基于图像局部不变特征的类属超图构建与目标识别技术研究
|
摘要
图像目标识别技术是计算机视觉领域的研究热点,经过几十年的发展,虽然该方面的研究已经有了许多令人鼓舞的研究成果,但是由于问题本身的复杂性,图像目标识别仍然是一个具有挑战性的问题。本文从成像条件变化时图像具有不同成像状态的角度出发,构建了对目标成像条件的大范围变化具有适应性的图像模型并用于目标识别。论文对图像的表征、图像建模与模型训练、图像目标识别等方面的关键技术进行了研究。开展的工作和取得的成果主要有以下几个方面:
(1)图像的属性图表示模型和属性图相似性度量定义。在对图像局部不变特征进行稳健特征选择的基础上,通过综合利用图像的局部特征信息和特征的空间分布信息,将图像用属性图进行表示。图像的属性图模型不仅利用了局部特征信息,而且利用了特征的空间布局,有利于图像模型识别性能的提升。在对图像进行属性图表示后,接下来综合利用图像的局部特征信息和特征点的空间布局进行特征匹配,得到属性图特征点之间的匹配关系,最后根据匹配关系定义属性图相似性度量。属性图相似性度量将用于后续的图像建模以及目标识别。
(2)类属超图模型的构建与模型快速训练。以目标不同成像条件下的图像对应的属性图组成的图集为训练集,构建了一种以属性图为顶点,以属性图之间的相似性关系为边的图像目标模型,称为类属超图(Class Specific Hyper Graph,CSHG)模型。该模型的构建过程中首先建立了目标的初始类属超图模型,然后基于提出的属性图相似性传播聚类思想,给出了一种构建图的家族树(FTOG:Family Tree of a Graph)的方法,经训练可得到具有强的类专属特性的FTOG,由这些FTOG综合构成了对感兴趣目标的类属超图模型。类属超图模型不仅利用了图像的局部特征描述信息,而且利用了特征的空间分布信息,能够适应图像成像条件的大范围变化。模型的快速训练是模型的核心研究问题之一,基于RSOM聚类树搜索方法,给出了类属超图模型的快速训练算法。类属超图模型的快速训练方法提高了模型的训练效率,使得模型具有更强的实用性和可行性。另外,模型快速训练算法中的聚类搜索思想同样可以用于基于类属超图模型的目标识别过程中,可以有效提高目标识别的效率。
(3)类属超图模型的优化训练与智能化训练。为了得到优化的类属超图模型,给出了类属超图模型的优化训练方法。类属超图模型的优化包括两个阶段的训练,第一阶段的优化训练是基于类属超图模型上定义的熵函数,得到熵最小化准则下一定数量的FTOG,以保证训练所得模型结构的紧凑性;在第一阶段优化训练的基础上,第二阶段的优化训练是基于亲缘传播聚类(Affinity Propagation Clustering,AP)算法精简类属超图模型中各个FTOG聚类中的冗余属性图。经过两阶段的优国防科学技术大学研究生院博士学位论文化训练,得到优化的类属超图模型。在此基础上,可进一步对模型进行增量训练和自主训练,统称为智能化训练。针对新样本到来的情况,给出了类属超图模型的增量训练算法。在类属超图模型增量训练过程中,新增训练样本的类别信息可能是不能完全确定的,这时需要模型具有以一种弱监督的方式自主进行训练的能力,本文给出了类属超图模型的自主训练方法。增量训练和自主训练都是模型需要具有的重要能力,这两种能力使得模型具有更强的实用性。
(4)基于类属超图模型的图像目标识别与标注。针对简单背景条件下的图像目标和复杂背景条件下的图像目标,分别给出了基于类属超图模型的目标识别算法。利用给出的识别算法可以完成复杂成像条件下的图像目标识别。在目标识别的基础上,给出了目标区域标注方法。最后,对类属超图模型的构建过程与基于类属超图模型进行目标识别的过程进行综合,给出了完整的基于类属超图模型的图像目标识别系统设计方案。
Image based object recognition is an active research domain in computer vision. Although some successful progress has been achieved over a number of decades, object recognition is still a challenging problem because of the complexity of object imaging. This thesis derives a canonical model of visual category or class which is accommodated to significant or complex variations in imaging conditions from the view of large variations in variant conditions of an object. Techniques of image representation, object modeling and training, and object recognition have been thoroughly studied. The main work of the dissertation includes the following aspects.
(1) Attributed graph representation model and a similarity measure between two graphs are proposed. On the basis of selection of salient local invariant features, images are represented with attributed graphs by integrating the local information contained in those local features and their spatial information. Because the attributed graphs contain not only the local feature information, but also the spatial relationship among the features, the recognition performance of image models constructed using attributed graphs will be enhanced. After representation of images with attributed graphs, a feature matching algorithm that utilizing the global and local information comprehensively is proposed. Given the matching results, a similarity measure between graphs is constructed to be used in image modeling and object recognition.
(2) A method for the construction of the class specific hyper graph (CSHG) and its efficient training method are proposed. The CSHG model, whose vertex are attributed graphs and hyper-edges represent the similarity information of attributed graphs, is constructed from a large corpus of multi-view images represented with attributed graphs. In the process of constructing a CSHG model, an initial CSHG model is firstly constructed, then a similarity propagation based graph clustering method is used to obtain class specific familiy tree of graphs (FTOG), all class specific FTOGs make up a CSHG model. A CSHG model is a comprehensive integration of the global and local information contained in those local features and can accommodate to significant or complex variations in imaging conditions. Training efficiency of the model is one of the most important problems. Borrowing the RSOM tree method, an efficient training algorithm of CSHG model is proposed, which makes it more feasible to object recognition in practice. In addition, the indexing method in RSOM tree is also used in later recognition algorithm of CSHG model.
(3) Methods of optimization training, incremental training and weak supervised training of a CSHG model have been studied. The optimization training of a CSHG model includes two stages. In the first stage, an optimized CSHG model structure is obtained using the entropy function defined on the CSHG model. In the second stage, redundant graphs in FTOG clusters in the CSHG model are detected and omitted using an affinity propagation method. In the end, the optimized CSHG model is constructed. In incremental settings, new images will continue to be obtained after a CSHG model has been trained. It is necessary to incrementally train a CSHG model. An incremental training algorithm is proposed based on an RSOM tree. In the process of incremental training, the category attribution of newly-come images might be omitted or un-annotated. We also propose a weaklly supervised training algorithm, which can automatically detected new class specific FTOGs. In which case, the training system will actively ask for attribution annotation for such FTOGs. This process can be termed as weak supervision or half supervion. Incremental training and weak supervised training are promising properties of our CSHG model.
(4) The techniques for object recognition and object annotation are researched. Based on the trained CSHG model, object recognition methods for images with simple or complex background clutters and challenging viewing conditions are proposed. An object region labeling algorithm is proposed. A design schema of a CSHG model based recognition system is proposed in Chapter VI.
(1)图像的属性图表示模型和属性图相似性度量定义。在对图像局部不变特征进行稳健特征选择的基础上,通过综合利用图像的局部特征信息和特征的空间分布信息,将图像用属性图进行表示。图像的属性图模型不仅利用了局部特征信息,而且利用了特征的空间布局,有利于图像模型识别性能的提升。在对图像进行属性图表示后,接下来综合利用图像的局部特征信息和特征点的空间布局进行特征匹配,得到属性图特征点之间的匹配关系,最后根据匹配关系定义属性图相似性度量。属性图相似性度量将用于后续的图像建模以及目标识别。
(2)类属超图模型的构建与模型快速训练。以目标不同成像条件下的图像对应的属性图组成的图集为训练集,构建了一种以属性图为顶点,以属性图之间的相似性关系为边的图像目标模型,称为类属超图(Class Specific Hyper Graph,CSHG)模型。该模型的构建过程中首先建立了目标的初始类属超图模型,然后基于提出的属性图相似性传播聚类思想,给出了一种构建图的家族树(FTOG:Family Tree of a Graph)的方法,经训练可得到具有强的类专属特性的FTOG,由这些FTOG综合构成了对感兴趣目标的类属超图模型。类属超图模型不仅利用了图像的局部特征描述信息,而且利用了特征的空间分布信息,能够适应图像成像条件的大范围变化。模型的快速训练是模型的核心研究问题之一,基于RSOM聚类树搜索方法,给出了类属超图模型的快速训练算法。类属超图模型的快速训练方法提高了模型的训练效率,使得模型具有更强的实用性和可行性。另外,模型快速训练算法中的聚类搜索思想同样可以用于基于类属超图模型的目标识别过程中,可以有效提高目标识别的效率。
(3)类属超图模型的优化训练与智能化训练。为了得到优化的类属超图模型,给出了类属超图模型的优化训练方法。类属超图模型的优化包括两个阶段的训练,第一阶段的优化训练是基于类属超图模型上定义的熵函数,得到熵最小化准则下一定数量的FTOG,以保证训练所得模型结构的紧凑性;在第一阶段优化训练的基础上,第二阶段的优化训练是基于亲缘传播聚类(Affinity Propagation Clustering,AP)算法精简类属超图模型中各个FTOG聚类中的冗余属性图。经过两阶段的优国防科学技术大学研究生院博士学位论文化训练,得到优化的类属超图模型。在此基础上,可进一步对模型进行增量训练和自主训练,统称为智能化训练。针对新样本到来的情况,给出了类属超图模型的增量训练算法。在类属超图模型增量训练过程中,新增训练样本的类别信息可能是不能完全确定的,这时需要模型具有以一种弱监督的方式自主进行训练的能力,本文给出了类属超图模型的自主训练方法。增量训练和自主训练都是模型需要具有的重要能力,这两种能力使得模型具有更强的实用性。
(4)基于类属超图模型的图像目标识别与标注。针对简单背景条件下的图像目标和复杂背景条件下的图像目标,分别给出了基于类属超图模型的目标识别算法。利用给出的识别算法可以完成复杂成像条件下的图像目标识别。在目标识别的基础上,给出了目标区域标注方法。最后,对类属超图模型的构建过程与基于类属超图模型进行目标识别的过程进行综合,给出了完整的基于类属超图模型的图像目标识别系统设计方案。
Image based object recognition is an active research domain in computer vision. Although some successful progress has been achieved over a number of decades, object recognition is still a challenging problem because of the complexity of object imaging. This thesis derives a canonical model of visual category or class which is accommodated to significant or complex variations in imaging conditions from the view of large variations in variant conditions of an object. Techniques of image representation, object modeling and training, and object recognition have been thoroughly studied. The main work of the dissertation includes the following aspects.
(1) Attributed graph representation model and a similarity measure between two graphs are proposed. On the basis of selection of salient local invariant features, images are represented with attributed graphs by integrating the local information contained in those local features and their spatial information. Because the attributed graphs contain not only the local feature information, but also the spatial relationship among the features, the recognition performance of image models constructed using attributed graphs will be enhanced. After representation of images with attributed graphs, a feature matching algorithm that utilizing the global and local information comprehensively is proposed. Given the matching results, a similarity measure between graphs is constructed to be used in image modeling and object recognition.
(2) A method for the construction of the class specific hyper graph (CSHG) and its efficient training method are proposed. The CSHG model, whose vertex are attributed graphs and hyper-edges represent the similarity information of attributed graphs, is constructed from a large corpus of multi-view images represented with attributed graphs. In the process of constructing a CSHG model, an initial CSHG model is firstly constructed, then a similarity propagation based graph clustering method is used to obtain class specific familiy tree of graphs (FTOG), all class specific FTOGs make up a CSHG model. A CSHG model is a comprehensive integration of the global and local information contained in those local features and can accommodate to significant or complex variations in imaging conditions. Training efficiency of the model is one of the most important problems. Borrowing the RSOM tree method, an efficient training algorithm of CSHG model is proposed, which makes it more feasible to object recognition in practice. In addition, the indexing method in RSOM tree is also used in later recognition algorithm of CSHG model.
(3) Methods of optimization training, incremental training and weak supervised training of a CSHG model have been studied. The optimization training of a CSHG model includes two stages. In the first stage, an optimized CSHG model structure is obtained using the entropy function defined on the CSHG model. In the second stage, redundant graphs in FTOG clusters in the CSHG model are detected and omitted using an affinity propagation method. In the end, the optimized CSHG model is constructed. In incremental settings, new images will continue to be obtained after a CSHG model has been trained. It is necessary to incrementally train a CSHG model. An incremental training algorithm is proposed based on an RSOM tree. In the process of incremental training, the category attribution of newly-come images might be omitted or un-annotated. We also propose a weaklly supervised training algorithm, which can automatically detected new class specific FTOGs. In which case, the training system will actively ask for attribution annotation for such FTOGs. This process can be termed as weak supervision or half supervion. Incremental training and weak supervised training are promising properties of our CSHG model.
(4) The techniques for object recognition and object annotation are researched. Based on the trained CSHG model, object recognition methods for images with simple or complex background clutters and challenging viewing conditions are proposed. An object region labeling algorithm is proposed. A design schema of a CSHG model based recognition system is proposed in Chapter VI.
引文
[1] Biederman I. An Invitation to Cognitive Science [C]. Visual Cognition, Vol 2, chapter Visual Object Recognition, MIT Press, 1995:121-165.
[2] http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2009/.
[3] Chung F. Spectral Graph Theory [C]. CBMS Regional Conference Series in Mathematics, Conference Board of the American Mathematical Science, Washington, DC. 1997, 92.
[4] Berge C. Hypergraphs [M], North-Holland, 1989.
[5] Bebis G, Georgiopoulos M and Lobo N V. learning Geometric Hashing Functions for Model-based Object Recognition [C]. International Conference on Computer Vision, 1995:543-548.
[6] Cyr C and Kimia B. 3D Object Recognition Using Similarity-based Aspect Graph [C]. International Conference on Computer Vision, 2001:254-261.
[7] Murase H and Nayar S. Visual Learning and Recognition of 3D Objects from Appearance [J]. International Joural of Computer Vision, 1995, 14(1).
[8] Swain M J and Ballard B H. Color Indexing [J]. International Joural of Computer Vision, 1991, 7(1):11-32.
[9] Selinger A and Nelson R C. A Perceptual Grouping Hierarchy for Appearance-based 3d Object Recognition [J]. Computer Vision and Image Understanding, 1999, 76(1):83-92.
[10] Lowe D. Distinctive Image Features from Scale-invariant Keypoints [J]. International Joural of Computer Vision, 2004, 60(2):91-110.
[11] Mikolajczyk K and Schmid C. An Affine Invariant Interest Point Detector [C]. European Conference on Computer Vision, 2002:128-142.
[12] Obrdzalek S and Matas J. Object Recognition Using Local Affine Frames on Distinguished Regions [C]. BMVC, 2002:414-431.
[13] Rothganger F Lazebnik S Schmid C and Ponce J. 3D Object Modeling and Recognition Using Local Affine-invariant Image descriptors and Multi-view Spatial Constraints [J]. International Joural of Computer Vision, 2006, 66(3):231-259.
[14] Tuyelaars T and Van-Gool L. Wide Baseline Stereo Based on Local, Affinely Invariant Regions [C]. BMVC, 2000.
[15] Mikolajczyk K and Schmid C. Indexing Based on Scale-invariant Interest Points [C]. International Conference on Computer Vision, 2001, 1:525-531.
[16] Baumberg A. Reliable Feature Matching Across Widely Separated Views [C]. International Conference on Computer Vision, 2000:774-781.
[17] Matas J, Chum O, Urban M and Pajdla T. Robust Wide Baseline Stereo fromMaximally Stable Extremal Regions. BMVC, 2002:384-393.
[18] Schaffalitzky F and Zisserman A. Automated Scene Maching in Movies [C]. In Workshop on Content-Based Image and Video Retrieval, 2002:186-197.
[19] Tuytelaars T, Van-Gool L and Koch R. Matching Affinely Invatiant Regions for Visual Servoing [C]. In Intl. Conference on Robotics and Automation, 1999:1601-1606.
[20] Bay H, Tuytelaars T and Gool L V. SURF: Speeded Up Robust Features [C]. European Conference on Computer Vision, 2006, 3951(1):404-417.
[21] Kadir T, Brady M and Zisserman A. An Invariant Method for Selecting Salient Regions in Images [C]. European Conference on Computer Vision, 2004, 1(1):345-457.
[22] Mikolajczyk K and Schmid C. Scale and Affine Invariant Interest Point Detectors [J]. International Journal of Computer Vision, 2004, 60(1):63-86.
[23] Linderberg T. Feature Detection with Automatic Scale Selection [J]. International Journal of Computer Vision, 1998, 30(2):79-116.
[24] Zhang J, Marszalek M, Lazebnik S and Schmid C. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study [J]. International Journal of Computer Vision, 2007, 73(2):213-238.
[25] Mikolajczyk K and Schmid C. A Performance Evaluation of Local Descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[26] Tuytelaarsl T and Mikolajczyk Krystian. Local Invariant Feature Detectors: A Survey [J]. Computer Graphics and Vision, 2007, 3(3):177-280.
[27] Li F F and Perona P. A Bayesian Hierarchical model for Learning Natural Scene Categories [C]. International Conference on Computer Vision and Pattern Recognition, 2005, 2(2):524-531.
[28] Sivic J, Russell B C, Efros A A, Zisserman A and Freeman W T. Discovering Objects and Their Location in Images [C]. International Conference on Computer Vision, 2005, 1(1):872-877.
[29] Torralba A, Fergus R and Weiss Y. Small Codes and Large Image Databases for Recognition [C]. International Conference on Computer Vision, 2008.
[30] Eric Nowak etc. al. Sampling Strategies for Bag-of-Features Image Classification [C]. European Conference on Computer Vision, 2006, 3954:490-503.
[31] Philbin J, Sivic J and Zisserman A. Geometric Latent Dirichlet Allocation (gLDA) Model for Unsupervised Particular Object Discovery in Unordered Image Collections [C]. BMVC, 2008.
[32] Nister D and Stewenius. Scalable Recognition with a Vocabulary Tree [C]. International Conference on Computer Vision and Pattern Recognition, 2006,2(2):2161-2168.
[33] Qingfang Zheng and Wen Gao. Constructing Visual Phrases for Effective and Efficient Object-Based Image Retrieval [J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2008, 5(1), Article 7:1-19.
[34]夏胜平,刘建军,袁振涛,虞华,张乐锋,郁文贤.基于集群的并行分布式RSOM聚类[J].电子学报,2007,35(3):385-391.
[35] Crandall D J and Huttenlocher D P. Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition [C]. European Conference on Computer Vision, 2006, 3951(1):16-29.
[36] Jiang X, Munger A and Bunke H. On Median Graphs: Properties, Algorithms and Applications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(10):1144-1151.
[37] Torsello A and Hancock E. Learning Shape-Classes Using a Mixture of Treeunions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(6):954-967.
[38] Bonev B, Escolano F, Lozano M A, Suau P, Cazorla M A and Aguilar W. Constellations and the Unsupervised Learning of Graphs [C]. Graph-Based Representations in Pattern Recognition, 2007, 14(1):340-350.
[39] Lowe D. Local Feature View Clustering for 3d Object Recognition [C]. International Conference on Computer Vision and Pattern Recognition, 2001, 2(1):1682-1688.
[40] Ferrari V, Tuytelaara T and Van-Gool L. Simultaneous Object Recogntiion and Segmentation from Single or Multiple Model Views [J]. International Journal of Computer Vision, 2006, 67(2):159-188.
[41]陈静,夏胜平.几种典型模式识别分类器武断性的分析[J].计算机研究与发展. 2007,5B:32-36.
[42] Todorovic S and Ahuja N. Unsupervised Category Modeling, Recognition and Segmentation in Iamges [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009.
[43] http://www.lotushill.org/
[44] Mitchell Tom M. Machine Learning [M]. McGraw-Hill Companies, Inc. 1997.
[45] Harris C and Stephens M. A Combined Corner and Edge Detector [C]. Alvey Vision Conference, 1988:147-151.
[46] Schimid C, Mohr R, Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[47]曹晓光,徐琳,郁文筱.基于角点检测的高精度点匹配算法[J].仪器仪表学报. 2006,27(6):1269-1271.
[48]宋利,周源华,周军.基于特征匹配的鲁棒图像镶嵌[J]. 2004,38(5):783-786.
[49]王靖,朱梦宇,赵保军等.基于小波和改进型Hausdorff距离的遥感图像配准方法[J].电子学报. 2006,34(12):2167-2169.
[50]张登荣,蔡志刚,俞乐.基于匹配的遥感影像自动纠正方法研究[J].浙江大学学报(工学版). 2007,41(3):402-406.
[51]张登荣,俞乐,蔡志刚.点特征和小波金字塔技术的遥感图像快速匹配技术[J].浙江大学学报(理学版).2007,34(4):465-468.
[52] Yua L, Zhanga D, Holdenb E. A Fast and Fully Automatic Registration Approach Based on Point Features for Multi-Source Remote-Sensing Images [J]. Computers & Geosciences, 2007:1-11.
[53]梁志敏,高洪明,王志江等.摄像机标定中亚像素级角点检测算法[J].焊接学报. 2006,27(2):102-104.
[54]孙敏,李德玉,俞梦孙.基于Harris算子和K-means聚类的红外图像脸部特征自动定位[J].航天医学与医学工程. 2007,20(4):285-288.
[55]陈宇波,许海柱,黄婷婷等.在人脸图像中确定嘴巴位置的方法[J].电子科技大学学报. 2007,36(6):1308-1310.
[56]邢慧,颜景龙,张树江.一种基于角点特征的数字稳像算法研究[J].应用基础与工程科学学报. 2006,14(4):566-571.
[57]张鹏林,关泽群,王新洲.时间序列影像特征点提取与匹配算法研究[J].武汉大学学报信息科学版. 2004,29(4):329-332.
[58]彭勃,周文晖,刘济林.基于Hassis角点检测的立体视觉里程计[J].兵工学报. 2007,28(12):1498-1502.
[59]刘贵喜,王蕾.基于区域选择和特征点匹配的图像配准算法[J].光电子激光. 2007,18(8):999-1002.
[60]杨占龙,郭宝龙.基于兴趣点不变矩的图像拼接[J].光电子激光. 2007,18(6):738-740.
[61] Zhao Xuan, Wang Shengjin, Ding Xiaoqing. A Dynamic Generating Graphical Model for Point-Sets Matching [J]. Applied Mathematics and Computation. 2007,185:1109-1119.
[62] Lumini A, Nanni L. Detector of Image Orientation Based on Borda Count [J]. Pattern Recognition Letters. 2006, 27:180-186.
[63] Schimid C, Mohr R, Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[64] Hae-Yeoun L, InKoo K, HeungKyu L et. al. Evaluaton of Feature Extration Techniques for Robust Watermarking [J]. Lecture Notes in Computer Science. Germany: Springer, 2005(3710):418-431.
[65] Baumberg A. Reliable Feature Matching Across Widely Separated Views [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2000:774-781.
[66] Mikolajczyk K and Schmid C. Indexing Based on Scale Invariant Interest Points [C]. International Conference on Computer Vision, 2001, 1:525-531.
[67] Schimid C and Mohr R. Local Grayvalue Invariants for Image Retrieval [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5):530-534.
[68] Tuytelaars T and V Gool L J. Content–Based Image Retrieval Based on Local Affinely Invariant Regions [C]. International Conference on Visual Information and Information Systems, 1999:493-500.
[69] Zhen Z, Wang H, Teoh E. Analysis of Gray Level Corner Detection [J]. Pattern Recognition Letters. 1999, 20(2): 149-162.
[70]王付新,黄毓瑜,王田苗.三维重建中特征点提取算法的研究与实现[J].工程图学学报,2007,3:91-96.
[71]朱庆,吴波,万能等.具有良好重复率与信息量的立体影像点特征提取方法[J].电子学报. 2006, 34(2):205-209.
[72]刘富,侯涛,栾慧等.掌纹轮廓特征点提取新方法[J].吉林大学学报(工学版). 2007,37(4):897-900.
[73]韩秋蕾,姚志军,朱明.一种鲁棒的均值漂移与彩色特征点提取相结合的面部跟踪算法[J].电子器件. 2007,30(5):1712-1715.
[74]张美多,郭宝龙.车牌识别系统关键技术研究.计算机工程[J]. 2007,33(16):186-188.
[75]王君秋,查红彬.结合兴趣点和边缘的建筑吴物和物体识别方法[J].计算机辅助设计与图形学报. 2006,18(8):1257-1263.
[76] Xiaojun Q and Ji Q. A Robust Content-Based Digital Image Watermarking Scheme [J]. Signal Processing. 2007,87:1264-1280.
[77]陶茂垣,卢正鼎,袁武钢等.基于图像尺度空间的几何不变特征点提取算法[J].电子学报. 2006,34(12A):2565-2568.
[78] Smith S M and Brady J M. SUSAN-A New Approach to How Level Image Processing [J]. International Journal of Computer Vision, 1997, 23(34):45-78.
[79]张迁,刘政凯,庞龙伟等.一种遥感影像的自动配准方法[J].小型微型计算机系统. 2004,25(7):1129-1131.
[80]顾华,苏光大,杜成.人脸关键特征点的自动定位[J].光电子激光. 2004,15(8):975-979.
[81]王荣本,余天洪,顾柏圆.基于边界的车道标识线识别和跟踪方法研究[J].计算机工程. 2006,32(18):195-196.
[82] Mauricio H and Geovanni. Facial Feature Extracting Based on the Smallest Univalue Segment Assimilating Nucleus (SUSAN) Algorithm [C]. International Conference on Picture Coding Symposiump, 2004:261-266.
[83]赵志华,蔡健荣,赵杰文等. SUSAN算子在苹果图像缺陷分割中的应用研究[J].计算机工程. 2004,30(15):141-142.
[84]陈廉清,袁红彬,王龙山. SUSAN算子在微小轴承表面缺陷图像分割中的应用[J].光学技术. 2007,33(2):305-307.
[85] Etienne V and Robert L. Detecting and Matching Feature Points [J]. Journal of Visual Communication and Image Representation. 2005, 16(1):38-54.
[86] Kyu-Yeol C, Won-Pyo D and Chang-Sung J. SUSAN Window Based Cost Calculation for Fast Stereo Matching [C]. International Conference on Computational Intelligence and Security. 2005, 3802:947-952.
[87]闫奇,唐慧君,张变莲.基于改进SUSAN算法的箭环目标跟踪与测量[J].光子学报. 2007,36(10):1933-1938.
[88]毕务忠,严高师.基于改进SUSAN原则的小目标检测算法[J].激光与红外. 2006,36(6):504-507.
[89] Xun W, Jianqiu J, Yun L et al. Multi-Feature SUSAN Corner Detection Method [C]. International Society for Optical Engineering. 2005, 6044:1-7.
[90]邵泽明,朱剑英,王化明.基于SUSAN算法的分层快速角点检测[J].华南理工大学学报(自然科学版),2006,34(7):65-68
[91] Rosten E and Drummond T. Fusing Points and Lines for High Performance Tracking [C]. International Conference on Computer Vision, 2005:1508-1511.
[92] Rosten E and Drummond T. Machine Learning for High-Speed Corner Detection [C]. European Conference on Computer Vision, 2006:430-443.
[93] Quinlan J R. Induction of Decision Trees [J]. Machine Learning, 1986, 1:81-106.
[94]张玉冰,罗青山,曾贵华.基于部件的对象实时跟踪[J].计算机工程与应用. 2008, 44(7):69-71.
[95] Linderberg T. Feature Detection with Automatic Scale Selection [J]. International Journal of Computer Vision, 1998, 30(2):77-116.
[96] Tone M and Hamada. Scale Change and Rotation Invariant Digital Image Watermarking Method [J]. Systems and Computers in Japan. 2007, 38(10):1-9.
[97] Chang Z, Yaowu C, JayLin K. Fast Detection of Overlapped Areas in Smart Camera Network [J]. Chinese Journal of Scientific Instrument. 2007, 28(7):1153-1158.
[98] Viola P and Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features [C]. International Conference on Computer Vision and PatternRecognition, 2001:511-518.
[99] Brown M and Lowe D. Invariant Features from Invariant Point Groups [C]. BMVC, 2002:1-10.
[100] Kadir T and Brady M. Scale, Saliency and Image Description [J]. International Journal of Computer Vision. 2001, 45(2):83-105.
[101] Tuytelaars T and Van Gool L. Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions [C]. British Machine Vision Conference, 2000:412-425.
[102] Tuytelaars T and Van Gool L. Matching Widely Seperated Views Based on Affine Invariant Regions [J]. International Journal of Computer Vision, 2004, 1(59):61-85.
[103]李竹林,赵宗涛,刘彦保等.基于稳定极值区域的宽基线双目立体匹配算法[J].计算机工程,2007,33(22):212-216.
[104] Matas J, Chum O, Urban M et al. Robust Wide-Baseline Stereo from Maximally Stable Extremal Regions [J]. Image and Vision Computing, 2004, 22(10):761-767.
[105] Michal P, Jiri M and Stepan O. Stable Affine Frames on Isophotes [C]. IEEE International Conference on Computer Vision, 2007:1-8.
[106] Ke Y and Sukthankar R. PCA-SIFT: a More Distinctive Representation for Local Image Descriptors [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2004, 2:506-513.
[107] Mikolajczyk K and Schmid. A Performance Evaluation of Local Descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[108] Lazebnik S, Schmid C and Ponce J. A Sparse Texture Representation Using Local Affine Regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1265-1278.
[109] Gabor D. Theory of Communication [M]. J. Inst. Elet. Eng., 1946, 93:429-457.
[110] Van Gool L, Moons T and Ungureanu D. Affine/Photometric Invariants for Planar Intensity Patterns [C]. European Conference on Computer Vision, 1996, pagesⅠ:642-651.
[111] Koenderink J J and Van Doom A J. Representation of Local Geometry in the Visual System [J]. Biol. Cybern., 1987, 55(6):367-375.
[112] Florack L, Romeny B H, Koenderink J and Viergever M. Scale and the Differential Structure of Images [J]. Image and Vision Computing, 1992, 10(6):376-388.
[113] Lowe D G. Object Recognition from Local Scale-Invariant Features [C]. International Conference on Computer Vision, 1999:1150-1157.
[114] Linderberg T. Scale-Space for Discrete Signals [J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 1990, 12(3):234-254.
[115]王润生.图像理解[M].长沙:国防科技大学出版社,1995.
[116] Linderberg T and Eklundh J O. Scale Detection and Region Extration from a Scale-Space Primal Sketch [C]. International Conference on Computer Vision, 1990, 416-426.
[117] Linderberg T. Junction Detection with Automatic Selection of Detection Scales and Localization Scales [C]. IEEE International Conference on Image Processing, 1994, 924-928.
[118] Elazary, L, Itti, L. Interesting Objects are Visually Salient [J]. Journal of Vision, 2008, 8(3):1-15.
[119] Xia S P, Ren P and Hancock E R. Ranking the Local Invariant Features for the Robust Visual Saliencies [C], International Conference on Pattern Recognition, 2008.
[120] Lowe D G. The ViewPoint Consistency Constraint [J]. International Journal of Computer Vision, 1987, 1(1):57-72.
[121] Huttenlocher D P and Ullman S. Object Recognition Using Alignment [C]. International Conference on Computer Vision, 1987:102-111.
[122] Goad C. Special Purpose Automatic Programming for 3D model-Based Vision [C]. DARPA Image Understanding Workshop, 1983:371-381.
[123] Grimson W E L and Lozano-Perez T. Localizing Overlapping Parts by Searching the Interpretation Tree [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(4):469—482.
[124] Stockman G. Object Recognition and Localization Via Pose Clustering [J]. Computer Vision, Graphics and Image Processing, 1987, 40:361-387.
[125] Thompson D W and Mundy J L. Three-Dimentional Model Matching from an Unconstrained Viewpoint [C]. International Conference on Robotics and Automation, 1987:208-220.
[126] Fischler M A and Bolles R C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Amalysis and Automated Cartography [J]. Comm. Assoc. Comp. Mach., 1981, 24(6):381-395.
[127] Hartley R I and Zisserman A. Multiple View Geometry in Computer Vision [M]. Cambridge University Press, ISBN:0521623049, 2000.
[128] Lamdan Y, Schwarta J T and Wolfson H J. Object Recognition by Affine Invariant Matching [C]. IEEE Conference on Computer Vision and Pattern Recognition, 1988:335-344.
[129] Wolfson H J and Rigoutsos I. Geometric Hashing: An Overview [J]. IEEE Comput. Sci. Eng., 1997, 4(4):10-21.
[130] Rothwell C, Forsyth D, Zisserman A and Mundy J. Extracting Projective Structure from Single Perspective Views of 3D Point Sets [C]. International Conference on Computer Vision, 1993:573-582.
[131] Rubner Y, Tomasi C and Guibas L J. The Earth Mover’s Distance as a Metric for Image Retrieval [J]. International Journal of Computer Vision, 2000, 40(2):99-121.
[132] Murase H and Nayar S. Visual Learning and Recognition of 3D Object from Appearance [J]. International Journal of Computer Vision, 1995, 14(1).
[133] Turk M and Pentland A P. Face Recognition Using Eigenfaces [C]. IEEE Conference on Computer Vision and Pattern Recogntition, 1991:586-591.
[134] Nene S A, Nayar S K and Murase H. Columbia Object Image Library (COIL-100). Int J. of Comp. Vis., 1995, 14:5-24.
[135] Pontil M, Rogai S and Verri A. Recognition 3D Objects with Linear Support Vector Machines [C]. European Conference on Computer Vision, 1998:469-483.
[136] Schmid C and Zisserman A. Automatic Line Matching Across Views [C]. IEEE Conference on Computer Vision and Pattern Recognition, 1997:666-671.
[137] Harris C J and Stephens. A Combined Corner and Edge Detector [C]. The 4th Alvey Vision Conference, 1988:147-151.
[138] Ferrari V, Tuytelaars and Van Gool L. Simultaneous Object Recogntition and Segmentation by Image Exploration [C]. European Conference on Computer Vision, 2004, 1:40-54.
[139] Moreels P Maire M and Perona P. Recognition by Probabilistic Hypothesis Construction [C]. European Conference on Computer Vision, 2004, 2:55-68.
[140] Schaffalitzky F and Zisserman A. Multi-View Matching for Unordered Image Sets, or“How Do I Organize My Holiday Snaps?”. Eropean Conference on Computer Vision, 2002, 1:414-431.
[141] Kirby M and Sirovich L. Applications of the Karhunen-Loeve Procedure for the Characterization of Human Faces [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(1):103-108.
[142] Turk M and Pentland A. Eigenfaces for Recognition [J]. Journal of Cognitive Neuroscience, 1991, 3(1).
[143] Rowley H, Baluja S and Kanade T. Neural Network-Based Face Detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-38.
[144] Viola P and Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features [C]. IEEE Conference on Computer and Pattern Recognition, 2001:511-518.
[145] Freund Y and Schapire R E. A Decision-Theoretic Generalization of On-LineLearning and an Application to Boosting [J]. Journal of Computer and System Sciences, 1997, 55(1):119-139.
[146] Opelt A, Fussenegger M, Pinz A and Auer P. Weak Hypotheses and Boosting for Generic Object Detection and Recognition [C]. European Conference on Computer Vision, 2004, 2:71-84.
[147] Ferfus R and Perona P. Caltech Object Category Datasets. http://www.vision.caltech.edu/html-files/archive.html, 2003.
[148] Opelt, A, Fussenggger M, Pinz A and Auer p. Graz Object Category Datasets. http://www.emt.tugraz.at/~pinz/data, 2005.
[149] Fergus R, Perona P and Zisserman A. Object Class Recognition by Unsupervised Scale-Invariant Learning [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2003:264-271.
[150] Burl M C, Leung T K and Perona. Face Localization Via Shape Statistics [C]. Workshop on Automatic Face and Gesture Recognition, 1995.
[151] Weber M, Welling M and Perona P. Unsupervised Learning of Models for Recognition [C]. Eropean Conference on Computer Vision, 2000, 1:18-32.
[152] Li Fei-Fei, Fergus R and Perona P. A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories [C]. International Conference on Computer Vision, 2003:1134-1141.
[153] Csurka G, Dance C R, Fan L, Willamowski J and Bray C. Visual Categorization with Bags of Keypoints [C]. European Conference on Computer Vision, 2004:1-22.
[154] Baeza-Yates R and Ribeiro-Neto B. Modern Information Retrieval [C]. ACM Press, ISBN: 020139829, 1999.
[155] Philbin J, Chum O, Isard M, Sivic J and Zisserman A. Object Retrieval with Large Vocabularies and Fast Spatial Matching [C]. IEEE International Conference on Computer Vision and Pattern Recognition, 2007.
[156] Hofmann T. Probabilistic Latent Smantic Indexing [C]. SIGIR, 1999.
[157] Hofmann T. Unsupervised Learning by Probabilistic Latent Semantic Analysis [J]. Machine Learning, 2001, 43:177-196.
[158] Blei D, Ng A and Jordan M. Latent Dirichlet Allocation [J]. Journal of Machine Learning Research, 2003, 3:993-1022.
[159] Vapnik V N. Statistical Learning Theory [M]. Wiley- Interscience, 1998.
[160] Schonemann P. A Generalized Solution of the Orthogonal Procrustes Problem [J]. Psychometrika, 1966, 31(3):1-10.
[161] Golub G H and Loan C F. Matrix Computation [C]. 3rd ed., Science Press, 2001.
[162] Green and Goers. A problem with Congruence [C]. Annual Meeting of THE Psychometric Society, 1979.
[163] J M F Ten Berge and D L Konl. Orthogonal Rotations to Maximal Agreement for Two or More Matrices of Different Column Orders [J]. Psychometrica, 1984, 49:49-55.
[164]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002.
[165] Everingham M, Gool L V, Williams C, Winn J and Zisserman A. Overview and Results of Classification Challenge, 2007 [C]. The PASACAL VOC’07 Challenge Workshop, in conj. With ICCV.
[166] Fawcett T. ROC Graphs: Notes and Practical Considerations for Reseachers, 2004.
[167] Frey B J and Duech D. Clustering by Passing Messages Between Data Points [J]. Science, 2007, 315:972-976.
[168] Mezard M. Where Are the Exempars? [J]. Science, 2007, 315:949-951.
[2] http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2009/.
[3] Chung F. Spectral Graph Theory [C]. CBMS Regional Conference Series in Mathematics, Conference Board of the American Mathematical Science, Washington, DC. 1997, 92.
[4] Berge C. Hypergraphs [M], North-Holland, 1989.
[5] Bebis G, Georgiopoulos M and Lobo N V. learning Geometric Hashing Functions for Model-based Object Recognition [C]. International Conference on Computer Vision, 1995:543-548.
[6] Cyr C and Kimia B. 3D Object Recognition Using Similarity-based Aspect Graph [C]. International Conference on Computer Vision, 2001:254-261.
[7] Murase H and Nayar S. Visual Learning and Recognition of 3D Objects from Appearance [J]. International Joural of Computer Vision, 1995, 14(1).
[8] Swain M J and Ballard B H. Color Indexing [J]. International Joural of Computer Vision, 1991, 7(1):11-32.
[9] Selinger A and Nelson R C. A Perceptual Grouping Hierarchy for Appearance-based 3d Object Recognition [J]. Computer Vision and Image Understanding, 1999, 76(1):83-92.
[10] Lowe D. Distinctive Image Features from Scale-invariant Keypoints [J]. International Joural of Computer Vision, 2004, 60(2):91-110.
[11] Mikolajczyk K and Schmid C. An Affine Invariant Interest Point Detector [C]. European Conference on Computer Vision, 2002:128-142.
[12] Obrdzalek S and Matas J. Object Recognition Using Local Affine Frames on Distinguished Regions [C]. BMVC, 2002:414-431.
[13] Rothganger F Lazebnik S Schmid C and Ponce J. 3D Object Modeling and Recognition Using Local Affine-invariant Image descriptors and Multi-view Spatial Constraints [J]. International Joural of Computer Vision, 2006, 66(3):231-259.
[14] Tuyelaars T and Van-Gool L. Wide Baseline Stereo Based on Local, Affinely Invariant Regions [C]. BMVC, 2000.
[15] Mikolajczyk K and Schmid C. Indexing Based on Scale-invariant Interest Points [C]. International Conference on Computer Vision, 2001, 1:525-531.
[16] Baumberg A. Reliable Feature Matching Across Widely Separated Views [C]. International Conference on Computer Vision, 2000:774-781.
[17] Matas J, Chum O, Urban M and Pajdla T. Robust Wide Baseline Stereo fromMaximally Stable Extremal Regions. BMVC, 2002:384-393.
[18] Schaffalitzky F and Zisserman A. Automated Scene Maching in Movies [C]. In Workshop on Content-Based Image and Video Retrieval, 2002:186-197.
[19] Tuytelaars T, Van-Gool L and Koch R. Matching Affinely Invatiant Regions for Visual Servoing [C]. In Intl. Conference on Robotics and Automation, 1999:1601-1606.
[20] Bay H, Tuytelaars T and Gool L V. SURF: Speeded Up Robust Features [C]. European Conference on Computer Vision, 2006, 3951(1):404-417.
[21] Kadir T, Brady M and Zisserman A. An Invariant Method for Selecting Salient Regions in Images [C]. European Conference on Computer Vision, 2004, 1(1):345-457.
[22] Mikolajczyk K and Schmid C. Scale and Affine Invariant Interest Point Detectors [J]. International Journal of Computer Vision, 2004, 60(1):63-86.
[23] Linderberg T. Feature Detection with Automatic Scale Selection [J]. International Journal of Computer Vision, 1998, 30(2):79-116.
[24] Zhang J, Marszalek M, Lazebnik S and Schmid C. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study [J]. International Journal of Computer Vision, 2007, 73(2):213-238.
[25] Mikolajczyk K and Schmid C. A Performance Evaluation of Local Descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[26] Tuytelaarsl T and Mikolajczyk Krystian. Local Invariant Feature Detectors: A Survey [J]. Computer Graphics and Vision, 2007, 3(3):177-280.
[27] Li F F and Perona P. A Bayesian Hierarchical model for Learning Natural Scene Categories [C]. International Conference on Computer Vision and Pattern Recognition, 2005, 2(2):524-531.
[28] Sivic J, Russell B C, Efros A A, Zisserman A and Freeman W T. Discovering Objects and Their Location in Images [C]. International Conference on Computer Vision, 2005, 1(1):872-877.
[29] Torralba A, Fergus R and Weiss Y. Small Codes and Large Image Databases for Recognition [C]. International Conference on Computer Vision, 2008.
[30] Eric Nowak etc. al. Sampling Strategies for Bag-of-Features Image Classification [C]. European Conference on Computer Vision, 2006, 3954:490-503.
[31] Philbin J, Sivic J and Zisserman A. Geometric Latent Dirichlet Allocation (gLDA) Model for Unsupervised Particular Object Discovery in Unordered Image Collections [C]. BMVC, 2008.
[32] Nister D and Stewenius. Scalable Recognition with a Vocabulary Tree [C]. International Conference on Computer Vision and Pattern Recognition, 2006,2(2):2161-2168.
[33] Qingfang Zheng and Wen Gao. Constructing Visual Phrases for Effective and Efficient Object-Based Image Retrieval [J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2008, 5(1), Article 7:1-19.
[34]夏胜平,刘建军,袁振涛,虞华,张乐锋,郁文贤.基于集群的并行分布式RSOM聚类[J].电子学报,2007,35(3):385-391.
[35] Crandall D J and Huttenlocher D P. Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition [C]. European Conference on Computer Vision, 2006, 3951(1):16-29.
[36] Jiang X, Munger A and Bunke H. On Median Graphs: Properties, Algorithms and Applications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(10):1144-1151.
[37] Torsello A and Hancock E. Learning Shape-Classes Using a Mixture of Treeunions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(6):954-967.
[38] Bonev B, Escolano F, Lozano M A, Suau P, Cazorla M A and Aguilar W. Constellations and the Unsupervised Learning of Graphs [C]. Graph-Based Representations in Pattern Recognition, 2007, 14(1):340-350.
[39] Lowe D. Local Feature View Clustering for 3d Object Recognition [C]. International Conference on Computer Vision and Pattern Recognition, 2001, 2(1):1682-1688.
[40] Ferrari V, Tuytelaara T and Van-Gool L. Simultaneous Object Recogntiion and Segmentation from Single or Multiple Model Views [J]. International Journal of Computer Vision, 2006, 67(2):159-188.
[41]陈静,夏胜平.几种典型模式识别分类器武断性的分析[J].计算机研究与发展. 2007,5B:32-36.
[42] Todorovic S and Ahuja N. Unsupervised Category Modeling, Recognition and Segmentation in Iamges [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009.
[43] http://www.lotushill.org/
[44] Mitchell Tom M. Machine Learning [M]. McGraw-Hill Companies, Inc. 1997.
[45] Harris C and Stephens M. A Combined Corner and Edge Detector [C]. Alvey Vision Conference, 1988:147-151.
[46] Schimid C, Mohr R, Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[47]曹晓光,徐琳,郁文筱.基于角点检测的高精度点匹配算法[J].仪器仪表学报. 2006,27(6):1269-1271.
[48]宋利,周源华,周军.基于特征匹配的鲁棒图像镶嵌[J]. 2004,38(5):783-786.
[49]王靖,朱梦宇,赵保军等.基于小波和改进型Hausdorff距离的遥感图像配准方法[J].电子学报. 2006,34(12):2167-2169.
[50]张登荣,蔡志刚,俞乐.基于匹配的遥感影像自动纠正方法研究[J].浙江大学学报(工学版). 2007,41(3):402-406.
[51]张登荣,俞乐,蔡志刚.点特征和小波金字塔技术的遥感图像快速匹配技术[J].浙江大学学报(理学版).2007,34(4):465-468.
[52] Yua L, Zhanga D, Holdenb E. A Fast and Fully Automatic Registration Approach Based on Point Features for Multi-Source Remote-Sensing Images [J]. Computers & Geosciences, 2007:1-11.
[53]梁志敏,高洪明,王志江等.摄像机标定中亚像素级角点检测算法[J].焊接学报. 2006,27(2):102-104.
[54]孙敏,李德玉,俞梦孙.基于Harris算子和K-means聚类的红外图像脸部特征自动定位[J].航天医学与医学工程. 2007,20(4):285-288.
[55]陈宇波,许海柱,黄婷婷等.在人脸图像中确定嘴巴位置的方法[J].电子科技大学学报. 2007,36(6):1308-1310.
[56]邢慧,颜景龙,张树江.一种基于角点特征的数字稳像算法研究[J].应用基础与工程科学学报. 2006,14(4):566-571.
[57]张鹏林,关泽群,王新洲.时间序列影像特征点提取与匹配算法研究[J].武汉大学学报信息科学版. 2004,29(4):329-332.
[58]彭勃,周文晖,刘济林.基于Hassis角点检测的立体视觉里程计[J].兵工学报. 2007,28(12):1498-1502.
[59]刘贵喜,王蕾.基于区域选择和特征点匹配的图像配准算法[J].光电子激光. 2007,18(8):999-1002.
[60]杨占龙,郭宝龙.基于兴趣点不变矩的图像拼接[J].光电子激光. 2007,18(6):738-740.
[61] Zhao Xuan, Wang Shengjin, Ding Xiaoqing. A Dynamic Generating Graphical Model for Point-Sets Matching [J]. Applied Mathematics and Computation. 2007,185:1109-1119.
[62] Lumini A, Nanni L. Detector of Image Orientation Based on Borda Count [J]. Pattern Recognition Letters. 2006, 27:180-186.
[63] Schimid C, Mohr R, Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000, 37(2):151-172.
[64] Hae-Yeoun L, InKoo K, HeungKyu L et. al. Evaluaton of Feature Extration Techniques for Robust Watermarking [J]. Lecture Notes in Computer Science. Germany: Springer, 2005(3710):418-431.
[65] Baumberg A. Reliable Feature Matching Across Widely Separated Views [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2000:774-781.
[66] Mikolajczyk K and Schmid C. Indexing Based on Scale Invariant Interest Points [C]. International Conference on Computer Vision, 2001, 1:525-531.
[67] Schimid C and Mohr R. Local Grayvalue Invariants for Image Retrieval [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5):530-534.
[68] Tuytelaars T and V Gool L J. Content–Based Image Retrieval Based on Local Affinely Invariant Regions [C]. International Conference on Visual Information and Information Systems, 1999:493-500.
[69] Zhen Z, Wang H, Teoh E. Analysis of Gray Level Corner Detection [J]. Pattern Recognition Letters. 1999, 20(2): 149-162.
[70]王付新,黄毓瑜,王田苗.三维重建中特征点提取算法的研究与实现[J].工程图学学报,2007,3:91-96.
[71]朱庆,吴波,万能等.具有良好重复率与信息量的立体影像点特征提取方法[J].电子学报. 2006, 34(2):205-209.
[72]刘富,侯涛,栾慧等.掌纹轮廓特征点提取新方法[J].吉林大学学报(工学版). 2007,37(4):897-900.
[73]韩秋蕾,姚志军,朱明.一种鲁棒的均值漂移与彩色特征点提取相结合的面部跟踪算法[J].电子器件. 2007,30(5):1712-1715.
[74]张美多,郭宝龙.车牌识别系统关键技术研究.计算机工程[J]. 2007,33(16):186-188.
[75]王君秋,查红彬.结合兴趣点和边缘的建筑吴物和物体识别方法[J].计算机辅助设计与图形学报. 2006,18(8):1257-1263.
[76] Xiaojun Q and Ji Q. A Robust Content-Based Digital Image Watermarking Scheme [J]. Signal Processing. 2007,87:1264-1280.
[77]陶茂垣,卢正鼎,袁武钢等.基于图像尺度空间的几何不变特征点提取算法[J].电子学报. 2006,34(12A):2565-2568.
[78] Smith S M and Brady J M. SUSAN-A New Approach to How Level Image Processing [J]. International Journal of Computer Vision, 1997, 23(34):45-78.
[79]张迁,刘政凯,庞龙伟等.一种遥感影像的自动配准方法[J].小型微型计算机系统. 2004,25(7):1129-1131.
[80]顾华,苏光大,杜成.人脸关键特征点的自动定位[J].光电子激光. 2004,15(8):975-979.
[81]王荣本,余天洪,顾柏圆.基于边界的车道标识线识别和跟踪方法研究[J].计算机工程. 2006,32(18):195-196.
[82] Mauricio H and Geovanni. Facial Feature Extracting Based on the Smallest Univalue Segment Assimilating Nucleus (SUSAN) Algorithm [C]. International Conference on Picture Coding Symposiump, 2004:261-266.
[83]赵志华,蔡健荣,赵杰文等. SUSAN算子在苹果图像缺陷分割中的应用研究[J].计算机工程. 2004,30(15):141-142.
[84]陈廉清,袁红彬,王龙山. SUSAN算子在微小轴承表面缺陷图像分割中的应用[J].光学技术. 2007,33(2):305-307.
[85] Etienne V and Robert L. Detecting and Matching Feature Points [J]. Journal of Visual Communication and Image Representation. 2005, 16(1):38-54.
[86] Kyu-Yeol C, Won-Pyo D and Chang-Sung J. SUSAN Window Based Cost Calculation for Fast Stereo Matching [C]. International Conference on Computational Intelligence and Security. 2005, 3802:947-952.
[87]闫奇,唐慧君,张变莲.基于改进SUSAN算法的箭环目标跟踪与测量[J].光子学报. 2007,36(10):1933-1938.
[88]毕务忠,严高师.基于改进SUSAN原则的小目标检测算法[J].激光与红外. 2006,36(6):504-507.
[89] Xun W, Jianqiu J, Yun L et al. Multi-Feature SUSAN Corner Detection Method [C]. International Society for Optical Engineering. 2005, 6044:1-7.
[90]邵泽明,朱剑英,王化明.基于SUSAN算法的分层快速角点检测[J].华南理工大学学报(自然科学版),2006,34(7):65-68
[91] Rosten E and Drummond T. Fusing Points and Lines for High Performance Tracking [C]. International Conference on Computer Vision, 2005:1508-1511.
[92] Rosten E and Drummond T. Machine Learning for High-Speed Corner Detection [C]. European Conference on Computer Vision, 2006:430-443.
[93] Quinlan J R. Induction of Decision Trees [J]. Machine Learning, 1986, 1:81-106.
[94]张玉冰,罗青山,曾贵华.基于部件的对象实时跟踪[J].计算机工程与应用. 2008, 44(7):69-71.
[95] Linderberg T. Feature Detection with Automatic Scale Selection [J]. International Journal of Computer Vision, 1998, 30(2):77-116.
[96] Tone M and Hamada. Scale Change and Rotation Invariant Digital Image Watermarking Method [J]. Systems and Computers in Japan. 2007, 38(10):1-9.
[97] Chang Z, Yaowu C, JayLin K. Fast Detection of Overlapped Areas in Smart Camera Network [J]. Chinese Journal of Scientific Instrument. 2007, 28(7):1153-1158.
[98] Viola P and Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features [C]. International Conference on Computer Vision and PatternRecognition, 2001:511-518.
[99] Brown M and Lowe D. Invariant Features from Invariant Point Groups [C]. BMVC, 2002:1-10.
[100] Kadir T and Brady M. Scale, Saliency and Image Description [J]. International Journal of Computer Vision. 2001, 45(2):83-105.
[101] Tuytelaars T and Van Gool L. Wide Baseline Stereo Matching Based on Local, Affinely Invariant Regions [C]. British Machine Vision Conference, 2000:412-425.
[102] Tuytelaars T and Van Gool L. Matching Widely Seperated Views Based on Affine Invariant Regions [J]. International Journal of Computer Vision, 2004, 1(59):61-85.
[103]李竹林,赵宗涛,刘彦保等.基于稳定极值区域的宽基线双目立体匹配算法[J].计算机工程,2007,33(22):212-216.
[104] Matas J, Chum O, Urban M et al. Robust Wide-Baseline Stereo from Maximally Stable Extremal Regions [J]. Image and Vision Computing, 2004, 22(10):761-767.
[105] Michal P, Jiri M and Stepan O. Stable Affine Frames on Isophotes [C]. IEEE International Conference on Computer Vision, 2007:1-8.
[106] Ke Y and Sukthankar R. PCA-SIFT: a More Distinctive Representation for Local Image Descriptors [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2004, 2:506-513.
[107] Mikolajczyk K and Schmid. A Performance Evaluation of Local Descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630.
[108] Lazebnik S, Schmid C and Ponce J. A Sparse Texture Representation Using Local Affine Regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1265-1278.
[109] Gabor D. Theory of Communication [M]. J. Inst. Elet. Eng., 1946, 93:429-457.
[110] Van Gool L, Moons T and Ungureanu D. Affine/Photometric Invariants for Planar Intensity Patterns [C]. European Conference on Computer Vision, 1996, pagesⅠ:642-651.
[111] Koenderink J J and Van Doom A J. Representation of Local Geometry in the Visual System [J]. Biol. Cybern., 1987, 55(6):367-375.
[112] Florack L, Romeny B H, Koenderink J and Viergever M. Scale and the Differential Structure of Images [J]. Image and Vision Computing, 1992, 10(6):376-388.
[113] Lowe D G. Object Recognition from Local Scale-Invariant Features [C]. International Conference on Computer Vision, 1999:1150-1157.
[114] Linderberg T. Scale-Space for Discrete Signals [J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 1990, 12(3):234-254.
[115]王润生.图像理解[M].长沙:国防科技大学出版社,1995.
[116] Linderberg T and Eklundh J O. Scale Detection and Region Extration from a Scale-Space Primal Sketch [C]. International Conference on Computer Vision, 1990, 416-426.
[117] Linderberg T. Junction Detection with Automatic Selection of Detection Scales and Localization Scales [C]. IEEE International Conference on Image Processing, 1994, 924-928.
[118] Elazary, L, Itti, L. Interesting Objects are Visually Salient [J]. Journal of Vision, 2008, 8(3):1-15.
[119] Xia S P, Ren P and Hancock E R. Ranking the Local Invariant Features for the Robust Visual Saliencies [C], International Conference on Pattern Recognition, 2008.
[120] Lowe D G. The ViewPoint Consistency Constraint [J]. International Journal of Computer Vision, 1987, 1(1):57-72.
[121] Huttenlocher D P and Ullman S. Object Recognition Using Alignment [C]. International Conference on Computer Vision, 1987:102-111.
[122] Goad C. Special Purpose Automatic Programming for 3D model-Based Vision [C]. DARPA Image Understanding Workshop, 1983:371-381.
[123] Grimson W E L and Lozano-Perez T. Localizing Overlapping Parts by Searching the Interpretation Tree [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(4):469—482.
[124] Stockman G. Object Recognition and Localization Via Pose Clustering [J]. Computer Vision, Graphics and Image Processing, 1987, 40:361-387.
[125] Thompson D W and Mundy J L. Three-Dimentional Model Matching from an Unconstrained Viewpoint [C]. International Conference on Robotics and Automation, 1987:208-220.
[126] Fischler M A and Bolles R C. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Amalysis and Automated Cartography [J]. Comm. Assoc. Comp. Mach., 1981, 24(6):381-395.
[127] Hartley R I and Zisserman A. Multiple View Geometry in Computer Vision [M]. Cambridge University Press, ISBN:0521623049, 2000.
[128] Lamdan Y, Schwarta J T and Wolfson H J. Object Recognition by Affine Invariant Matching [C]. IEEE Conference on Computer Vision and Pattern Recognition, 1988:335-344.
[129] Wolfson H J and Rigoutsos I. Geometric Hashing: An Overview [J]. IEEE Comput. Sci. Eng., 1997, 4(4):10-21.
[130] Rothwell C, Forsyth D, Zisserman A and Mundy J. Extracting Projective Structure from Single Perspective Views of 3D Point Sets [C]. International Conference on Computer Vision, 1993:573-582.
[131] Rubner Y, Tomasi C and Guibas L J. The Earth Mover’s Distance as a Metric for Image Retrieval [J]. International Journal of Computer Vision, 2000, 40(2):99-121.
[132] Murase H and Nayar S. Visual Learning and Recognition of 3D Object from Appearance [J]. International Journal of Computer Vision, 1995, 14(1).
[133] Turk M and Pentland A P. Face Recognition Using Eigenfaces [C]. IEEE Conference on Computer Vision and Pattern Recogntition, 1991:586-591.
[134] Nene S A, Nayar S K and Murase H. Columbia Object Image Library (COIL-100). Int J. of Comp. Vis., 1995, 14:5-24.
[135] Pontil M, Rogai S and Verri A. Recognition 3D Objects with Linear Support Vector Machines [C]. European Conference on Computer Vision, 1998:469-483.
[136] Schmid C and Zisserman A. Automatic Line Matching Across Views [C]. IEEE Conference on Computer Vision and Pattern Recognition, 1997:666-671.
[137] Harris C J and Stephens. A Combined Corner and Edge Detector [C]. The 4th Alvey Vision Conference, 1988:147-151.
[138] Ferrari V, Tuytelaars and Van Gool L. Simultaneous Object Recogntition and Segmentation by Image Exploration [C]. European Conference on Computer Vision, 2004, 1:40-54.
[139] Moreels P Maire M and Perona P. Recognition by Probabilistic Hypothesis Construction [C]. European Conference on Computer Vision, 2004, 2:55-68.
[140] Schaffalitzky F and Zisserman A. Multi-View Matching for Unordered Image Sets, or“How Do I Organize My Holiday Snaps?”. Eropean Conference on Computer Vision, 2002, 1:414-431.
[141] Kirby M and Sirovich L. Applications of the Karhunen-Loeve Procedure for the Characterization of Human Faces [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(1):103-108.
[142] Turk M and Pentland A. Eigenfaces for Recognition [J]. Journal of Cognitive Neuroscience, 1991, 3(1).
[143] Rowley H, Baluja S and Kanade T. Neural Network-Based Face Detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1):23-38.
[144] Viola P and Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features [C]. IEEE Conference on Computer and Pattern Recognition, 2001:511-518.
[145] Freund Y and Schapire R E. A Decision-Theoretic Generalization of On-LineLearning and an Application to Boosting [J]. Journal of Computer and System Sciences, 1997, 55(1):119-139.
[146] Opelt A, Fussenegger M, Pinz A and Auer P. Weak Hypotheses and Boosting for Generic Object Detection and Recognition [C]. European Conference on Computer Vision, 2004, 2:71-84.
[147] Ferfus R and Perona P. Caltech Object Category Datasets. http://www.vision.caltech.edu/html-files/archive.html, 2003.
[148] Opelt, A, Fussenggger M, Pinz A and Auer p. Graz Object Category Datasets. http://www.emt.tugraz.at/~pinz/data, 2005.
[149] Fergus R, Perona P and Zisserman A. Object Class Recognition by Unsupervised Scale-Invariant Learning [C]. IEEE Conference on Computer Vision and Pattern Recognition, 2003:264-271.
[150] Burl M C, Leung T K and Perona. Face Localization Via Shape Statistics [C]. Workshop on Automatic Face and Gesture Recognition, 1995.
[151] Weber M, Welling M and Perona P. Unsupervised Learning of Models for Recognition [C]. Eropean Conference on Computer Vision, 2000, 1:18-32.
[152] Li Fei-Fei, Fergus R and Perona P. A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories [C]. International Conference on Computer Vision, 2003:1134-1141.
[153] Csurka G, Dance C R, Fan L, Willamowski J and Bray C. Visual Categorization with Bags of Keypoints [C]. European Conference on Computer Vision, 2004:1-22.
[154] Baeza-Yates R and Ribeiro-Neto B. Modern Information Retrieval [C]. ACM Press, ISBN: 020139829, 1999.
[155] Philbin J, Chum O, Isard M, Sivic J and Zisserman A. Object Retrieval with Large Vocabularies and Fast Spatial Matching [C]. IEEE International Conference on Computer Vision and Pattern Recognition, 2007.
[156] Hofmann T. Probabilistic Latent Smantic Indexing [C]. SIGIR, 1999.
[157] Hofmann T. Unsupervised Learning by Probabilistic Latent Semantic Analysis [J]. Machine Learning, 2001, 43:177-196.
[158] Blei D, Ng A and Jordan M. Latent Dirichlet Allocation [J]. Journal of Machine Learning Research, 2003, 3:993-1022.
[159] Vapnik V N. Statistical Learning Theory [M]. Wiley- Interscience, 1998.
[160] Schonemann P. A Generalized Solution of the Orthogonal Procrustes Problem [J]. Psychometrika, 1966, 31(3):1-10.
[161] Golub G H and Loan C F. Matrix Computation [C]. 3rd ed., Science Press, 2001.
[162] Green and Goers. A problem with Congruence [C]. Annual Meeting of THE Psychometric Society, 1979.
[163] J M F Ten Berge and D L Konl. Orthogonal Rotations to Maximal Agreement for Two or More Matrices of Different Column Orders [J]. Psychometrica, 1984, 49:49-55.
[164]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002.
[165] Everingham M, Gool L V, Williams C, Winn J and Zisserman A. Overview and Results of Classification Challenge, 2007 [C]. The PASACAL VOC’07 Challenge Workshop, in conj. With ICCV.
[166] Fawcett T. ROC Graphs: Notes and Practical Considerations for Reseachers, 2004.
[167] Frey B J and Duech D. Clustering by Passing Messages Between Data Points [J]. Science, 2007, 315:972-976.
[168] Mezard M. Where Are the Exempars? [J]. Science, 2007, 315:949-951.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |