图像理解的关键问题和方法研究
|
摘要
图像理解是当前计算机研究领域的热点和难点，其根本任务就是让计算机正确解释所感知的图像场景以及场景中的内容，图像理解与计算机视觉、与人工智能有着密切的联系，具有重要的理论研究意义和广阔的应用前景。
图像理解具有鲜明的层次性，作为图像理解的低层数据的是视觉信息，理论出发点是计算机视觉，作为图像理解的高层数据是知识信息，理论依据出发点是人工智能。图像理解中视觉数据和人类知识两种类型的信息流贯穿图像理解的整个过程，但是目前对这两种类型的数据和信息流的研究基本上是割裂的，忽略了知识和数据之间的融合，忽略了低层处理和高层分析的联系。
本文从数据驱动知识、知识指导数据这一图像理解的核心问题出发，从视觉信息分析处理与知识信息分析处理的结合部入手，着重研究图像理解信息流中数据和知识的表示、存储、分析和转换，研究合适的视觉信息处理载体和知识信息处理方法，实现广义目标检测识别、区域语义理解以及场景分析等图像理解的主要任务，形成新颖的图像理解方法：同时，研究图像理解的结构特性，构建新型的目标空间关系模型和整体场景的分析模型，建立模型之间的约束反馈机制，体现理解的反馈和渐进性，指导先验信息的获取，并作用于低层的视觉数据处理分析，提高理解的速度和准确性，初步形成新型、完整、有效、快速的图像理解原型。
本文的主要工作如下：
1、研究了图像理解中数据和信息表示的融合，概述了图像理解中常见的信息表示方法，侧重描述新的“知识”和“数据”两种信息的融合和转换手段，体现图像理解中实体的认知关系；研究了图像理解中视觉信息的提取问题，总结了图像理解视觉特征的提取策略，建立了视觉像素的统计概率模型，在模型基础上提出了一种新的目标定位方法，对背景具有一定的抗背景干扰能力，并形成了对特征提取方法的有益补充。
2、研究了图像理解中视觉信息的存储与分析，针对图像理解中的图结构模型载体分析问题，总结了图模型中经典的参数估计和概率推理方法以及在视觉分析中的应用，提出了一种基于目标空间关系的无向图结构模型，讨论了新模型中的参数学习问题，推导出迭代公式，进行场景目标分析，形成对图像理解认知载体的丰富和完善。
3、研究了图像理解中视觉信息的概念认知划分，针对广义目标检测识别方法问题，提出了基于共享特征的层次Boosting目标检测识别方法，可同时进行多类目标检测和识别，在检测率近似保持不变的情况下，提高了目标的识别率，缩短了分类的搜索时间，体现了图像理解的渐进性，形成了视觉信息向知识信息的转换。
4、研究了图像理解中的知识处理和分析，针对图像理解中的区域分析和语义标记问题，提出了基于粗糙集合的区域分割方法和知识库约简方法，对场景中视觉属性较为一致的区域具有较好的分割效果，同时在保持概念分类能力不变的情况下形成了知识的有效约简，一定程度上避免的噪声数据的干扰，提高了语义标记和区域分析的合理性，实现了数据和知识的融合。
5、初步研究了场景分类的基本方法，提出的高斯概率统计模型对场景分类具有一定的有效性，同时，验证了场景分类信息对目标分析的指导和约束作用，提高了目标分析的准确度，体现了图像理解中反馈的认知结构。
Image understanding is the hotspot and difficulty in computer reseach area. The essential task is to interpret the acquired image scene and its contents accurately. It is closely relative with computer vision and artificial intelligence with important theories and wide applications.
Image understanding has the distinct layer property. As the visual information in lower layer, the theorical startpoint is computer vision and as the knowledge information in higher one, the theorical basis is artificial intelligence. Visual data and knowledge are two types of information through understanding images, but current researches on them is often separative which neglect the fusions between knowledge and data and ignore the relations between process in lower layer and analysis in higher one.
Considering key issues about data-driven knowledge and knowledge-guiding data in image understanding, we start researches for novel methods from joints between these two kinds of information processing. The thesis focuses on representation, storage, analysis and transform with data and knowledge in image understanding to research proper cognitive carriers and knowledge processing methods for several sub-tasks as generic object detection and recognition, regional semantic understanding and scene analysis which forms the novel way. At the same time, we discuss the structures in image understanding and build models for objects with spatial relations and global scenes to represent corresponding restriction and feedback mechanisms, which guide for knowledge accuqusition and act on data processing in lower layer to improve speed and accuracy in image understanding and rm novel complete effective and rapid archetypal structure initially.
This thesis includes the following contents:
1、On the research of fusion with data and knowledge representation, we describe the general ways of information representation with emphasis on fusion and translation between knowledge and data to reveal cognitive relations in entities. Then we summarize the feature extraction strategies and build the regional statistical models with pixels. Based on them, a new object location method is proposed to keep out the "background" noise and supply the current ways for feature extraction.
2、We study the storage and analysis on visual information to solve the graphic models as carriers in image understanding. We ummarize the theories for parameter estimation and probability inference with corresponding visual. Then we present an undirected graphic model based on spatial relations, discuss two main problems above and obtain the iterative equations to analyze object and scene for enrichment in image understanding.
3、We discuss the cognitive division in visual information for generic object detection and recognition and propose the layer joint boosting algorithms based on sharing features. With the condition of approximate unchanged detection rate, the recognition rate increases and classification time decreases dramatically to show gradualness in image understanding and transform from visual data to knowledge.
4、We research the knowledge processing and analysis in image understanding to solve the problems in regional analysis and semantics labeling. We present the new image segmentation and knowledge base reduction methods with rough set theories. The result demonstrates the better segmentation performance on visual consistent area and effect reduction without changes in conception classifications to avoid interference with noisy data and improve reasonability in labeling semantics and analyzing regions to some extend realizing the fusion with data and knowledge.
5、We analyze the basic method for scene classification primarily and propose the new method based on Gaussian probabilistic statistical models for effect results. At the same time, we also validate the classification results as prior knowledge have strong guidance and restrict to improve accuracy in object analysis and reveal feedback in image understanding.
图像理解具有鲜明的层次性，作为图像理解的低层数据的是视觉信息，理论出发点是计算机视觉，作为图像理解的高层数据是知识信息，理论依据出发点是人工智能。图像理解中视觉数据和人类知识两种类型的信息流贯穿图像理解的整个过程，但是目前对这两种类型的数据和信息流的研究基本上是割裂的，忽略了知识和数据之间的融合，忽略了低层处理和高层分析的联系。
本文从数据驱动知识、知识指导数据这一图像理解的核心问题出发，从视觉信息分析处理与知识信息分析处理的结合部入手，着重研究图像理解信息流中数据和知识的表示、存储、分析和转换，研究合适的视觉信息处理载体和知识信息处理方法，实现广义目标检测识别、区域语义理解以及场景分析等图像理解的主要任务，形成新颖的图像理解方法：同时，研究图像理解的结构特性，构建新型的目标空间关系模型和整体场景的分析模型，建立模型之间的约束反馈机制，体现理解的反馈和渐进性，指导先验信息的获取，并作用于低层的视觉数据处理分析，提高理解的速度和准确性，初步形成新型、完整、有效、快速的图像理解原型。
本文的主要工作如下：
1、研究了图像理解中数据和信息表示的融合，概述了图像理解中常见的信息表示方法，侧重描述新的“知识”和“数据”两种信息的融合和转换手段，体现图像理解中实体的认知关系；研究了图像理解中视觉信息的提取问题，总结了图像理解视觉特征的提取策略，建立了视觉像素的统计概率模型，在模型基础上提出了一种新的目标定位方法，对背景具有一定的抗背景干扰能力，并形成了对特征提取方法的有益补充。
2、研究了图像理解中视觉信息的存储与分析，针对图像理解中的图结构模型载体分析问题，总结了图模型中经典的参数估计和概率推理方法以及在视觉分析中的应用，提出了一种基于目标空间关系的无向图结构模型，讨论了新模型中的参数学习问题，推导出迭代公式，进行场景目标分析，形成对图像理解认知载体的丰富和完善。
3、研究了图像理解中视觉信息的概念认知划分，针对广义目标检测识别方法问题，提出了基于共享特征的层次Boosting目标检测识别方法，可同时进行多类目标检测和识别，在检测率近似保持不变的情况下，提高了目标的识别率，缩短了分类的搜索时间，体现了图像理解的渐进性，形成了视觉信息向知识信息的转换。
4、研究了图像理解中的知识处理和分析，针对图像理解中的区域分析和语义标记问题，提出了基于粗糙集合的区域分割方法和知识库约简方法，对场景中视觉属性较为一致的区域具有较好的分割效果，同时在保持概念分类能力不变的情况下形成了知识的有效约简，一定程度上避免的噪声数据的干扰，提高了语义标记和区域分析的合理性，实现了数据和知识的融合。
5、初步研究了场景分类的基本方法，提出的高斯概率统计模型对场景分类具有一定的有效性，同时，验证了场景分类信息对目标分析的指导和约束作用，提高了目标分析的准确度，体现了图像理解中反馈的认知结构。
Image understanding is the hotspot and difficulty in computer reseach area. The essential task is to interpret the acquired image scene and its contents accurately. It is closely relative with computer vision and artificial intelligence with important theories and wide applications.
Image understanding has the distinct layer property. As the visual information in lower layer, the theorical startpoint is computer vision and as the knowledge information in higher one, the theorical basis is artificial intelligence. Visual data and knowledge are two types of information through understanding images, but current researches on them is often separative which neglect the fusions between knowledge and data and ignore the relations between process in lower layer and analysis in higher one.
Considering key issues about data-driven knowledge and knowledge-guiding data in image understanding, we start researches for novel methods from joints between these two kinds of information processing. The thesis focuses on representation, storage, analysis and transform with data and knowledge in image understanding to research proper cognitive carriers and knowledge processing methods for several sub-tasks as generic object detection and recognition, regional semantic understanding and scene analysis which forms the novel way. At the same time, we discuss the structures in image understanding and build models for objects with spatial relations and global scenes to represent corresponding restriction and feedback mechanisms, which guide for knowledge accuqusition and act on data processing in lower layer to improve speed and accuracy in image understanding and rm novel complete effective and rapid archetypal structure initially.
This thesis includes the following contents:
1、On the research of fusion with data and knowledge representation, we describe the general ways of information representation with emphasis on fusion and translation between knowledge and data to reveal cognitive relations in entities. Then we summarize the feature extraction strategies and build the regional statistical models with pixels. Based on them, a new object location method is proposed to keep out the "background" noise and supply the current ways for feature extraction.
2、We study the storage and analysis on visual information to solve the graphic models as carriers in image understanding. We ummarize the theories for parameter estimation and probability inference with corresponding visual. Then we present an undirected graphic model based on spatial relations, discuss two main problems above and obtain the iterative equations to analyze object and scene for enrichment in image understanding.
3、We discuss the cognitive division in visual information for generic object detection and recognition and propose the layer joint boosting algorithms based on sharing features. With the condition of approximate unchanged detection rate, the recognition rate increases and classification time decreases dramatically to show gradualness in image understanding and transform from visual data to knowledge.
4、We research the knowledge processing and analysis in image understanding to solve the problems in regional analysis and semantics labeling. We present the new image segmentation and knowledge base reduction methods with rough set theories. The result demonstrates the better segmentation performance on visual consistent area and effect reduction without changes in conception classifications to avoid interference with noisy data and improve reasonability in labeling semantics and analyzing regions to some extend realizing the fusion with data and knowledge.
5、We analyze the basic method for scene classification primarily and propose the new method based on Gaussian probabilistic statistical models for effect results. At the same time, we also validate the classification results as prior knowledge have strong guidance and restrict to improve accuracy in object analysis and reveal feedback in image understanding.
引文
[1] J. H. Elder, S.W. Zucker. Local scale control for edge detection and blur estimation. IEEE Transactions on Pattern Analysis Machine Intelligence, 20(7): 699-716, 1998.
[2] J. Jeong-Hun, H. Ki-Sang. Fast Line Segment Grouping Method for Finding Globally More Favorable Line Segments. Pattern Recognition, 35(10): 2235-2247, 2002.
[3] R. Sanchez-Reillo, C. Sanchez-Avila. Gonzales-Marcos. A Biometric identification through hand geometry measurements. IEEE Transactions on Pattern Analysis Machine Intelligence, 22(10): 1168-1171, 2000.
[4] G. F. Luger. Artificial Intelligence: Structures and Strategies for Complex Problem Solving. New York: Addison Wesley, 2005.
[5] 章毓晋．图像分割．北京：科学出版社，2001．
[6] Y. Ohta. Knowledge Based Interpretation of outdoors Natural Color Scenes. Boston: Pitman, 1985.
[7] V. Venkateswar, R. Chellappa. A Hierarchical Approach to Detection of Buildings in Aerial Images. Technical Report CS-TR-2720. Center for Automation Research, University of Maryland. 2003.
[8] M. Zhang, L.Q.Hall and D.B.Goldgof. A generic knowledge-guided image segmentation and labeling system using fuzzy clustering algorithms. IEEE Transactions on System, Man and Cybernetics. Part B, Cybernetics, 32(5): 571-582, 2003.
[9] 王润生．图像理解．长沙：国防科技大学出版社，1995．
[10] S. Barbara. Modeling and Detection of Geospatial Objects Using Texture Motifs. Ph.D thesis, 2005.
[11] Z. L. Start. Markov Random Field Modeling in Image Analysis, Berlin: Springer-Verlag, 2000.
[12] T. Sinisa, C.Michael. Interpretation of Complex Scenes Using Generative Dynamic-Structure Models. International Journal of Pattern Recognition and Artificial Intelligence, 15(1): 9-42, 2001.
[13] M. Marengoni, A. Hanson, S. Zilberstein and E. Riseman. Decision making and uncertainty management in a 3D reconstruction system. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7): 852-858, 2003.
[14] S. K. Kopparapu, B. D. Uday. Bayesian approach to image interpretation. Kluwer Academic Publishers, 2001.
[15] I. Biederman. An Invitation to Cognitive Science. MIT Press, 2(2): 121-165, 1995.
[16] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278-2324, 1998.
[17] Y. LeCun. MNIST Database of Handwritten digits, http://yann.lecun.com/exdb/mnist/index, 2004.
[18] Y. LeCun, F. Huang and L. Bottou. Learning methods for generic object recognition with invariance to pose and lighting. In Proceedings of Computer Vision and Pattern Recognition, 2: 97-104, 2004.
[19] Y. Amit, D. Geman. A computational model for visual selection. Neural Computation, 11(7): 1691-1715, 1998.
[20] Y. Amit, D. Geman and K. Wilder. Joint induction of shape features and tree classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(11): 1300-1305, 1997.
[21] A. M. Martinez, A.C. Kak. PCA versus LDA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2): 228-233, 2001.
[22] M. Turk, A. Pentland. Eigenfaees for recognition. Journal of Cognitive Neuroscience, 3(1): 71-86, 1991.
[23] T. Tuytelaars, A. Zaatri, L. Van Gool and H. Van Brussel. Automatic object recognition as part of an integrated supervisorycontrol system. IEEE International Conference on Robotics and Automation, (4): 3707-3712, 2000.
[24] P. J. Phillips, H. Moon, S. A. Rizvi and P. J. Rauss. The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(10): 1090-1104, 2002.
[25] M. A. Fischler, R. A. E; schlager. The representation and matching of pictorial structures. IEEE Transactions on Computer, c-22(1): 67-92, 1973.
[26] H. Rowley, S. Baluja and T. Kanade. Neural network-hased face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(1): 23-38, 1998.
[27] H. Schneiderman, T. Kanade. A statistical method for 3D object detection applied to faces and cars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1746-1759, 2000.
[28] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 511-518, 2001.
[29] C. Papageorgious, M. Oren and T. Poggio. A general framework for object detection. In Proceedings of the 7th International Conference on Computer Vision, 1223-1228, 1998.
[30] N. Dalai, B. Triggs. Histograms of oriented gradients for human detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 886-893, 2005.
[31] M. Fleck, D. Forsyth and C. Bregler. Finding naked people. In Proceedings of the 4th European Conference on Computer Vision, 591-602, 1996.
[32] D. Forsyth and M. Fleck. Body plans. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 678-683, 1997.
[33] K. Mikolajezyk, C. Schmid and A. Zisserman. Human detection based on a probabilistic assembly of robust part detectors. In Proceedings of the 8th European Conference on Computer Vision, 1: 69-82, 2004.
[34] T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham. Active shape models—their training and application. Computer Vision and Image Understanding, 61(1): 38-59, 1995.
[35] L. Chengjun, H. Wechsler. Gabor feature based classification using the enhanced fisher lineardiscriminant model for face recognition. IEEE Transactions on Image Processing, 11(4): 467-476, 2002.
[36] G. Csurka, C. Bray, C. Dance and L. Fan. Visual categorization with bags of keypoints. In Workshop on Statistical Learning in Computer Vision, 1-22, 2004.
[37] G. Dorko and C. Schmid. Object class recognition using discriminative local features. IEEE Transactions on Pattern Analysis and Machine Intelligence, Review (Submitted), 2004.
[38] A. Opelt, M. Fussenegger. Weak hypotheses and boosting for generic object detection and recognition. In Proceedings of the 8th European Conference on Computer Vision, 2:71-84, 2004.
[39] M. Burl, P. Perona. Recognition of planar object class. In Proceedings of Computer Vision and Pattern Recognition, 223-230, 1996.
[40] M. Burl, M. Weber and P. Perona. A probabilistic approach to object recognition using local photometry and global geometry. In Proceedings of European Conference on Computer Vision, 628-641, 1998.
[41] M. Weber, W. Einhauser, M. Welling and P. Perona. Viewpoint-invariant learning and detection of human heads. In Proceedings 4th IEEE International Conference Automatic Face and Gesture Recognition, 20-27, 2000.
[42] M. C. Burl, T. K. Leung and P. Perona. Face localization via shape statistics. In International Workshop on Automatic Face and Gesture Recognition, 154-159, 1995.
[43] T. Leung and J. Malik. Contour continuity and region based image segmentation. In Proceedings of the 5th European Conference on Computer Vision, 544-559, 1998.
[44] T. K. Leung, M C. Burl and P. Peroma. Finding faces in cluttered scenes using random labeled graph matching. In Proceedings of the 5th International Conference on Computer Vision, 637-644, 1995.
[45] M. Weber. Unsupervised Learning of Models of Object Recognition. PhD thesis, Califomia Institute of Technology, Pasadena, 2000.
[46] M. Weber, M. Welling and P. Perona. Towards automatic discovery of object categories. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2101-2108, 2000.
[47] M. Weber, M. Welling and P. Perona. Unsupervised learning of models for recognition. In Proceedings 6th European Conference of Computer Vision, 1: 18-32, 2000.
[48] R. Fergus. Visual Object Category Recognition. PhD thesis, Oxford University, 2005.
[49] L. Fei-Fei, R. Forgus and P. Perona. A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the 9th International Conference on Computer Vision, 1134-1141, 2003.
[50] P. Felzenszwalb, D. Huttenloeher. Pictorial structures for object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2066-2073, 2000.
[51] D. Crandall, P. Felzenszwalb and D. Huttenlocher. Spatial priors for part-based recognition using statistical models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1: 10-17, 2005.
[52] S. Agarwal, D. Roth. Learning a sparse representation for object detection. In Proceedings of the 7th European Conference on Computer Vision, 113-130, 2002.
[53] A. Carlson, C. Cumby, J. Rosen and D. Roth. The snow learning architecture, uiucdcsr-99-2101. Technical report, Department of Computer Science, UIUC, 1999.
[54] E. Borenstein, S. UIIman. Class-specific, top-down segmentation. In Proceedings of the 7th European Conference on Computer Vision, 109-124, 2002.
[55] A. Torralba, K. P. Murpht and W. T. Freeman. Sharing features: efficient boosting procedures for muiticlass object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 762-769, 2004.
[56] B. Leibe, A. Leonardis and B. Sehiele. Combined object categorization and segmentation with an implicit shape model. In Workshop on Statistical Learning in Computer Vision, 2004.
[57] S. Jianbo, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8): 888-905, 1997.
[58] T. Kadir, M. Brady. Scale saliency operator, http://www.robots.ox.ac.uk/-timork/salscal,2003,
[59] D. Lowe. Local feature view clustering for 3D object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 682-688, 2001.
[60] K. Mikolajczyk, C. Schmid. Indexing based on scale invariant interest points. In Proceedings of the 8th International Conference on Computer Vision, 525-531,2001.
[61] C. J. Harris, M. Stephens. A combined corner and edge detector. In Proceedings of the 4th Alvey Vision Conference, 147-151, 1988.
[62] D. Lowe. Object recognition from local scale-invariant features. In Proceedings of 7th International Conference on Computer Vision and Pattern Recognition, 682-688, 2001.
[63] K. Barnard, P. Duygulu and D. A. Forsyth. Clustering art. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2:408-415,2001.
[64] K. Barnard, D. A. Forsyth. Learning the semantics of words and pictures. In International Conference on Computer Vision, 2:408-415, 2001.
[65] P. Carbonetto. Unsupervised statistical models for general object recognition. Master thesis, The University of British Columbia, 2001.
[66] T. Zhuowen, C. Xiangrong, Y. L. Alan and Z. S. Chun. Image Parsing: Unifying segmentation, detection and recognition. International Journal of Computer Vision archive, 63(2): 113-140, 2005.
[67] I. Biederrnan. An Invitation to Cognitive Science. MIT Press, 2(2): 121-165, 1995.
[68] A. Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3): 145-175, 2001.
[69] L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2:524-531, 2001.
[70] R. Q. Quiroga, L. Reddy, G. Kreiman, C. Koch and I. Freid. Invafiant visual representation by single neurons in the human brain. Nature Letters, 435(23): 1102-1107, 2005.
[71] A. Oliva, J. M. Molfe. The Interaction of Memory and Vision in Search Through a Familiar Scene. Journal of Experimental Psychology: Human Perception and Performance, 30(6): 1132-1146, 2004.
[72] K. K. Evans, A. Treisman. Perception of objects in natural scenes: Is It Really Attention Free? Journal of Experimental Psychology: Human Perception and Performance, 31(6): 1476-1492, 2005.
[73] 章毓晋．图像理解与计算机视觉．北京：清华大学出版社，2000．
[74] 高文，陈熙霖．计算机视觉——算法与系统原理．北京：清华大学出版社，1999．
[75] 艾海舟，武勃等译．图像处理、分析与机器视觉．北京：人民邮电出版社，2003．
[76] 董火明，高隽，胡良梅，王安东．基于PCA网络的协同指纹识别．模式识别与人工智能，17(1)：87-93，2004．
[77] G. Jun, Z. Qin, X. Xiaohong and Y. Jing. A novel evolutionary template-matching algorithm and researches on it. Chinese Journal of Electronics, 15(2): 246-250, 2006.
[78] G. Jun, D. Huoming, S. Jing and Z. Jing. Parameters Optimization of Synergetic Recognition Approach. Chinese Journal of Electronics, 14(2): 192-197, 2005.
[79] 董火明，高隽，胡良梅．多分类器融合的指纹全局特征协同融合．电路与系统学报，10(3)：58-63，2005．
[80] 汪荣贵，高隽，张佑生，彭青松．一种新的面向对象的概率图模型．计算机研究与发展，42(8)：1283-1292，2005．
[81] J. Gao, Z. Xie. Generic Object recognition with regional statistical models and layer joint boosting. Pattern Recognition. Accepted.
[82] Z. Xie, J. Gao. Tolerant rough set based image segmentation with morphology operators. LNCS Transactions on Rough Sets. Accepted.
[83] L. Fei-Fei, R. Fergus, and P. Perona. Learning generative visual models from few training examples:an incremental Bayesian approach tested on 101 object categories. In Workshop on Generative-Model Based Vision in Computer Vision and Pattern Recognition, 2004.
[84] T. Serre, A. Oliva and T. Poggio. A feedforward theory of visual cortex accounts for human performance in rapid categorization. CBCL Paper # MMVI-02, Massachusetts Institute of Technology, Cambridge, MA, March, 2006.
[85] V. Goffaux, C. Jacques, A. Mouraux, A. Oliva, B. Rossion and P.G. Schyns. Building the Gist of a Scene: The Role of Global Image Features in Recognition. Progress in Brain Research: Visual perception, 155: 23-36, 2005.
[86] 章毓晋．基于内容的视觉信息检索．北京：科学出版社，2003．
[87] B. Furht. Video and image processing in multimedia systems. Boston: Kluwer Academic Publishers, 226-270, 1995.
[88] P. M. Kelly, M. Cannon. CANDID: Comparison algorithm for navigating digital image databases. In Proceedings of 7IC Scientific and Statistical Database Management, 252-258, 1994.
[89] M. Riesenhuber, T. Poggio. Hierarchical models of object recognition in cortex. Nature Neurosciences, 2(11): 1019-1025, 1999.
[90] T. Serre, L. Wolf and T. Poggio. Object recognition with features inspired by visual cortex. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2): 994-1000, 2005.
[91] J. Shi, J. Malik. Normalized cuts and image segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 731-737, 1997.
[92] 叶奇祥，高文，王伟强等．一种基于图像颜色和空间信息的彩色图像分割算法．软件学报，15(4)：522-530，2004．
[93] E. Borenstein, S. Ullman. Class specific top down-segmentation. In Proceedings of the European Conference on Computer Vision Copenhagen, 110-122, 2001.
[94] S. C. Zhu. Statistical modeling and conceptualization of visual patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(6): 1-22, 2003.
[95] Z. W. Tu, S. C. Zhu. Image segmentation by data-driven Markov Chain Monte Carlo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5): 657-673, 2002.
[96] M. I. Jordan. Introduction to graphical models. Unpublished, 2003.
[97] Y. W. The. Bethe free energy and contrastive divergence approximations for undirected graphical models. PhD thesis, University of Toronto, 2003.
[98] Y. W. The, M. Welling. The unified propagation and sealing algorithm. Advances in Neural Information Processing Systems, 14(2): 953-960, 2001.
[99] K. Murphy, Y. Weiss and M. 1. Jordan. Loopy belief propagation for approximate inference: an empirical study. In Proceedings of the IEEE Conference on Uncertainty in Artificial Intelligence, (15): 467-475, 1999.
[100] T. Hofmann. Unsupervised learning by probabilistic latent semantic analysis. Machine Learning, 42: 177-196, 2001.
[101] J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman and W. T. Freeman. Discovering objects and their location in images. In Proceedings of International Conference on Computer Vision, (1): 370-377, 2005.
[102] D. M. Blei, A. Y. Ng and M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Research 3,993-1022, 2003.
[103] I. Cadez, P. Smyth. Parameter estimation for inhomogeneous markov random fields using pseudolikelihood. University of California, 1998.
[104] R. Lienhart, A. Kuranov and V. Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. In DAGM 25th Pattern Recognition Symposium, 297-304, 2003.
[105] R. Schapire, Y. Singer. BoosTexter: A boosting-based system for text categorization. Machine Learning, 39(2/3):135-168, 2000.
[106] 王海川，张立明．一种新的Adaboost快速训练算法．复旦学报，43(1)：27-33，2004．
[107] P. Viola, M. Jones. Fast and robust classification using asymmetric Adaboost and a detector cascade. Advances in Neural Information Processing System 14, 1: 311-318, 2002.
[108] B. McCane, K. Novins. On training cascade face detectors. Palmerston North, 245-246, 2003.
[109] A. Opelt, M. Fussenegger, A. Pinz and P. Auer. Weak hypothesis and boosting for generic object detection and recognition. In Proceedings of European Conference of Computer Vision, (2): 71-84, 2004.
[110] A. Goshtasby, S. H. Gage and J. F. Bartholic. A two-stage cross-correlation approach to template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(3): 374-378, 1984.
[111] T. G. Dietterich, G. Bakiri. Solving multi-class learning problems via ECOCs. Journal of Artificial Intelligence Research, 2: 263-286, 1995.
[112] L. Kuncheva. Using diversity measures for generating error-correcting output codes in classifier ensembles. Pattern Recognition Letters, 26: 83-90, 2005.
[113] M. Zhang, L. Q. Hall and D.B. Goldgof. A generic knowledge-guided image segmentation and labeling system using fuzzy clustering algorithms. IEEE Transactions on System, Man and Cybernetics. Part B, Cybernetics, 32(5): 571-582, 2003.
[114] J. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8): 888-905, 2000.
[115] W. Y. Ma, B. S. Manjunath. EdgeFlow: A technique for boundary detection and image segmentation. IEEE Transactions on Image Process, 9(8): 1375-1388, 2000.
[116] Z. W. Tu, X. R. Chen and S. C. Zhu. Image parsing: unifying segmentation, detection, and recognition. International Journal of Computer Vision, Marr Prize Issue, 63(2): 113-140, 2005.
[117] 王国胤．粗糙集理论与知识获取．西安：西安交通大学出版社，2001．
[118] A. Mohabey, A. K. Bay. Fusion of rough set theoretic approximation and FCM for color image segmentation. In Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, 2: 1529-1534, 2000.
[119] A. Mohabey, A. K. Bay. Rough set theory based segmentation of color images. In International Conference of the North American Fuzzy Information Processing Society, 338-342, 2000.
[120] J. F. Peters, M. Borkowski. K-means indiscernibility relation over pixels. Lecture Notes in Computer Science, 3066:580-585,2004.
[121] L. Polkowski, A. Skowron. Analytical morphology: mathematical morphology of decision tables. Fundamenta Informaticae, 27(2-3): 255-271, 1996.
[122] L. Polkowski, A. Skowron. Rough mereological foundations for design, analysis, synthesis and control in distributive systems. In proceedings of Second Joint Annual Conference on Information Sciences, 346-349,1995.
[123] D. Comanicu, P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24:603-619,2002.
[124] P. Carbonetto, F. D. Nando and K. Barnard. A statistical model for general contextual object recognition. In Proceedings of European Conference on Computer Vision, 350-362,2004.
[125] A. Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3): 145-175,2001.
[126] A. Vailaya, M. Figueiredo, A. Jain and H. Zhang. Image classification for content-based indexing. IEEE Transactions on Image Processing, 10: 117-130,2001.
[127] Y. W. Teh, M. Welling. The Unified Propagation and Scaling Algorithm. Advances in neural information processing systems, 14: 953-960,2002.
[2] J. Jeong-Hun, H. Ki-Sang. Fast Line Segment Grouping Method for Finding Globally More Favorable Line Segments. Pattern Recognition, 35(10): 2235-2247, 2002.
[3] R. Sanchez-Reillo, C. Sanchez-Avila. Gonzales-Marcos. A Biometric identification through hand geometry measurements. IEEE Transactions on Pattern Analysis Machine Intelligence, 22(10): 1168-1171, 2000.
[4] G. F. Luger. Artificial Intelligence: Structures and Strategies for Complex Problem Solving. New York: Addison Wesley, 2005.
[5] 章毓晋．图像分割．北京：科学出版社，2001．
[6] Y. Ohta. Knowledge Based Interpretation of outdoors Natural Color Scenes. Boston: Pitman, 1985.
[7] V. Venkateswar, R. Chellappa. A Hierarchical Approach to Detection of Buildings in Aerial Images. Technical Report CS-TR-2720. Center for Automation Research, University of Maryland. 2003.
[8] M. Zhang, L.Q.Hall and D.B.Goldgof. A generic knowledge-guided image segmentation and labeling system using fuzzy clustering algorithms. IEEE Transactions on System, Man and Cybernetics. Part B, Cybernetics, 32(5): 571-582, 2003.
[9] 王润生．图像理解．长沙：国防科技大学出版社，1995．
[10] S. Barbara. Modeling and Detection of Geospatial Objects Using Texture Motifs. Ph.D thesis, 2005.
[11] Z. L. Start. Markov Random Field Modeling in Image Analysis, Berlin: Springer-Verlag, 2000.
[12] T. Sinisa, C.Michael. Interpretation of Complex Scenes Using Generative Dynamic-Structure Models. International Journal of Pattern Recognition and Artificial Intelligence, 15(1): 9-42, 2001.
[13] M. Marengoni, A. Hanson, S. Zilberstein and E. Riseman. Decision making and uncertainty management in a 3D reconstruction system. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7): 852-858, 2003.
[14] S. K. Kopparapu, B. D. Uday. Bayesian approach to image interpretation. Kluwer Academic Publishers, 2001.
[15] I. Biederman. An Invitation to Cognitive Science. MIT Press, 2(2): 121-165, 1995.
[16] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278-2324, 1998.
[17] Y. LeCun. MNIST Database of Handwritten digits, http://yann.lecun.com/exdb/mnist/index, 2004.
[18] Y. LeCun, F. Huang and L. Bottou. Learning methods for generic object recognition with invariance to pose and lighting. In Proceedings of Computer Vision and Pattern Recognition, 2: 97-104, 2004.
[19] Y. Amit, D. Geman. A computational model for visual selection. Neural Computation, 11(7): 1691-1715, 1998.
[20] Y. Amit, D. Geman and K. Wilder. Joint induction of shape features and tree classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(11): 1300-1305, 1997.
[21] A. M. Martinez, A.C. Kak. PCA versus LDA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2): 228-233, 2001.
[22] M. Turk, A. Pentland. Eigenfaees for recognition. Journal of Cognitive Neuroscience, 3(1): 71-86, 1991.
[23] T. Tuytelaars, A. Zaatri, L. Van Gool and H. Van Brussel. Automatic object recognition as part of an integrated supervisorycontrol system. IEEE International Conference on Robotics and Automation, (4): 3707-3712, 2000.
[24] P. J. Phillips, H. Moon, S. A. Rizvi and P. J. Rauss. The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(10): 1090-1104, 2002.
[25] M. A. Fischler, R. A. E; schlager. The representation and matching of pictorial structures. IEEE Transactions on Computer, c-22(1): 67-92, 1973.
[26] H. Rowley, S. Baluja and T. Kanade. Neural network-hased face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(1): 23-38, 1998.
[27] H. Schneiderman, T. Kanade. A statistical method for 3D object detection applied to faces and cars. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1746-1759, 2000.
[28] P. Viola, M. Jones. Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 511-518, 2001.
[29] C. Papageorgious, M. Oren and T. Poggio. A general framework for object detection. In Proceedings of the 7th International Conference on Computer Vision, 1223-1228, 1998.
[30] N. Dalai, B. Triggs. Histograms of oriented gradients for human detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 886-893, 2005.
[31] M. Fleck, D. Forsyth and C. Bregler. Finding naked people. In Proceedings of the 4th European Conference on Computer Vision, 591-602, 1996.
[32] D. Forsyth and M. Fleck. Body plans. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 678-683, 1997.
[33] K. Mikolajezyk, C. Schmid and A. Zisserman. Human detection based on a probabilistic assembly of robust part detectors. In Proceedings of the 8th European Conference on Computer Vision, 1: 69-82, 2004.
[34] T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham. Active shape models—their training and application. Computer Vision and Image Understanding, 61(1): 38-59, 1995.
[35] L. Chengjun, H. Wechsler. Gabor feature based classification using the enhanced fisher lineardiscriminant model for face recognition. IEEE Transactions on Image Processing, 11(4): 467-476, 2002.
[36] G. Csurka, C. Bray, C. Dance and L. Fan. Visual categorization with bags of keypoints. In Workshop on Statistical Learning in Computer Vision, 1-22, 2004.
[37] G. Dorko and C. Schmid. Object class recognition using discriminative local features. IEEE Transactions on Pattern Analysis and Machine Intelligence, Review (Submitted), 2004.
[38] A. Opelt, M. Fussenegger. Weak hypotheses and boosting for generic object detection and recognition. In Proceedings of the 8th European Conference on Computer Vision, 2:71-84, 2004.
[39] M. Burl, P. Perona. Recognition of planar object class. In Proceedings of Computer Vision and Pattern Recognition, 223-230, 1996.
[40] M. Burl, M. Weber and P. Perona. A probabilistic approach to object recognition using local photometry and global geometry. In Proceedings of European Conference on Computer Vision, 628-641, 1998.
[41] M. Weber, W. Einhauser, M. Welling and P. Perona. Viewpoint-invariant learning and detection of human heads. In Proceedings 4th IEEE International Conference Automatic Face and Gesture Recognition, 20-27, 2000.
[42] M. C. Burl, T. K. Leung and P. Perona. Face localization via shape statistics. In International Workshop on Automatic Face and Gesture Recognition, 154-159, 1995.
[43] T. Leung and J. Malik. Contour continuity and region based image segmentation. In Proceedings of the 5th European Conference on Computer Vision, 544-559, 1998.
[44] T. K. Leung, M C. Burl and P. Peroma. Finding faces in cluttered scenes using random labeled graph matching. In Proceedings of the 5th International Conference on Computer Vision, 637-644, 1995.
[45] M. Weber. Unsupervised Learning of Models of Object Recognition. PhD thesis, Califomia Institute of Technology, Pasadena, 2000.
[46] M. Weber, M. Welling and P. Perona. Towards automatic discovery of object categories. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2101-2108, 2000.
[47] M. Weber, M. Welling and P. Perona. Unsupervised learning of models for recognition. In Proceedings 6th European Conference of Computer Vision, 1: 18-32, 2000.
[48] R. Fergus. Visual Object Category Recognition. PhD thesis, Oxford University, 2005.
[49] L. Fei-Fei, R. Forgus and P. Perona. A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the 9th International Conference on Computer Vision, 1134-1141, 2003.
[50] P. Felzenszwalb, D. Huttenloeher. Pictorial structures for object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2066-2073, 2000.
[51] D. Crandall, P. Felzenszwalb and D. Huttenlocher. Spatial priors for part-based recognition using statistical models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1: 10-17, 2005.
[52] S. Agarwal, D. Roth. Learning a sparse representation for object detection. In Proceedings of the 7th European Conference on Computer Vision, 113-130, 2002.
[53] A. Carlson, C. Cumby, J. Rosen and D. Roth. The snow learning architecture, uiucdcsr-99-2101. Technical report, Department of Computer Science, UIUC, 1999.
[54] E. Borenstein, S. UIIman. Class-specific, top-down segmentation. In Proceedings of the 7th European Conference on Computer Vision, 109-124, 2002.
[55] A. Torralba, K. P. Murpht and W. T. Freeman. Sharing features: efficient boosting procedures for muiticlass object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 762-769, 2004.
[56] B. Leibe, A. Leonardis and B. Sehiele. Combined object categorization and segmentation with an implicit shape model. In Workshop on Statistical Learning in Computer Vision, 2004.
[57] S. Jianbo, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8): 888-905, 1997.
[58] T. Kadir, M. Brady. Scale saliency operator, http://www.robots.ox.ac.uk/-timork/salscal,2003,
[59] D. Lowe. Local feature view clustering for 3D object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 682-688, 2001.
[60] K. Mikolajczyk, C. Schmid. Indexing based on scale invariant interest points. In Proceedings of the 8th International Conference on Computer Vision, 525-531,2001.
[61] C. J. Harris, M. Stephens. A combined corner and edge detector. In Proceedings of the 4th Alvey Vision Conference, 147-151, 1988.
[62] D. Lowe. Object recognition from local scale-invariant features. In Proceedings of 7th International Conference on Computer Vision and Pattern Recognition, 682-688, 2001.
[63] K. Barnard, P. Duygulu and D. A. Forsyth. Clustering art. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2:408-415,2001.
[64] K. Barnard, D. A. Forsyth. Learning the semantics of words and pictures. In International Conference on Computer Vision, 2:408-415, 2001.
[65] P. Carbonetto. Unsupervised statistical models for general object recognition. Master thesis, The University of British Columbia, 2001.
[66] T. Zhuowen, C. Xiangrong, Y. L. Alan and Z. S. Chun. Image Parsing: Unifying segmentation, detection and recognition. International Journal of Computer Vision archive, 63(2): 113-140, 2005.
[67] I. Biederrnan. An Invitation to Cognitive Science. MIT Press, 2(2): 121-165, 1995.
[68] A. Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3): 145-175, 2001.
[69] L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2:524-531, 2001.
[70] R. Q. Quiroga, L. Reddy, G. Kreiman, C. Koch and I. Freid. Invafiant visual representation by single neurons in the human brain. Nature Letters, 435(23): 1102-1107, 2005.
[71] A. Oliva, J. M. Molfe. The Interaction of Memory and Vision in Search Through a Familiar Scene. Journal of Experimental Psychology: Human Perception and Performance, 30(6): 1132-1146, 2004.
[72] K. K. Evans, A. Treisman. Perception of objects in natural scenes: Is It Really Attention Free? Journal of Experimental Psychology: Human Perception and Performance, 31(6): 1476-1492, 2005.
[73] 章毓晋．图像理解与计算机视觉．北京：清华大学出版社，2000．
[74] 高文，陈熙霖．计算机视觉——算法与系统原理．北京：清华大学出版社，1999．
[75] 艾海舟，武勃等译．图像处理、分析与机器视觉．北京：人民邮电出版社，2003．
[76] 董火明，高隽，胡良梅，王安东．基于PCA网络的协同指纹识别．模式识别与人工智能，17(1)：87-93，2004．
[77] G. Jun, Z. Qin, X. Xiaohong and Y. Jing. A novel evolutionary template-matching algorithm and researches on it. Chinese Journal of Electronics, 15(2): 246-250, 2006.
[78] G. Jun, D. Huoming, S. Jing and Z. Jing. Parameters Optimization of Synergetic Recognition Approach. Chinese Journal of Electronics, 14(2): 192-197, 2005.
[79] 董火明，高隽，胡良梅．多分类器融合的指纹全局特征协同融合．电路与系统学报，10(3)：58-63，2005．
[80] 汪荣贵，高隽，张佑生，彭青松．一种新的面向对象的概率图模型．计算机研究与发展，42(8)：1283-1292，2005．
[81] J. Gao, Z. Xie. Generic Object recognition with regional statistical models and layer joint boosting. Pattern Recognition. Accepted.
[82] Z. Xie, J. Gao. Tolerant rough set based image segmentation with morphology operators. LNCS Transactions on Rough Sets. Accepted.
[83] L. Fei-Fei, R. Fergus, and P. Perona. Learning generative visual models from few training examples:an incremental Bayesian approach tested on 101 object categories. In Workshop on Generative-Model Based Vision in Computer Vision and Pattern Recognition, 2004.
[84] T. Serre, A. Oliva and T. Poggio. A feedforward theory of visual cortex accounts for human performance in rapid categorization. CBCL Paper # MMVI-02, Massachusetts Institute of Technology, Cambridge, MA, March, 2006.
[85] V. Goffaux, C. Jacques, A. Mouraux, A. Oliva, B. Rossion and P.G. Schyns. Building the Gist of a Scene: The Role of Global Image Features in Recognition. Progress in Brain Research: Visual perception, 155: 23-36, 2005.
[86] 章毓晋．基于内容的视觉信息检索．北京：科学出版社，2003．
[87] B. Furht. Video and image processing in multimedia systems. Boston: Kluwer Academic Publishers, 226-270, 1995.
[88] P. M. Kelly, M. Cannon. CANDID: Comparison algorithm for navigating digital image databases. In Proceedings of 7IC Scientific and Statistical Database Management, 252-258, 1994.
[89] M. Riesenhuber, T. Poggio. Hierarchical models of object recognition in cortex. Nature Neurosciences, 2(11): 1019-1025, 1999.
[90] T. Serre, L. Wolf and T. Poggio. Object recognition with features inspired by visual cortex. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2): 994-1000, 2005.
[91] J. Shi, J. Malik. Normalized cuts and image segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 731-737, 1997.
[92] 叶奇祥，高文，王伟强等．一种基于图像颜色和空间信息的彩色图像分割算法．软件学报，15(4)：522-530，2004．
[93] E. Borenstein, S. Ullman. Class specific top down-segmentation. In Proceedings of the European Conference on Computer Vision Copenhagen, 110-122, 2001.
[94] S. C. Zhu. Statistical modeling and conceptualization of visual patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(6): 1-22, 2003.
[95] Z. W. Tu, S. C. Zhu. Image segmentation by data-driven Markov Chain Monte Carlo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5): 657-673, 2002.
[96] M. I. Jordan. Introduction to graphical models. Unpublished, 2003.
[97] Y. W. The. Bethe free energy and contrastive divergence approximations for undirected graphical models. PhD thesis, University of Toronto, 2003.
[98] Y. W. The, M. Welling. The unified propagation and sealing algorithm. Advances in Neural Information Processing Systems, 14(2): 953-960, 2001.
[99] K. Murphy, Y. Weiss and M. 1. Jordan. Loopy belief propagation for approximate inference: an empirical study. In Proceedings of the IEEE Conference on Uncertainty in Artificial Intelligence, (15): 467-475, 1999.
[100] T. Hofmann. Unsupervised learning by probabilistic latent semantic analysis. Machine Learning, 42: 177-196, 2001.
[101] J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman and W. T. Freeman. Discovering objects and their location in images. In Proceedings of International Conference on Computer Vision, (1): 370-377, 2005.
[102] D. M. Blei, A. Y. Ng and M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Research 3,993-1022, 2003.
[103] I. Cadez, P. Smyth. Parameter estimation for inhomogeneous markov random fields using pseudolikelihood. University of California, 1998.
[104] R. Lienhart, A. Kuranov and V. Pisarevsky. Empirical analysis of detection cascades of boosted classifiers for rapid object detection. In DAGM 25th Pattern Recognition Symposium, 297-304, 2003.
[105] R. Schapire, Y. Singer. BoosTexter: A boosting-based system for text categorization. Machine Learning, 39(2/3):135-168, 2000.
[106] 王海川，张立明．一种新的Adaboost快速训练算法．复旦学报，43(1)：27-33，2004．
[107] P. Viola, M. Jones. Fast and robust classification using asymmetric Adaboost and a detector cascade. Advances in Neural Information Processing System 14, 1: 311-318, 2002.
[108] B. McCane, K. Novins. On training cascade face detectors. Palmerston North, 245-246, 2003.
[109] A. Opelt, M. Fussenegger, A. Pinz and P. Auer. Weak hypothesis and boosting for generic object detection and recognition. In Proceedings of European Conference of Computer Vision, (2): 71-84, 2004.
[110] A. Goshtasby, S. H. Gage and J. F. Bartholic. A two-stage cross-correlation approach to template matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(3): 374-378, 1984.
[111] T. G. Dietterich, G. Bakiri. Solving multi-class learning problems via ECOCs. Journal of Artificial Intelligence Research, 2: 263-286, 1995.
[112] L. Kuncheva. Using diversity measures for generating error-correcting output codes in classifier ensembles. Pattern Recognition Letters, 26: 83-90, 2005.
[113] M. Zhang, L. Q. Hall and D.B. Goldgof. A generic knowledge-guided image segmentation and labeling system using fuzzy clustering algorithms. IEEE Transactions on System, Man and Cybernetics. Part B, Cybernetics, 32(5): 571-582, 2003.
[114] J. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8): 888-905, 2000.
[115] W. Y. Ma, B. S. Manjunath. EdgeFlow: A technique for boundary detection and image segmentation. IEEE Transactions on Image Process, 9(8): 1375-1388, 2000.
[116] Z. W. Tu, X. R. Chen and S. C. Zhu. Image parsing: unifying segmentation, detection, and recognition. International Journal of Computer Vision, Marr Prize Issue, 63(2): 113-140, 2005.
[117] 王国胤．粗糙集理论与知识获取．西安：西安交通大学出版社，2001．
[118] A. Mohabey, A. K. Bay. Fusion of rough set theoretic approximation and FCM for color image segmentation. In Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, 2: 1529-1534, 2000.
[119] A. Mohabey, A. K. Bay. Rough set theory based segmentation of color images. In International Conference of the North American Fuzzy Information Processing Society, 338-342, 2000.
[120] J. F. Peters, M. Borkowski. K-means indiscernibility relation over pixels. Lecture Notes in Computer Science, 3066:580-585,2004.
[121] L. Polkowski, A. Skowron. Analytical morphology: mathematical morphology of decision tables. Fundamenta Informaticae, 27(2-3): 255-271, 1996.
[122] L. Polkowski, A. Skowron. Rough mereological foundations for design, analysis, synthesis and control in distributive systems. In proceedings of Second Joint Annual Conference on Information Sciences, 346-349,1995.
[123] D. Comanicu, P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24:603-619,2002.
[124] P. Carbonetto, F. D. Nando and K. Barnard. A statistical model for general contextual object recognition. In Proceedings of European Conference on Computer Vision, 350-362,2004.
[125] A. Oliva, A. Torralba. Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3): 145-175,2001.
[126] A. Vailaya, M. Figueiredo, A. Jain and H. Zhang. Image classification for content-based indexing. IEEE Transactions on Image Processing, 10: 117-130,2001.
[127] Y. W. Teh, M. Welling. The Unified Propagation and Scaling Algorithm. Advances in neural information processing systems, 14: 953-960,2002.