶斌,彭嘉雄.基于结构特征的军用机场识别与理解[J].华中科技大学学报,2001,29(3):39-42.
[39] Shen J. Shepherd J, Ngu A H H. Semantic-sensitive classification for large imagelibraries[C]//In International Multimedia Modeling Conference, Melbourne,Australia,2005:340-345.
[40]吕颖达,申铉京,苗健,等.基于光源方向不一致性的局部光源图像盲鉴别方法[J].吉林大学学报:工学版,2010,40(6):1673-1677.
[41]钱乐乐.基于视觉层次感知机制的图像理解方法研究[J].合肥：合肥工业大学计算机与信息学院,2009.
[42] Wang Y, Chua C S, Ho Y K. Facial feature detection and face recognition from2Dand3D images [J]. Pattern Recognition Letter,2002,23(10):1191-1202.
[43] Meng J E, Chen W, Shi-qian W. High-speed face recognition based on discretecosine transform and RBF neural networks [J]. IEEE Transactions on NeuralNetworks,2005,16(3):679-691.
[44] Wang Shou-jue. A new development on ANN in china-biomimetic patternrecognition and multi-weight vector neurons [J]. Lecture Notes in ComputerScience Artificial Intelligence,2003(2639):35-43.
[45]徐蕾.仿生模式识别应用研究[D].青岛：中国海洋大学信息科学与工程学院,2008.
[46]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D].重庆:重庆大学自动化学院,2009.
[47]王志良,郑思仪,王先梅,等.心理认知计算的研究现状及发展趋势[D].模式识别与人工智能,2011,24(2):215-225.
[48]来疆亮.模式识别中高维空间点分布几何分析方法的研究[D].北京:中国科学院半导体研究所，2005.
[49] Daugman J, Machine S, Li Z A. Face and gesture recognition: overview[J]. IEEETransactions on Pattern Analysis Intelligence,1997,19(7):675-676.
[50]陈嘉威.视觉注意计算模型的研究及其应用[J].厦门:厦门大学信息科学与技术学院,2009.
[51] Cao Wen-ming, Hao Feng, Wang Shou-jue. The application of DBF neuralnetworks for objection recognition [J]. Information Sciences,2004,160(3):153-160.
[52] Do M N, Vetterli M. The contourlet transform: an efficient directionalmultiresolution image representation [J]. IEEE Transactions Image on Processing,2005,14(12),2091-2106.
[53] Do M N, Vetterli M. The finite ridgelet transform for image representation [J].IEEE Transactions on Image Processing,2003,12(1),16-28.
[54] Pennec E Le, Mallat S. Sparse geometric image representations with bandelets[J].Processing of Transactions on Image Processing,2005,14(4):423-438,.
[55]肖潇.高维空间几何复杂体理论的研究及其在人脸识别中的应用[D].杭州:浙江工业大学信息工程学院,2008.
[56] Ma L, Tan T, Wang Y, et al. Efficient iris recognition by characterizing key localvariations[J]. IEEE Transactions on Image Processing,2004,13(6):739-750.
[57] Ivins J P, Porrill J, Frisby J P. A deformable model of the human iris driven bynon-linearleast-squares minimisation[C]. The6th International Conference onImage Processing and its Applications,1997,1(14-17),234-238.
[58]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报,2003,31(12A):1975-1981.
[59]李倩,邓浩江,王守觉.一种可识别样本中共同抽象特征的神经网络[J].电子学报,2001,29(8):1028-1031.
[60] Cao Wen-ming, Wang Shou-jue, Feng Hao. Approximation with direction basisfunction neural networks[J]. IEEE Region10Annual International Conferences,Proceedings/TENCON,2002,1290-1293.
[61]易楠,陈旭.基于仿生模式识别的人脸识别系统的研究[J].微计算机信息,2010,26(8):172-173.
[62] Yuan Xiao-yan, Shi Peng-fei. A non-linear normalization model for irisrecognition[R]. Lecture Notes in Computer Science, Springer Berlin/Heidelberg,2005,3781:135-141.
[63] Wei Zhuo-shi, TanTie-niu, Sun Zhen-an. Nonlinear iris deformation correctionbased on Gaussian model[R]. Lecture Notes in Computer Science, Springer BerlinHeidelberg,2007,4642:780-790.
[64]王改良,武妍.基于仿生模式识别理论的声调识别[J].计算机应用,2010,30(10):2709-2711.
[65]赵莹，高隽，汪荣贵,等.一种新的基于仿生模式识别的广义最近邻方法[J].电子学报，2004,32(增刊):196-198.
[66]叶虹.基于高维空间点覆盖理论非特定人问候语的语音识别[D].杭州:浙江工业大学信息工程学院,2005.
[67]杨谦,齐翔林,汪云九.简单细胞方位选择性感受野组织形成的神经网络模型[J].中国科学(C辑),2000,30(4):412-420.
[68]傅光磊.基于语义绑定的分层视觉词汇库的图像理解算法研究[D].上海:上海交通大学信息安全工程学院,2010.
[69] Riesenhuber M, Poggio T. Neural mechanisms of object recognition [J]. CurrentOpinion in Neurobiology,2002,12(2):162-168.
[70] Thomas Serre, Lior Wolf, Stanley Bileschi. et al. Robust object recognition withcortex-like mechanisms [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(3):411-426.
[71] Jim Mutch, David G Lowe. Multiclass object recognition with sparse, localizedfeatures [J]. In Proceedings of the2006IEEE Conference on CVPR,2006,1:1-18.
[72] Rao P N, Ballard D H. Dynamic model of visual recognition predicts neuralresponse erties in the visual cortex [J]. Neural Computation,1997,9(4):721-763.
[73]谢昭.图像理解的关键问题和方法研究[D].合肥：合肥工业大学计算机与信息学院,2007.
[74] Deco C, Schurmann B. A hierarchical neural system with attentional top-downenhancement of the spatial resolution for object recognition [J]. Vision Research,2000,40:2845-2859.
[75]危辉.一个关于视知觉不变性的层次网络表示与计算模型[J].小型微型计算机系统,2003,24(7):1280-1284.
[76]危辉,架尚敏.基于连通结构与动力学过程的知觉记忆层次模型[J].软件学报,2004,15(11):1616-1628.
[77] Epshtein B, Ullman S. Feature hierarchies for object classification[C]. Proceedingsof2005IEEE International Conference on Computer Vision,2005,1:220-227.
[78] Dileep George, Jei Hawkins. A hierarchical Bayesian model of invariant patternrecognition in the visual cortex[C]. Proceedings of2005IEEE International JointConference on Neural Networks,2005,3:1812-1817.
[79] Callaway E M. Feedforward, feedback and inhibitory connections in primate visualcortex [J]. Neural Networks,2004,17(5-6):625-632.
[80] Grossberg S, Swaminathan G. A laminar cortical model for3D perception ofslanted and curved surface and of2D images: development, attention, andbistability [J]. Vision Research,2004,44(11):1147-1187.
[81]汪云九.神经信息学-神经系统的理论和模型[M].北京:高等教育出版社,2007.
[82] Gilbert C D, Sigman M, and Crist R E. The neural basis of perceptual learning.Neuron,2001,31(5):681-697.
[83] Do M N, Vetterli M. Framing pyramids [J]. IEEE Transactions on Signalprocessing,2003,51(9):2329-2342.
[84]刘萍萍,赵宏伟,耿庆田,等.基于局部特征和视皮层识别机制的图像分类[J].吉林大学学报:工学版,2011,41(5):1401-1406.
[85]赵宏伟,王慧,刘萍萍,等.基于视中枢神经机制的视觉信息处理模型[J].吉林大学学报:工学版,2008,38(增刊2):158-161.
[86]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[D].长春:吉林大学计算机科学与技术学院,2010.
[87]韩东峰.图像分类识别中特征及模型的若干问题研究[D].长春:吉林大学计算机科学与技术学院,2008.
[88] Li S, Kwok J T, Zhu H, et al. Texture classification using the support machines [J].Pattern Recognition,2003,36:2883-2893.
[89] Kim K I, Jung K, Park S H, et al. Support vector machines for textureclassification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(11):2883-2893.
[90] Qin X, Yang Y. Simiarity measure and learning with gray level aura matrices(GLAM)for texture image retrieval[C]. Proceedings of IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2004,1:326-333.
[91]陆飞.仿生模式识别的几何学习算法理论的研究[D].杭州:浙江工业大学信息工程学院,2006.
[92]何振亚.多维数字信号处理[M].北京:国防工业出版社,1995.
[93]刘萍萍.图像的局部不变性特征方法研究[D].长春:吉林大学计算机科学与技术学院,2009.
[94] Michael Tye. The Imagery Debate[D]. Cambridge: MIT Press, USA,1991.
[95] Kosslyn S M. The cognitive neuroscience of mental imagery[J]. Neuropsychologia,1995,33:1335–1344.
[96] Kosslyn S M, Shwartz S P. A simulation of visual imagery[J]. Cognitive Science,1977,1:265–295.
[97] Ganis G, Thompson W L, Kosslyn S M. Brain areas underlying visual mentalimagery and visual perception: An FMRI study[J]. Cognitive Brain Research,2004,20,226–241.
[98] Barkowsky T, Bertel S, Engel D, Freksa C. Design of an architecture for reasoningwith mental images[C]. Proceedings of the International Workshop on Spatial andVisual Components in Mental Reasoning about Large-Scale Spaces, BadZwischenahn, Germany,2003.
[99]余波,张立明.基于初级视觉皮层的图像匹配模型[J].生物物理学报,1999,15(1):104–111.
[100]危辉,何新贵.表象式直接知识表示[J].计算机学报,2001,24,891–896.
[101]危辉,潘云鹤.形象思维的视表象基础[J].浙江大学学报(工学版),2001,35(2):152–156.
[102] Cao W M, Hao F. Biomimetic pattern recognition based on the Young-Helmholtzmodel of multispectral image[C].2009International Conference on ArtificialIntelligence and Computational Intelligence, Shanghai, China,2009,398-402.
[103] Li S, Qi X L, Hu H H, Wang Y J. synchronous oscillation of neural network modelof functional column[J]. Scientia Sinica Vitae,2004,34:385–394.
[104]王守觉,曲延锋,李卫军,等.基于仿生模式识别与传统模式识别的人脸识别效果比较研究[J].电子学报,2004,32(7):1057–1061.
[105] Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex[J].Nature Neuroscience,1999,2:1019–1025.
[106] David I Perrett, Oram M W. Neurophysiology of shape processing[J]. Image VisionComputing,1993,11:317–333.
[107] Zhang Xiang-he, Wang Dan, Ren Lu-quan, Liu Ping-ping. Biomimetic constructionof category mental imagery based on recognition mechanism of visual cortex ofhuman brain[J]. Journal of Bionic Engineering,2010,7(Suppl.): S238-S244.
[108] Daugman J G. Uncertainty relations for resolution in space, spatial frequency, andorientation optimized by two-dimensional visual cortical filters[J]. Journal of theOptical Society of America A,1985,2:1160–1169.
[109] Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functionalarchitecture in the cat’s visual cortex[J]. Journal of Physiology,1962,160:106–154.
[110] Griffin G, Holub A D, Perona P. The Caltech-256, Caltech TechnicalReport[DB/OL]. http://www.vision. caltech.edu/Image_Datasets/Caltech256/
[111] Grigorescu C, Petkov N, Westenberg M A. Contour detection based on nonclassicalreceptive field inhibition[C]. IEEE Transactions on Image Processing,2003,12,729–739.
[112] Serre Thomas, Wolf Lior, Bileschi Stanley. Robust object recognition withcortex-like mechanisms[J]. IEEE Tractions on Pattern Analysis and MachineIntelligence,2007,29(3):411-426.
[113]谭伟恒,申铉京,杨金峰.基于人体定位和动态肤色阈值的肤色检测算法[J].仪器仪表学报,29(1):115-119.
[114] Holub A, Welling M, Perona P. Exploiting unla-belled data for hybrid objectclassification[C].In NIPS Workshop on Inter-Class Transfer, Whistler,2005.
[115] Berg A C, Berg T L, Malik J. Shape matching and object recognition using lowdistortion correspondence[C]. IEEE Computer Society, Washington DC, USA,2005.
[116] Li Fei-fei, Pietro Perona. A Bayesian hierarchical model for learning natural scenecategories[C]//IEEE Computer Society Conference on Computer Vision and PatternRecognition,2005.
[117] Russell B C, Sivic J, Efros A A, et al. Discovering objects and their location inimages[C].Tenth IEEE International Conference on Computer Vision,2005.
[118]李远宁,刘汀,蒋树强,等.基于“Bag of words”的视频匹配方法[J].通信学报,2007,28(12):147-151.
[119]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电了学报，2006,34(1):155-158.
[120]王守觉,徐健,王宪保,等.基于仿生模式识别的多镜头人脸身份确认系统研究[J].电子学报,2002,30(1),1-3.
[121]王志海,赵占强,王守觉.仿生模式识别在单镜头人脸识别中的应用[J].模式识别与人工智能,2004,17(1):98-102.
[122]潘晓霞.基于高维空间覆盖方法的非特定人连续数字语音识别的研究[D].杭州:浙江工业大学信息工程学院,2004.
[123]胡建慧.基于仿生模式识别的虹膜识别算法研究[D].杭州：浙江工业大学信息工程学院，2006.
[124]张祥合,王丹,任露泉,等.基于高维空间仿生信息学的目标识别新算法[D].吉林大学学报:工学版,2011,41(增刊2):269-274.
[125]苏谦,邬文锦,王红武,等.基于近红外光谱和仿生模式识别玉米品种快速鉴别方法[J].光谱学与光谱分析,2009,29(9):2413-2416.
[126] Wu L L, Wang S J. Study on closed-set speaker identification based on biomimeticpattern recognition [J]. Chinese Journal of Electronics,2009,18,259-261.
[127]满彩岩.智能视频监控中的人体运动分析及关键技术研究[D].长春:计算机科学与技术学院,2009.
[128] Park C H, Lee J J, Oh S K. Iris feature extraction and matching based on multiscaleand directional image representation[C]. Scale Space Methods in Computer Vision,Proceedings, Berlin: Springer-Verlag Berlin,2003:576-583.
[129] Bar-Hillel A, Weinshall D. Efficient learning of relational object class models [J].International Journal of Computer Vision,2008,77(1):175–198,.
[130] Bernstein E, Amit Y. Part-based statistical models for object classification anddetection[C]. IEEE Conference on Computer Vision and Pattern Recognition,2005.
[131]燕忠,袁春伟.基于蚁群智能和支持向量机的人脸性别识别方法[J].电子与信息学报,2004,26(8):1177-1182.
[132]安冬,王守觉.基于仿生模式识别和PCA/ICA的DOA估计方法[J].电子学报,2004,(09):1448-1451.
[133]王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法[J].计算机学报,2005,(10):1657-1663.
[134] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C].2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1,886-893.
[135] Mikolajczyk Krystian, Schmid Cordelia. Scale and affine invariant interest pointdetectors [J]. International Journal of Computer Vision,2004,60(1):63-86.
[136] Mikolajcryk Krystian, Schmid Cordelia. A performance evaluation of localdescriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[137]张有正.基于双权值神经网络的逼近性及其应用[J].杭州:浙江工业大学信息工程学院,2006.
[138]梁路宏,艾海舟,何克忠,等.基于多关联模板匹配的人脸检测[J].软件学报,2001,12(1):92-102.
[139] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measure withclassification based on feature distribution [J]. Pattern Recognition,1996,29(1):51-59.
[140]胡斓,夏利民.基于Boosting RBF神经网络的人脸年龄估计[J].计算机工程,2006,32(19):119-201.
[141] Sammal A, Subramani V, Marx D. Analysis of sexual dimorphism in human face[J]. Journal of Visual Communication&Image Representation,2007(8):453-463.
[142] Brasnert P, Mihaylova L, Bull D, et al. Sequential Monte Carlo tracking by cues invideo sequences [J]. Image and Vision Computing,2007(25):1217-1227.
[143]工俊明,陈世旺.渐进背景影像的建构[J].国立台湾师范人学学报:数理与利技类,2002,47(21):43-54.
[144] Wang Tie-sheng, Gu I Y H, Khan Z H. Adaptive particle filters for visual objecttracking using joint PCA appearance model and consensus pointcorrespondences[C]. IEEE International Conference on Multimedia and Expo,2009:1370-1373.
[145]申若虹.模式识别中基于概率统计的Bayer算法分析[J].机械工程与自动化,2010(6):48-49.
[146] Yang Z, Li M, Ai H. An experimental study on automatic face genderclassification[C]. In Proceeding of the18th IEEE International Conference onPattern Recognition (ICPR'06),2006,3:1099-1102.
[147] Bray M, Meier E Koller, Gool L Van. Smart particle filtering for high-dimensionaltracking [J]. Computer Vision and Image Understanding,2007,106(1):116-129.
[148] Fahed Abdallah, Amadou Gning, Philippe Bonnifait. Box particle filtering fornonlinear state estimation using interval analysis [J]. Automatica,2008,44(3):807-815.
[149] Tan Hua-chun, Zhang Yu-jin. Detecting eye blink states by tracking iris and eyelids[J]. Pattern Recognition Letters,2006,27(6):667-675.
[150]张骏. Boosting方法及其在图像理解中的应用研究[D].合肥：合肥工业大学计算机与信息学院,2009.
[151]王丹，张祥合，张立，等.多维多分辨仿生识别方法及其应用[J].吉林大学学报:工学版,2011,41(2):408-412.
[152] Xie Shu-fu, Shan Shi-guang, Chen Xi-lin, et al. V-LGBP: Volume Binarv Patternsfor Face Representation and Recognition[C]. International Conference on PatternRecognition,2008. Florida, USA Based Local Gabor.(Oral).
[153]任明武.数字图像处理[M].南京:南京理工大学出版社,2003.
[154] Park Young Kyung, Park Seok Lai, Kim Joong Kyu. Retinex method based onadaptive smoothing for illumination invariant face recognition[J]. SignalProcessing,2008,88:1929-1945.
[155] Liyanage C, Silva De, Liu Jing, et al. Multimodal approach to human face detectionand tracking[J]. IEEE Transactions on Industrial Electronics,2008,55(3):1385-1392.
[156] Kazuhiro Hotta. Robust face recognition under partial occlusion based on supportvector machine with local Gaussian summation kernel [J]. Image and VisionComputing,2008,26:1490-1498.
[157]周书仁,梁昔明,朱灿,等.基于ICA与HMM的表情识别[J].中国图象图形学报,2008,13(12):2321-2328.
[158]徐光祐,曹媛媛.动作识别与行为理解综述[J].中国图象图形学报,2009,14(2):189-195.
[159] Bray M, MeierE Koller, Gool L Van. Smart particle filtering for high-dimensionaltracking. Computer Vision and Image Understanding,2007,106(1):116-129.
[160] Felzenszwalb P, Huttenlocher D. Pictorial structures for object recognition [J].International Journal of Computer Vision,2005,61(1):55-79.
[161]李鑫.基于生物视觉机理的直线图形认知系统研究[D].长春:吉林大学计算机科学与技术学院,2007.
[162]邱雪娜.基于视觉的运动目标跟踪算法及其在移动机器人中的应用[D].华东理工大学信息科学与工程学院,2011.
[163] Harzallah H, Jurie F, Schmid C. Combining efficient object localization and imageclassification [C]. In IEEE Conference on Computer Vision,2009.
[164] Moeslund T B, Hilton A, Kruger V. A survey of advances in vision-based humanmotion capture and analysis [J]. Computer Vision and Image Understanding,2006,103(2-3):90-126.
[165]胡良梅.基于信息融合的图像理解方法研究[D].合肥：合肥工业大学计算机与信息学院,2006.
[166]李文艳.基于视觉注意的目标检测方法[D].重庆:重庆大学自动化学院,2009.
[167] Yao Bang-peng, Li Fei-fei. Grouplet: A structured image representation forrecognizing human and object interactions [C]. IEEE Conference on ComputerVision and Pattern Recognition,2010.
[168] Yao Bang-peng, Li Fei-fei. Modeling mutual context of object and human pose inhuman object interaction activities [C]. IEEE Conference on Computer Vision andPattern Recognition,2010.
[169]彭素静.基于视觉感知机理的显著区域研究[D].重庆:重庆大学自动化学院,2009.
[170] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels forclassification of texture and object categories: a comprehensive study[J].International Journal of Computer Vision,2007,73(2):213-238.
[171] Cootes T, Edwards G, Taylor C. Active appearance models [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2001，23(6):681-685.
[172]刘晓山.光照变化条件下人脸识别技术研究[D].广州:华南理工大学计算机科学与工程学院,2011.
[173] Felzenszwalb P, McAllester D. The generalized architecture [J]. Journal ofArtificial Intelligence Research,2007,29:153-190.
[174] Leibe B, Leonardis A, Schiele B. Robust object detection with interleavedcategorization and segmentation [J]. International Journal of Computer Vision,2008,77(1):259-289.
[175]傅晓英.基于半连接HMM模型的人体行为识别研究与实现[D].北京:北京交通大学计算机与信息技术学院,2009.
[176]武松林.基于坐姿的多人行为识别与分析方法研究[D].延吉:延边大学工学院,2010.
[177]秦锋,罗慧,程泽凯,等.一种新的基于AUC的多类分类评估方法[J].计算机工程与应用,2008,44(5):194-196.
[178] Torralba A. Contextual priming for object detection [J]. International Journal ofComputer Vision,2003,53(2):169–191.
[179]陈薇薇.基于人类视觉系统生理特性的模型及应用研究[D].长沙：国防科学技术大学,2004.
[180]吴田富.视觉选择性注意机制计算模型及其在物体识别中的应用[D.]合肥：合肥工业大学计算机与信息学院,2005.
[181]侯志强,韩崇昭.基于像素灰度归类的背景重构算法[J].软件学报,2005,16(9):1569-1576.
[182] Smal I, Draegestein K, Galjart N, et al. Particle filtering for multiple object trackingin dynamic fluorescence microscopy images: application to microtubule growthanalysis[J]. IEEE Trans Med Imaging,2008,27(6):789-804.
[183]皮文凯,刘宏,查红彬.基于自适应背景模型的全方位视觉人体运动检测[J].北京大学学报:自然科学版,2004,40(3):458-464.
[184]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[185] Wang S J, Chen X, Qin H, et al. Double synaptic weight neuron theory and itsapplication[C]. International Conference on Advances in Natural Computation,Changsha, China,2005,264-272.
[186] Weber M, Welling M, Perona P. Towards automatic discovery of objectcategories[C]. IEEE Conference on Computer Vision and Pattern Recognition,2000.
[187] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels forclassification of texture and object categories: A comprehensive study [J].International Journal of Computer Vision,2007,73(2):213–238.
[188]谭菊.基于视觉感知的目标特性分析[D]重庆:重庆大学自动化学院,2010.
[189]李新.面向神经计算的视觉信息处理研究[D].西安：西北工业大学计算机学院,2003.
[190]陈礼.视觉注意模型的研究及其在ROI图像压缩上的应用[D].重庆:重庆大学自动化学院,2008.
[191]凌志刚,赵春晖,梁彦,等.基于视觉的人行为理解综述[J].计算机应用研究,2008,25(9):2570-2578.
[192]王超.基于视觉分析的水下报警算法研究[D].大连:大连海事大学信息科学技术学院,2009.
[193]李军令.基于视中枢神经机制的视觉信息处理模型研究[D].长春:吉林大学计算机科学与技术学院,2008.
[194] Felzenszwalb P, Girshick R, McAllester D, et al. Object detection withdiscriminatively trained part based models [C]. IEEE Transactions on PatternAnalysis and Machine Intelligence,2009.
[195] Gupta A, Kembhavi A, Davis L S. Observing human-object interactions: Usingspatial and functional compatibility for recognition [C]. IEEE Transactions onPattern Analysis and Machine Intelligence,2009,31(10):1775-1789.
[196]陈媛媛.图像显著区域提取及其在图像检索中的应用[D].上海:上海交通大学信息安全工程学院,2006.
[197]张仁俊.视皮层细胞特征检测研究[D].长春:吉林大学计算机科学与技术学院,2008.
[198] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. InCVPR,2005:886–893.
[199]姜夕凯,苏松志,李绍滋,等.基于单张静态图像的人体行为识别方法综述[J].漳州师范学院学报(自然科学版),2011(4):23-26.
[200]王江涛.基于视频的目标检测、跟踪及其行为识别研究[D].南京:南京理工大学计算机科学与技术学院，2008.
[201]凌志刚,赵春晖,梁彦,等.基于视觉的人行为理解综述[J].计算机应用研究,2008,25(9):2570-2578.
[202] Ikizler N, Cinbis R G, Pehlivan S, et al. Recognizing Actions from Still Images[C].19th International Conference on Pattern Recognition (ICPR),2008:1-4.
[203] Yang Wei-long, Wang Yang, Mori Greg, et al. Recognizing Human Actions fromStill Images with Latent Poses[C].2010IEEE Conference on Computer Vision andPattern Recognition (CVPR),2010:2030-2037.
[204] Delaitre V, Laptev I, Sivic J. Recognizing human actions in still images: a study ofbag-of-features and part-based representations[C]. Proceedings of the BritishMachine Vision Conference,2010:1-11.
[2] Hemrnna Kop-Borotsehnig, Axel Pinz. A new concept for active fusion in imageunderstanding applying fuzzy set theory[C]//Proceedings of the Fifth IEEEInternational Conference on Fuzzy Systems,1996,2:793-799.
[3]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社，2000.
[4] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[5] Stephen Se, David G Lowe, James J Little. Vision-based global localization andmapping for mobile robotics [J]. IEEE Transactions on Robotics,2005,21(3):364-375.
[6]艾海舟.图像处理、分析和机器视觉[M].北京：清华大学出版社.
[7] Tabatabaee H, Milani Fard A, Jafariani H. A novel human identifier system usingretina image and fuzzy clustering approach[C]//Proceedings of the2nd IEEEInternational Conference on Information and Communication Technologies(ICTTA'06), Damascus, Syria,2006:1031-1036.
[8]韩双焕.笔式用户界面中手势的可用性设计和识别研究[D].北京：中国科学院研究生院软件研究所,2005.
[9]张艳河.基于视觉感知的产品品牌个性识别研究[J].杭州：浙江大学计算机科学与技术学院,2008.
[10] Rosch E. Mervis C B. Family resemblances: Studies in the internal structure ofcategories [J]. Cognitive Psychology,1975,7:573-605.
[11]高依旻.网络科技用户的信息搜索行为研究[D].南京:南京理工大学,2004.
[12] Vailaya A, Figueiredo A, Jain A, et al. Image classification for content-basedindexing [J]. IEEE Transactions on Image Processing,2001,10(1):117-130.
[13]高隽,谢昭.图像理解理论和方法[M].北京:科学出版社,2009.
[14]章毓晋.图像工程[M].2版.北京:清华大学出版社,2007.
[15] Jain A K, Hong L, Bolle R. On-line fingerprint verification [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,1997,19(4):302-313.
[16]王守觉.仿生模式识别(拓扑模式识别)——一种模式识别新模型的理论与应用[J].电子学报,2002,30(10):1417-1420.
[17]王丹.多维多分辨仿生识别方法研究[D].长春:吉林大学生物与农业工程学院,2011.
[18]王守觉.高维空间仿生信息学入门[M].北京：国防工业出版社,2008.
[19] Jain K. Handbook of Face Recognition[M]. Springer, New York,2004.
[20] Maltoni D, Maio D, Jain A K, et al. Handbook of Fingerprint Recognition[M].Springer Verlag,2003.
[21]王素利.基于认知机理的智能造字之结构描述研究[J].广州：华南理工大学计算机科学与工程学院,2008.
[22] Ficarra E, Benini L, Macii E, et al. Automated DNA fragments recognition andsizing through AFM image processing [J]. IEEE Transactions on InformationTechnology in Biomedicine,2005,9(4):508-517.
[23] Zhang D, Shu W. Two novel characteristic in palmprint verification: datum pointinvariance and line matching [J]. Pattern Recognition,1999,32(4):691-702.
[24] Zhang D, Kong W K, You J, et al. Online palmprint identification[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2003,25(9):104-105.
[25]王惠锋,孙正兴,王箭.语义图像检索研究进展[J].计算机研究与发展，2002,39(5):513-524.
[26] Michelle R. Greene, Aude Oliva. Recognition of natural scenes from globalproperties: Seeing the forest without representing the trees [J]. CognitivePsychology,2009,58(2):137-176.
[27] Chang E, Goh K, Sychay G, et al. Cbsa: content-based soft annotation formultimodal image retrieval using bayes point machines, IEEE Transactions onCircuits and Systems for Video Technology Special Issue on Conceptual andDynamical Aspects of Multimedia Content Description,2006,13(1):26-38.
[28] Phillips P J, Moon H, Rizvi S A, et al. The FERET evaluation methodology forface-recognition algorithms [J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,22(10):1090-1104.
[29]王树根.基于认知心理学的模式识别模型框架[J].武汉大学学报(信息科学版),2002,27(5):543-547.
[30] Yu S, Tan D, Tan T. A framework for evaluating the effect of view angle, clothingand carrying condition on gait recognition [C]. International Conference on PatternRecognition(ICPR'06),2006,4:441-444.
[31] Aran O, Akarun L. A multi-class classification strategy for Fisher scores:Application to signer independent sign language recognition [J]. PatternRecognition,2010,43:1776-1788
[32]罗云，章毓晋，高永英.基于分析的图像有意义区域提取[J].计算机学报,2000,23(12):1313-1319.
[33]席学强,王润生.一个针对遥感图像特定目标的自动识别系统[J].遥感技术与应用,2000,15(3):179-183.
[34] Zhao T, Liang Z H, Zhang D, et al. Interest filter vs. interest operator: Facerecognition using fisher linear discriminant based on interest filter representation[J]. Pattern Recognition Letters,2008,29(13):1849-1857.
[35] Jain A K, Prabhakar S, Hong L, et al. Filter bank-based fingerprint matching [J].IEEE Transaction on Image Processing,2000,9(5):846-859.
[36]杨国为,王守觉,刘扬阳.仿生模式识别的两个关键技术问题研究[J].电子学报,2008,32(12):2490-2492.
[37]邢延,张天序,复杂背景下基于知识的目标识别算法研究[J].模式识别与人工智能,1995,8(3):237-242.
[38]叶斌,彭嘉雄.基于结构特征的军用机场识别与理解[J].华中科技大学学报,2001,29(3):39-42.
[39] Shen J. Shepherd J, Ngu A H H. Semantic-sensitive classification for large imagelibraries[C]//In International Multimedia Modeling Conference, Melbourne,Australia,2005:340-345.
[40]吕颖达,申铉京,苗健,等.基于光源方向不一致性的局部光源图像盲鉴别方法[J].吉林大学学报:工学版,2010,40(6):1673-1677.
[41]钱乐乐.基于视觉层次感知机制的图像理解方法研究[J].合肥：合肥工业大学计算机与信息学院,2009.
[42] Wang Y, Chua C S, Ho Y K. Facial feature detection and face recognition from2Dand3D images [J]. Pattern Recognition Letter,2002,23(10):1191-1202.
[43] Meng J E, Chen W, Shi-qian W. High-speed face recognition based on discretecosine transform and RBF neural networks [J]. IEEE Transactions on NeuralNetworks,2005,16(3):679-691.
[44] Wang Shou-jue. A new development on ANN in china-biomimetic patternrecognition and multi-weight vector neurons [J]. Lecture Notes in ComputerScience Artificial Intelligence,2003(2639):35-43.
[45]徐蕾.仿生模式识别应用研究[D].青岛：中国海洋大学信息科学与工程学院,2008.
[46]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D].重庆:重庆大学自动化学院,2009.
[47]王志良,郑思仪,王先梅,等.心理认知计算的研究现状及发展趋势[D].模式识别与人工智能,2011,24(2):215-225.
[48]来疆亮.模式识别中高维空间点分布几何分析方法的研究[D].北京:中国科学院半导体研究所，2005.
[49] Daugman J, Machine S, Li Z A. Face and gesture recognition: overview[J]. IEEETransactions on Pattern Analysis Intelligence,1997,19(7):675-676.
[50]陈嘉威.视觉注意计算模型的研究及其应用[J].厦门:厦门大学信息科学与技术学院,2009.
[51] Cao Wen-ming, Hao Feng, Wang Shou-jue. The application of DBF neuralnetworks for objection recognition [J]. Information Sciences,2004,160(3):153-160.
[52] Do M N, Vetterli M. The contourlet transform: an efficient directionalmultiresolution image representation [J]. IEEE Transactions Image on Processing,2005,14(12),2091-2106.
[53] Do M N, Vetterli M. The finite ridgelet transform for image representation [J].IEEE Transactions on Image Processing,2003,12(1),16-28.
[54] Pennec E Le, Mallat S. Sparse geometric image representations with bandelets[J].Processing of Transactions on Image Processing,2005,14(4):423-438,.
[55]肖潇.高维空间几何复杂体理论的研究及其在人脸识别中的应用[D].杭州:浙江工业大学信息工程学院,2008.
[56] Ma L, Tan T, Wang Y, et al. Efficient iris recognition by characterizing key localvariations[J]. IEEE Transactions on Image Processing,2004,13(6):739-750.
[57] Ivins J P, Porrill J, Frisby J P. A deformable model of the human iris driven bynon-linearleast-squares minimisation[C]. The6th International Conference onImage Processing and its Applications,1997,1(14-17),234-238.
[58]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报,2003,31(12A):1975-1981.
[59]李倩,邓浩江,王守觉.一种可识别样本中共同抽象特征的神经网络[J].电子学报,2001,29(8):1028-1031.
[60] Cao Wen-ming, Wang Shou-jue, Feng Hao. Approximation with direction basisfunction neural networks[J]. IEEE Region10Annual International Conferences,Proceedings/TENCON,2002,1290-1293.
[61]易楠,陈旭.基于仿生模式识别的人脸识别系统的研究[J].微计算机信息,2010,26(8):172-173.
[62] Yuan Xiao-yan, Shi Peng-fei. A non-linear normalization model for irisrecognition[R]. Lecture Notes in Computer Science, Springer Berlin/Heidelberg,2005,3781:135-141.
[63] Wei Zhuo-shi, TanTie-niu, Sun Zhen-an. Nonlinear iris deformation correctionbased on Gaussian model[R]. Lecture Notes in Computer Science, Springer BerlinHeidelberg,2007,4642:780-790.
[64]王改良,武妍.基于仿生模式识别理论的声调识别[J].计算机应用,2010,30(10):2709-2711.
[65]赵莹，高隽，汪荣贵,等.一种新的基于仿生模式识别的广义最近邻方法[J].电子学报，2004,32(增刊):196-198.
[66]叶虹.基于高维空间点覆盖理论非特定人问候语的语音识别[D].杭州:浙江工业大学信息工程学院,2005.
[67]杨谦,齐翔林,汪云九.简单细胞方位选择性感受野组织形成的神经网络模型[J].中国科学(C辑),2000,30(4):412-420.
[68]傅光磊.基于语义绑定的分层视觉词汇库的图像理解算法研究[D].上海:上海交通大学信息安全工程学院,2010.
[69] Riesenhuber M, Poggio T. Neural mechanisms of object recognition [J]. CurrentOpinion in Neurobiology,2002,12(2):162-168.
[70] Thomas Serre, Lior Wolf, Stanley Bileschi. et al. Robust object recognition withcortex-like mechanisms [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(3):411-426.
[71] Jim Mutch, David G Lowe. Multiclass object recognition with sparse, localizedfeatures [J]. In Proceedings of the2006IEEE Conference on CVPR,2006,1:1-18.
[72] Rao P N, Ballard D H. Dynamic model of visual recognition predicts neuralresponse erties in the visual cortex [J]. Neural Computation,1997,9(4):721-763.
[73]谢昭.图像理解的关键问题和方法研究[D].合肥：合肥工业大学计算机与信息学院,2007.
[74] Deco C, Schurmann B. A hierarchical neural system with attentional top-downenhancement of the spatial resolution for object recognition [J]. Vision Research,2000,40:2845-2859.
[75]危辉.一个关于视知觉不变性的层次网络表示与计算模型[J].小型微型计算机系统,2003,24(7):1280-1284.
[76]危辉,架尚敏.基于连通结构与动力学过程的知觉记忆层次模型[J].软件学报,2004,15(11):1616-1628.
[77] Epshtein B, Ullman S. Feature hierarchies for object classification[C]. Proceedingsof2005IEEE International Conference on Computer Vision,2005,1:220-227.
[78] Dileep George, Jei Hawkins. A hierarchical Bayesian model of invariant patternrecognition in the visual cortex[C]. Proceedings of2005IEEE International JointConference on Neural Networks,2005,3:1812-1817.
[79] Callaway E M. Feedforward, feedback and inhibitory connections in primate visualcortex [J]. Neural Networks,2004,17(5-6):625-632.
[80] Grossberg S, Swaminathan G. A laminar cortical model for3D perception ofslanted and curved surface and of2D images: development, attention, andbistability [J]. Vision Research,2004,44(11):1147-1187.
[81]汪云九.神经信息学-神经系统的理论和模型[M].北京:高等教育出版社,2007.
[82] Gilbert C D, Sigman M, and Crist R E. The neural basis of perceptual learning.Neuron,2001,31(5):681-697.
[83] Do M N, Vetterli M. Framing pyramids [J]. IEEE Transactions on Signalprocessing,2003,51(9):2329-2342.
[84]刘萍萍,赵宏伟,耿庆田,等.基于局部特征和视皮层识别机制的图像分类[J].吉林大学学报:工学版,2011,41(5):1401-1406.
[85]赵宏伟,王慧,刘萍萍,等.基于视中枢神经机制的视觉信息处理模型[J].吉林大学学报:工学版,2008,38(增刊2):158-161.
[86]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[D].长春:吉林大学计算机科学与技术学院,2010.
[87]韩东峰.图像分类识别中特征及模型的若干问题研究[D].长春:吉林大学计算机科学与技术学院,2008.
[88] Li S, Kwok J T, Zhu H, et al. Texture classification using the support machines [J].Pattern Recognition,2003,36:2883-2893.
[89] Kim K I, Jung K, Park S H, et al. Support vector machines for textureclassification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(11):2883-2893.
[90] Qin X, Yang Y. Simiarity measure and learning with gray level aura matrices(GLAM)for texture image retrieval[C]. Proceedings of IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2004,1:326-333.
[91]陆飞.仿生模式识别的几何学习算法理论的研究[D].杭州:浙江工业大学信息工程学院,2006.
[92]何振亚.多维数字信号处理[M].北京:国防工业出版社,1995.
[93]刘萍萍.图像的局部不变性特征方法研究[D].长春:吉林大学计算机科学与技术学院,2009.
[94] Michael Tye. The Imagery Debate[D]. Cambridge: MIT Press, USA,1991.
[95] Kosslyn S M. The cognitive neuroscience of mental imagery[J]. Neuropsychologia,1995,33:1335–1344.
[96] Kosslyn S M, Shwartz S P. A simulation of visual imagery[J]. Cognitive Science,1977,1:265–295.
[97] Ganis G, Thompson W L, Kosslyn S M. Brain areas underlying visual mentalimagery and visual perception: An FMRI study[J]. Cognitive Brain Research,2004,20,226–241.
[98] Barkowsky T, Bertel S, Engel D, Freksa C. Design of an architecture for reasoningwith mental images[C]. Proceedings of the International Workshop on Spatial andVisual Components in Mental Reasoning about Large-Scale Spaces, BadZwischenahn, Germany,2003.
[99]余波,张立明.基于初级视觉皮层的图像匹配模型[J].生物物理学报,1999,15(1):104–111.
[100]危辉,何新贵.表象式直接知识表示[J].计算机学报,2001,24,891–896.
[101]危辉,潘云鹤.形象思维的视表象基础[J].浙江大学学报(工学版),2001,35(2):152–156.
[102] Cao W M, Hao F. Biomimetic pattern recognition based on the Young-Helmholtzmodel of multispectral image[C].2009International Conference on ArtificialIntelligence and Computational Intelligence, Shanghai, China,2009,398-402.
[103] Li S, Qi X L, Hu H H, Wang Y J. synchronous oscillation of neural network modelof functional column[J]. Scientia Sinica Vitae,2004,34:385–394.
[104]王守觉,曲延锋,李卫军,等.基于仿生模式识别与传统模式识别的人脸识别效果比较研究[J].电子学报,2004,32(7):1057–1061.
[105] Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex[J].Nature Neuroscience,1999,2:1019–1025.
[106] David I Perrett, Oram M W. Neurophysiology of shape processing[J]. Image VisionComputing,1993,11:317–333.
[107] Zhang Xiang-he, Wang Dan, Ren Lu-quan, Liu Ping-ping. Biomimetic constructionof category mental imagery based on recognition mechanism of visual cortex ofhuman brain[J]. Journal of Bionic Engineering,2010,7(Suppl.): S238-S244.
[108] Daugman J G. Uncertainty relations for resolution in space, spatial frequency, andorientation optimized by two-dimensional visual cortical filters[J]. Journal of theOptical Society of America A,1985,2:1160–1169.
[109] Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functionalarchitecture in the cat’s visual cortex[J]. Journal of Physiology,1962,160:106–154.
[110] Griffin G, Holub A D, Perona P. The Caltech-256, Caltech TechnicalReport[DB/OL]. http://www.vision. caltech.edu/Image_Datasets/Caltech256/
[111] Grigorescu C, Petkov N, Westenberg M A. Contour detection based on nonclassicalreceptive field inhibition[C]. IEEE Transactions on Image Processing,2003,12,729–739.
[112] Serre Thomas, Wolf Lior, Bileschi Stanley. Robust object recognition withcortex-like mechanisms[J]. IEEE Tractions on Pattern Analysis and MachineIntelligence,2007,29(3):411-426.
[113]谭伟恒,申铉京,杨金峰.基于人体定位和动态肤色阈值的肤色检测算法[J].仪器仪表学报,29(1):115-119.
[114] Holub A, Welling M, Perona P. Exploiting unla-belled data for hybrid objectclassification[C].In NIPS Workshop on Inter-Class Transfer, Whistler,2005.
[115] Berg A C, Berg T L, Malik J. Shape matching and object recognition using lowdistortion correspondence[C]. IEEE Computer Society, Washington DC, USA,2005.
[116] Li Fei-fei, Pietro Perona. A Bayesian hierarchical model for learning natural scenecategories[C]//IEEE Computer Society Conference on Computer Vision and PatternRecognition,2005.
[117] Russell B C, Sivic J, Efros A A, et al. Discovering objects and their location inimages[C].Tenth IEEE International Conference on Computer Vision,2005.
[118]李远宁,刘汀,蒋树强,等.基于“Bag of words”的视频匹配方法[J].通信学报,2007,28(12):147-151.
[119]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电了学报，2006,34(1):155-158.
[120]王守觉,徐健,王宪保,等.基于仿生模式识别的多镜头人脸身份确认系统研究[J].电子学报,2002,30(1),1-3.
[121]王志海,赵占强,王守觉.仿生模式识别在单镜头人脸识别中的应用[J].模式识别与人工智能,2004,17(1):98-102.
[122]潘晓霞.基于高维空间覆盖方法的非特定人连续数字语音识别的研究[D].杭州:浙江工业大学信息工程学院,2004.
[123]胡建慧.基于仿生模式识别的虹膜识别算法研究[D].杭州：浙江工业大学信息工程学院，2006.
[124]张祥合,王丹,任露泉,等.基于高维空间仿生信息学的目标识别新算法[D].吉林大学学报:工学版,2011,41(增刊2):269-274.
[125]苏谦,邬文锦,王红武,等.基于近红外光谱和仿生模式识别玉米品种快速鉴别方法[J].光谱学与光谱分析,2009,29(9):2413-2416.
[126] Wu L L, Wang S J. Study on closed-set speaker identification based on biomimeticpattern recognition [J]. Chinese Journal of Electronics,2009,18,259-261.
[127]满彩岩.智能视频监控中的人体运动分析及关键技术研究[D].长春:计算机科学与技术学院,2009.
[128] Park C H, Lee J J, Oh S K. Iris feature extraction and matching based on multiscaleand directional image representation[C]. Scale Space Methods in Computer Vision,Proceedings, Berlin: Springer-Verlag Berlin,2003:576-583.
[129] Bar-Hillel A, Weinshall D. Efficient learning of relational object class models [J].International Journal of Computer Vision,2008,77(1):175–198,.
[130] Bernstein E, Amit Y. Part-based statistical models for object classification anddetection[C]. IEEE Conference on Computer Vision and Pattern Recognition,2005.
[131]燕忠,袁春伟.基于蚁群智能和支持向量机的人脸性别识别方法[J].电子与信息学报,2004,26(8):1177-1182.
[132]安冬,王守觉.基于仿生模式识别和PCA/ICA的DOA估计方法[J].电子学报,2004,(09):1448-1451.
[133]王蕴红,范伟,谭铁牛.融合全局与局部特征的子空间人脸识别算法[J].计算机学报,2005,(10):1657-1663.
[134] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C].2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1,886-893.
[135] Mikolajczyk Krystian, Schmid Cordelia. Scale and affine invariant interest pointdetectors [J]. International Journal of Computer Vision,2004,60(1):63-86.
[136] Mikolajcryk Krystian, Schmid Cordelia. A performance evaluation of localdescriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[137]张有正.基于双权值神经网络的逼近性及其应用[J].杭州:浙江工业大学信息工程学院,2006.
[138]梁路宏,艾海舟,何克忠,等.基于多关联模板匹配的人脸检测[J].软件学报,2001,12(1):92-102.
[139] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measure withclassification based on feature distribution [J]. Pattern Recognition,1996,29(1):51-59.
[140]胡斓,夏利民.基于Boosting RBF神经网络的人脸年龄估计[J].计算机工程,2006,32(19):119-201.
[141] Sammal A, Subramani V, Marx D. Analysis of sexual dimorphism in human face[J]. Journal of Visual Communication&Image Representation,2007(8):453-463.
[142] Brasnert P, Mihaylova L, Bull D, et al. Sequential Monte Carlo tracking by cues invideo sequences [J]. Image and Vision Computing,2007(25):1217-1227.
[143]工俊明,陈世旺.渐进背景影像的建构[J].国立台湾师范人学学报:数理与利技类,2002,47(21):43-54.
[144] Wang Tie-sheng, Gu I Y H, Khan Z H. Adaptive particle filters for visual objecttracking using joint PCA appearance model and consensus pointcorrespondences[C]. IEEE International Conference on Multimedia and Expo,2009:1370-1373.
[145]申若虹.模式识别中基于概率统计的Bayer算法分析[J].机械工程与自动化,2010(6):48-49.
[146] Yang Z, Li M, Ai H. An experimental study on automatic face genderclassification[C]. In Proceeding of the18th IEEE International Conference onPattern Recognition (ICPR'06),2006,3:1099-1102.
[147] Bray M, Meier E Koller, Gool L Van. Smart particle filtering for high-dimensionaltracking [J]. Computer Vision and Image Understanding,2007,106(1):116-129.
[148] Fahed Abdallah, Amadou Gning, Philippe Bonnifait. Box particle filtering fornonlinear state estimation using interval analysis [J]. Automatica,2008,44(3):807-815.
[149] Tan Hua-chun, Zhang Yu-jin. Detecting eye blink states by tracking iris and eyelids[J]. Pattern Recognition Letters,2006,27(6):667-675.
[150]张骏. Boosting方法及其在图像理解中的应用研究[D].合肥：合肥工业大学计算机与信息学院,2009.
[151]王丹，张祥合，张立，等.多维多分辨仿生识别方法及其应用[J].吉林大学学报:工学版,2011,41(2):408-412.
[152] Xie Shu-fu, Shan Shi-guang, Chen Xi-lin, et al. V-LGBP: Volume Binarv Patternsfor Face Representation and Recognition[C]. International Conference on PatternRecognition,2008. Florida, USA Based Local Gabor.(Oral).
[153]任明武.数字图像处理[M].南京:南京理工大学出版社,2003.
[154] Park Young Kyung, Park Seok Lai, Kim Joong Kyu. Retinex method based onadaptive smoothing for illumination invariant face recognition[J]. SignalProcessing,2008,88:1929-1945.
[155] Liyanage C, Silva De, Liu Jing, et al. Multimodal approach to human face detectionand tracking[J]. IEEE Transactions on Industrial Electronics,2008,55(3):1385-1392.
[156] Kazuhiro Hotta. Robust face recognition under partial occlusion based on supportvector machine with local Gaussian summation kernel [J]. Image and VisionComputing,2008,26:1490-1498.
[157]周书仁,梁昔明,朱灿,等.基于ICA与HMM的表情识别[J].中国图象图形学报,2008,13(12):2321-2328.
[158]徐光祐,曹媛媛.动作识别与行为理解综述[J].中国图象图形学报,2009,14(2):189-195.
[159] Bray M, MeierE Koller, Gool L Van. Smart particle filtering for high-dimensionaltracking. Computer Vision and Image Understanding,2007,106(1):116-129.
[160] Felzenszwalb P, Huttenlocher D. Pictorial structures for object recognition [J].International Journal of Computer Vision,2005,61(1):55-79.
[161]李鑫.基于生物视觉机理的直线图形认知系统研究[D].长春:吉林大学计算机科学与技术学院,2007.
[162]邱雪娜.基于视觉的运动目标跟踪算法及其在移动机器人中的应用[D].华东理工大学信息科学与工程学院,2011.
[163] Harzallah H, Jurie F, Schmid C. Combining efficient object localization and imageclassification [C]. In IEEE Conference on Computer Vision,2009.
[164] Moeslund T B, Hilton A, Kruger V. A survey of advances in vision-based humanmotion capture and analysis [J]. Computer Vision and Image Understanding,2006,103(2-3):90-126.
[165]胡良梅.基于信息融合的图像理解方法研究[D].合肥：合肥工业大学计算机与信息学院,2006.
[166]李文艳.基于视觉注意的目标检测方法[D].重庆:重庆大学自动化学院,2009.
[167] Yao Bang-peng, Li Fei-fei. Grouplet: A structured image representation forrecognizing human and object interactions [C]. IEEE Conference on ComputerVision and Pattern Recognition,2010.
[168] Yao Bang-peng, Li Fei-fei. Modeling mutual context of object and human pose inhuman object interaction activities [C]. IEEE Conference on Computer Vision andPattern Recognition,2010.
[169]彭素静.基于视觉感知机理的显著区域研究[D].重庆:重庆大学自动化学院,2009.
[170] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels forclassification of texture and object categories: a comprehensive study[J].International Journal of Computer Vision,2007,73(2):213-238.
[171] Cootes T, Edwards G, Taylor C. Active appearance models [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2001，23(6):681-685.
[172]刘晓山.光照变化条件下人脸识别技术研究[D].广州:华南理工大学计算机科学与工程学院,2011.
[173] Felzenszwalb P, McAllester D. The generalized architecture [J]. Journal ofArtificial Intelligence Research,2007,29:153-190.
[174] Leibe B, Leonardis A, Schiele B. Robust object detection with interleavedcategorization and segmentation [J]. International Journal of Computer Vision,2008,77(1):259-289.
[175]傅晓英.基于半连接HMM模型的人体行为识别研究与实现[D].北京:北京交通大学计算机与信息技术学院,2009.
[176]武松林.基于坐姿的多人行为识别与分析方法研究[D].延吉:延边大学工学院,2010.
[177]秦锋,罗慧,程泽凯,等.一种新的基于AUC的多类分类评估方法[J].计算机工程与应用,2008,44(5):194-196.
[178] Torralba A. Contextual priming for object detection [J]. International Journal ofComputer Vision,2003,53(2):169–191.
[179]陈薇薇.基于人类视觉系统生理特性的模型及应用研究[D].长沙：国防科学技术大学,2004.
[180]吴田富.视觉选择性注意机制计算模型及其在物体识别中的应用[D.]合肥：合肥工业大学计算机与信息学院,2005.
[181]侯志强,韩崇昭.基于像素灰度归类的背景重构算法[J].软件学报,2005,16(9):1569-1576.
[182] Smal I, Draegestein K, Galjart N, et al. Particle filtering for multiple object trackingin dynamic fluorescence microscopy images: application to microtubule growthanalysis[J]. IEEE Trans Med Imaging,2008,27(6):789-804.
[183]皮文凯,刘宏,查红彬.基于自适应背景模型的全方位视觉人体运动检测[J].北京大学学报:自然科学版,2004,40(3):458-464.
[184]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报,2006,32(4):603-617.
[185] Wang S J, Chen X, Qin H, et al. Double synaptic weight neuron theory and itsapplication[C]. International Conference on Advances in Natural Computation,Changsha, China,2005,264-272.
[186] Weber M, Welling M, Perona P. Towards automatic discovery of objectcategories[C]. IEEE Conference on Computer Vision and Pattern Recognition,2000.
[187] Zhang J, Marszalek M, Lazebnik S, et al. Local features and kernels forclassification of texture and object categories: A comprehensive study [J].International Journal of Computer Vision,2007,73(2):213–238.
[188]谭菊.基于视觉感知的目标特性分析[D]重庆:重庆大学自动化学院,2010.
[189]李新.面向神经计算的视觉信息处理研究[D].西安：西北工业大学计算机学院,2003.
[190]陈礼.视觉注意模型的研究及其在ROI图像压缩上的应用[D].重庆:重庆大学自动化学院,2008.
[191]凌志刚,赵春晖,梁彦,等.基于视觉的人行为理解综述[J].计算机应用研究,2008,25(9):2570-2578.
[192]王超.基于视觉分析的水下报警算法研究[D].大连:大连海事大学信息科学技术学院,2009.
[193]李军令.基于视中枢神经机制的视觉信息处理模型研究[D].长春:吉林大学计算机科学与技术学院,2008.
[194] Felzenszwalb P, Girshick R, McAllester D, et al. Object detection withdiscriminatively trained part based models [C]. IEEE Transactions on PatternAnalysis and Machine Intelligence,2009.
[195] Gupta A, Kembhavi A, Davis L S. Observing human-object interactions: Usingspatial and functional compatibility for recognition [C]. IEEE Transactions onPattern Analysis and Machine Intelligence,2009,31(10):1775-1789.
[196]陈媛媛.图像显著区域提取及其在图像检索中的应用[D].上海:上海交通大学信息安全工程学院,2006.
[197]张仁俊.视皮层细胞特征检测研究[D].长春:吉林大学计算机科学与技术学院,2008.
[198] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. InCVPR,2005:886–893.
[199]姜夕凯,苏松志,李绍滋,等.基于单张静态图像的人体行为识别方法综述[J].漳州师范学院学报(自然科学版),2011(4):23-26.
[200]王江涛.基于视频的目标检测、跟踪及其行为识别研究[D].南京:南京理工大学计算机科学与技术学院，2008.
[201]凌志刚,赵春晖,梁彦,等.基于视觉的人行为理解综述[J].计算机应用研究,2008,25(9):2570-2578.
[202] Ikizler N, Cinbis R G, Pehlivan S, et al. Recognizing Actions from Still Images[C].19th International Conference on Pattern Recognition (ICPR),2008:1-4.
[203] Yang Wei-long, Wang Yang, Mori Greg, et al. Recognizing Human Actions fromStill Images with Latent Poses[C].2010IEEE Conference on Computer Vision andPattern Recognition (CVPR),2010:2030-2037.
[204] Delaitre V, Laptev I, Sivic J. Recognizing human actions in still images: a study ofbag-of-features and part-based representations[C]. Proceedings of the BritishMachine Vision Conference,2010:1-11.