图像局部不变特征提取技术研究及其应用
|
摘要
目标上局部不变特征的提取是图像处理、数字水印、拷贝检测、视频检索等众多计算机视觉领域的研究基础。由于大部分目标之间均存在视角、尺度、旋转以及模糊、局部遮挡、复杂背景等广义仿射变换,因此如何使提取的局部不变特征具有良好的稳定性、可重复性和可匹配性成为视觉领域的一个重点研究问题。
针对原始最大稳定极值区域算法的时间复杂度高、区域被覆盖以及形状不规则等缺点,构建了一种并行使用优化的邻域四叉树数据结构、基于成分树的最大稳定判定条件和基于向量的二阶中心矩调形通式的检测子,提取出加速的椭圆形最大稳定极值区域(Elliptical Maximally Stable Extremal Regions-Accelerative,EMSER-A)。在图像像素点排序的基础之上,根据使用按秩合并和路径压缩优化的邻域四叉树数据结构提取基于灰度阈值变化的极值区域,有效恢复了最终变成一个像素值和灰度阈值的区域的全部信息。使用极值区域作为结点构建成分树,并得到最大稳定判定条件。为了便于后续的特征描述,构建了基于向量的二阶中心矩调形通式,并将该通式降维为二维协方差矩阵,把不规则形状区域调整为椭圆形。EMSER-A检测子在保证可重复性的前提下,将时间复杂度由O(nloglogn)降低到O(Na(N))。特征提取和匹配实验表明:当存在广义仿射变换时,该检测子仍能提取数量较多且具有一定独特性的局部特征。可重复性比较实验证明:EMSER-A具有较为理想的视角、尺度、旋转、光照和模糊不变性。
为了解决特征点的定位精度不高、区域仿射形状的难以调整以及特征的弱仿射不变性等问题,论文还构建了基于点区域的仿射不变性检测子。证明了规范化LoG图像导数的尺度不变性,为特征尺度的确定提供了理论基础。提出了特征尺度的定性和定量定义,完善和发展了特征尺度的性质。系统地证明了仿射高斯尺度空间内形状自适应矩阵的仿射不变性以及基于该矩阵的规范化区域之间的旋转关系。给出了迭代过程中积分尺度和微分尺度的确定准则以及微分尺度对提高检测子抗噪性的影响。建立了基于仿射形状自适应矩阵的空间位置迭代矩阵,并使用该矩阵完成了从规范化区域到图像域的转换。在上述理论支撑下,构建了联合规范化LoG方程、多尺度Harris度量、仿射形状自适应矩阵以及空间位置迭代矩阵的仿射不变性检测子(Location/Scale/Shape-Iterative,LS~2-I),同步迭代出点区域的空间位置、特征尺度以及仿射邻域形状。特征提取和匹配实验表明:在存在广义仿射变换的同一个场景的两幅图像上提取特征区域,经过位置、尺度和形状的同步迭代,收敛的特征点邻域形状在规范化图像域内显示一致,实现了对特征点的精确定位和特征区域形状的仿射调整,并取得了理想的匹配结果。可重复性比较实验证明:在视角、尺度、旋转、光照变化以及存在模糊的情况下,LS~2-I具有较为理想的可重复性。
为了验证EMSER-A和LS~2-I的可匹配性及稳定性,论文构建了相应的图像检索机制。论文首先以EMSER-A和LS~2-I为底层局部特征区域,生成SIFT描述子并聚类成基于矢量量化的视觉关键词表,结合标准加权思想和衡量不变特征的相似性准则,提出了基于框选目标区域的检索方法,依据相似度得分对检索结果进行一次排序。为了更有效的发挥特征区域的不变性,论文提出了基于搜索单元区域匹配法和基于簇的空间一致性度量准则。前者根据EMSER-A和LS~2-I椭圆形特征区域的仿射协变性,在目标区域和被检图像上分别以某两个已匹配的椭圆形特征区域作为搜索单元,在该搜索单元内进行基于原匹配和新匹配之间关系的区域匹配,并删除零分匹配区域,最后根据得分情况对图像进行二次排序。后者根据正确匹配对空间角之间的关系,提出一种有效去除误匹配的基于簇的空间一致性滤波方法。论文构建了四种不同的检索机制,检索实验证明了特征区域EMSER-A和LS~2-I的可匹配性及基于目标区域和空间一致性检索机制的正确性。同时,增大图像库容量的对比实验和广义检索实验证明了特征区域及检索机制的稳定性和正确性。
The extraction of local invariant feature in the target is the research fundament in computer vision field,for example image processing,digital watermarking,copy detection and video retrieval.Because there are generalized affine transformations,such as viewpoint, scale,rotation,blur,partial occlusion and complex background,among most of targets,when generalized affine transformation occurred,it is concentrated in vision field to make the local invariant feature of good stability,repeatability and matching.
With respect to the shortcomings of high time complexity,regions overlapping and shape irregularity for original Maximally Stable Extremal Regions detector,the dissertation constructs a detector in parallel use of optimization neighborhood quadtree data structures, maximally stability criterion based on component tree and shape modification general expression with second order central moment based on vector;and then extracts Elliptical Maximally Stable Extremal Regions-Accelerative(EMSER-A).Based on pixel ordering, optimization neighborhood quadtree with path compression and union by rank are used to extract extremal regions based on intensity thresholds changing,which efficiently restore all of the information in the region that finally turned into one pixel and one intensity threshold. Extremal regions are used as nods to construct component tree,and maximally stability criterion is obtained by moving in the tree.For the convenience of the description for feature region,it establishes shape modification general expression with second order central moment based on vector,and reduces the dimensionality of the general expression to 2D covariance matrix,modifies irregularly regions to ellipse.Under the condition of ensuring repeatability, the EMSER-A recedes time complexity from O(nloglogn) to O(Na(N)).The experiments of extraction and matching show that,even on the occasions of generalized affine transformations,the detector can extract numerous distinctive local feature.The comparison experiment in repeatability proves that EMSER-A has the invariant in viewpoint,scale, rotation,brightness and blur.
For resolving the problems including the lower location precision of the feature point, difficulty to modifying affine shape of the region and the poor affine invariance of the feature, the dissertation also constructs the detector based on point regions.It demonstrates the scale invariance of normalized Laplacian-of-Gaussian image derivatives,which provides theoretical fundament for characteristic scales.It presents qualitative and quantitative definition,also further improves and develops the properties of characteristic scales.It systematically testifies to the affine invariance of shape-adapted matrix and the rotation relation between the two normalized regions based on the matrix.It establishes the determining principles of the integration scale and the differentiation scale,and analyzes the impact of differentiation scale on the antinoise performance.It builds the space location iterative matrix based on affine shape-adapted matrix and realizes the conversion from the normalized regions to the image domain.With the support of theories mentioned above,Location/Scale/Shape-Iterative(LS~2-I) is constructed combined with the normalized Laplacian-of-Gaussian,multi-scale Harris measure,affine shape-adapted matrix and space location iterative matrix,and synchronously iterates the space location,characteristic scales and affine neighborhood shape of point regions.The experiments of the extraction and the matching show that,when extracting feature regions in the two images having the same scene with the generalized affine transformation,through the synchronous iterate in location,scale and shape,the neighborhood of convergence feature points in normalized image regions has the same content and satisfactory matching results are received.The comparison experiment in repeatability demonstrates that,under the changes of viewpoint,scale,rotation,brightness and blur,LS~2-I has good characteristics of repeatability.
To testify the matching and stability of EMSER-A and LS~2-I,the paper constructs relevant image retrieval mechanism.Firstly,SIFT descriptors are produced in EMSER-A and LS2-I which are used as local feature regions at low level and then cluster into the visual vocabulary based on vector-quantized,by standard weighting and similarity rule for measuring invariant feature,query region is selected by the rectangle in the retrieval image. Finally,the similarity score is obtained according to which the image results are ranked at the first.To make full use of the invariance of the feature regions,it presents the spatial consistency measurement rule based on regions matching method in searching unit and family-based.The principles of the former are as follows:in terms of affine covariance of the elliptical feature regions of EMSER-A and LS~2-I,in the object regions and the retrievaling image the two elliptical regions which have matched are respectively taken as searching units where the regions are matched based on the relation between the original matching and the new matching,and delete the region which has the zero score.The later is on the basis of the relations among the diffirent correct matching pairs;we propose a filtration method to remove false matching:family-based spatial consistency filtration.At last,the frenquency ranking is weighted to be the spatial consistency reranking.The dissertation establishes four different retrieval mechanisms.Retrieval experiments prove the matching of EMSER-A and LS~2-I,and validity of the retrieval mechanism based on the object region and the spatial consistency. Meanwhile,comparison experiment by enlarging the capacity of images database and the experiment of the generalized retrieval demonstrate stability and correctness of the two feature regions and retrieval mechanism respectively.
针对原始最大稳定极值区域算法的时间复杂度高、区域被覆盖以及形状不规则等缺点,构建了一种并行使用优化的邻域四叉树数据结构、基于成分树的最大稳定判定条件和基于向量的二阶中心矩调形通式的检测子,提取出加速的椭圆形最大稳定极值区域(Elliptical Maximally Stable Extremal Regions-Accelerative,EMSER-A)。在图像像素点排序的基础之上,根据使用按秩合并和路径压缩优化的邻域四叉树数据结构提取基于灰度阈值变化的极值区域,有效恢复了最终变成一个像素值和灰度阈值的区域的全部信息。使用极值区域作为结点构建成分树,并得到最大稳定判定条件。为了便于后续的特征描述,构建了基于向量的二阶中心矩调形通式,并将该通式降维为二维协方差矩阵,把不规则形状区域调整为椭圆形。EMSER-A检测子在保证可重复性的前提下,将时间复杂度由O(nloglogn)降低到O(Na(N))。特征提取和匹配实验表明:当存在广义仿射变换时,该检测子仍能提取数量较多且具有一定独特性的局部特征。可重复性比较实验证明:EMSER-A具有较为理想的视角、尺度、旋转、光照和模糊不变性。
为了解决特征点的定位精度不高、区域仿射形状的难以调整以及特征的弱仿射不变性等问题,论文还构建了基于点区域的仿射不变性检测子。证明了规范化LoG图像导数的尺度不变性,为特征尺度的确定提供了理论基础。提出了特征尺度的定性和定量定义,完善和发展了特征尺度的性质。系统地证明了仿射高斯尺度空间内形状自适应矩阵的仿射不变性以及基于该矩阵的规范化区域之间的旋转关系。给出了迭代过程中积分尺度和微分尺度的确定准则以及微分尺度对提高检测子抗噪性的影响。建立了基于仿射形状自适应矩阵的空间位置迭代矩阵,并使用该矩阵完成了从规范化区域到图像域的转换。在上述理论支撑下,构建了联合规范化LoG方程、多尺度Harris度量、仿射形状自适应矩阵以及空间位置迭代矩阵的仿射不变性检测子(Location/Scale/Shape-Iterative,LS~2-I),同步迭代出点区域的空间位置、特征尺度以及仿射邻域形状。特征提取和匹配实验表明:在存在广义仿射变换的同一个场景的两幅图像上提取特征区域,经过位置、尺度和形状的同步迭代,收敛的特征点邻域形状在规范化图像域内显示一致,实现了对特征点的精确定位和特征区域形状的仿射调整,并取得了理想的匹配结果。可重复性比较实验证明:在视角、尺度、旋转、光照变化以及存在模糊的情况下,LS~2-I具有较为理想的可重复性。
为了验证EMSER-A和LS~2-I的可匹配性及稳定性,论文构建了相应的图像检索机制。论文首先以EMSER-A和LS~2-I为底层局部特征区域,生成SIFT描述子并聚类成基于矢量量化的视觉关键词表,结合标准加权思想和衡量不变特征的相似性准则,提出了基于框选目标区域的检索方法,依据相似度得分对检索结果进行一次排序。为了更有效的发挥特征区域的不变性,论文提出了基于搜索单元区域匹配法和基于簇的空间一致性度量准则。前者根据EMSER-A和LS~2-I椭圆形特征区域的仿射协变性,在目标区域和被检图像上分别以某两个已匹配的椭圆形特征区域作为搜索单元,在该搜索单元内进行基于原匹配和新匹配之间关系的区域匹配,并删除零分匹配区域,最后根据得分情况对图像进行二次排序。后者根据正确匹配对空间角之间的关系,提出一种有效去除误匹配的基于簇的空间一致性滤波方法。论文构建了四种不同的检索机制,检索实验证明了特征区域EMSER-A和LS~2-I的可匹配性及基于目标区域和空间一致性检索机制的正确性。同时,增大图像库容量的对比实验和广义检索实验证明了特征区域及检索机制的稳定性和正确性。
The extraction of local invariant feature in the target is the research fundament in computer vision field,for example image processing,digital watermarking,copy detection and video retrieval.Because there are generalized affine transformations,such as viewpoint, scale,rotation,blur,partial occlusion and complex background,among most of targets,when generalized affine transformation occurred,it is concentrated in vision field to make the local invariant feature of good stability,repeatability and matching.
With respect to the shortcomings of high time complexity,regions overlapping and shape irregularity for original Maximally Stable Extremal Regions detector,the dissertation constructs a detector in parallel use of optimization neighborhood quadtree data structures, maximally stability criterion based on component tree and shape modification general expression with second order central moment based on vector;and then extracts Elliptical Maximally Stable Extremal Regions-Accelerative(EMSER-A).Based on pixel ordering, optimization neighborhood quadtree with path compression and union by rank are used to extract extremal regions based on intensity thresholds changing,which efficiently restore all of the information in the region that finally turned into one pixel and one intensity threshold. Extremal regions are used as nods to construct component tree,and maximally stability criterion is obtained by moving in the tree.For the convenience of the description for feature region,it establishes shape modification general expression with second order central moment based on vector,and reduces the dimensionality of the general expression to 2D covariance matrix,modifies irregularly regions to ellipse.Under the condition of ensuring repeatability, the EMSER-A recedes time complexity from O(nloglogn) to O(Na(N)).The experiments of extraction and matching show that,even on the occasions of generalized affine transformations,the detector can extract numerous distinctive local feature.The comparison experiment in repeatability proves that EMSER-A has the invariant in viewpoint,scale, rotation,brightness and blur.
For resolving the problems including the lower location precision of the feature point, difficulty to modifying affine shape of the region and the poor affine invariance of the feature, the dissertation also constructs the detector based on point regions.It demonstrates the scale invariance of normalized Laplacian-of-Gaussian image derivatives,which provides theoretical fundament for characteristic scales.It presents qualitative and quantitative definition,also further improves and develops the properties of characteristic scales.It systematically testifies to the affine invariance of shape-adapted matrix and the rotation relation between the two normalized regions based on the matrix.It establishes the determining principles of the integration scale and the differentiation scale,and analyzes the impact of differentiation scale on the antinoise performance.It builds the space location iterative matrix based on affine shape-adapted matrix and realizes the conversion from the normalized regions to the image domain.With the support of theories mentioned above,Location/Scale/Shape-Iterative(LS~2-I) is constructed combined with the normalized Laplacian-of-Gaussian,multi-scale Harris measure,affine shape-adapted matrix and space location iterative matrix,and synchronously iterates the space location,characteristic scales and affine neighborhood shape of point regions.The experiments of the extraction and the matching show that,when extracting feature regions in the two images having the same scene with the generalized affine transformation,through the synchronous iterate in location,scale and shape,the neighborhood of convergence feature points in normalized image regions has the same content and satisfactory matching results are received.The comparison experiment in repeatability demonstrates that,under the changes of viewpoint,scale,rotation,brightness and blur,LS~2-I has good characteristics of repeatability.
To testify the matching and stability of EMSER-A and LS~2-I,the paper constructs relevant image retrieval mechanism.Firstly,SIFT descriptors are produced in EMSER-A and LS2-I which are used as local feature regions at low level and then cluster into the visual vocabulary based on vector-quantized,by standard weighting and similarity rule for measuring invariant feature,query region is selected by the rectangle in the retrieval image. Finally,the similarity score is obtained according to which the image results are ranked at the first.To make full use of the invariance of the feature regions,it presents the spatial consistency measurement rule based on regions matching method in searching unit and family-based.The principles of the former are as follows:in terms of affine covariance of the elliptical feature regions of EMSER-A and LS~2-I,in the object regions and the retrievaling image the two elliptical regions which have matched are respectively taken as searching units where the regions are matched based on the relation between the original matching and the new matching,and delete the region which has the zero score.The later is on the basis of the relations among the diffirent correct matching pairs;we propose a filtration method to remove false matching:family-based spatial consistency filtration.At last,the frenquency ranking is weighted to be the spatial consistency reranking.The dissertation establishes four different retrieval mechanisms.Retrieval experiments prove the matching of EMSER-A and LS~2-I,and validity of the retrieval mechanism based on the object region and the spatial consistency. Meanwhile,comparison experiment by enlarging the capacity of images database and the experiment of the generalized retrieval demonstrate stability and correctness of the two feature regions and retrieval mechanism respectively.
引文
[1]A.Baumberg.Reliable Feature Matching Across Widely Separated Views[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 1,2000:774-781.
[2]贾涛,陈涛,杨润奎.基于仿射不变量的长基线立体匹配[J].仪器仪表学报,2005,26(8):623-624.
[3]P.Pritchett.A.Zisserman.Wide baseline stereo matching[C].Proceedings of the 6th International Conference on Computer Vision,Bombay,India,1998:754-760.
[4]T.Tuytelaars,L.Van Gool.Wide baseline stereo matching based on local,affinely invariant regions[C].Proceedings of the 11th British Machine Vision Conference,Bristol,UK,2000:412-425.
[5]Y.Dufoumaud,C.Schmid,R.Horaud.Matching images with different resolutions[C].Proceedings of the Conference on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000:612-618.
[6]D.Lowe.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[7]J.Matas,O.Chum,M.Urban et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image andVisionComputing,2004,22(10):761-767.
[8]M.Donoser,H.Bischof.Efficient Maximally Stable Extremal Region(MSER)Tracking[C].Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,(1):553-560.
[9]E.Chutorian,M.Trivedi.N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions[C].Proceedings of the British Machine Vision Conference,Edinburgh,2006,(Ⅱ):739-748.
[10]A.Vedaldi.An Implementation of Multi-Dimensional Maximally Stable Extremal Regions.http://vision.ucla.edu/～vedaldi/code/mser/mser.html
[11]P.Michal,M.Jiri,O.Stepan.Stable AffineFrames on Isophotes[C].Proceedings of the IEEE 11th International Conference on Computer Vision,Rio de Janeiro,2007:1-8.
[12]F.Per-Erik.Maximally Stable Colour Regions for Recognition and Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis,2007:1-8.
[13]F.Schaffalitzky,A.Zisserman.Multi-view matching for unordered image sets,or "How do I organize my holiday snaps?"[C].Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002:414-431.
[14]刘曙,罗予频,杨士元.基于临界特征点的图像匹配算法[J].计算机工程,2007,33(19):173-174.
[15]J.You,P.Bhattacharya.Wavelet-based Coarse-to-fine Image Matching Scheme in a Parallel Virtual Machine Environment[J].IEEE Trans.On Image Processing,2000,9(9):1547-1559.
[16]孙向军,曹立鑫,刘凤山.基于角仿射不变的特征匹配[J].中国图像图形学报,2004,9(5): 589-593.
[17]刘瑞祯,谭铁牛.数字图像水印研究综述[J].通信学报,2000,21(8):39-48.
[18]M.Kutter,S.Bhattacharjee,T.Ebrahimi.Towards second generation watermarking schemes[C].Proceedings of the IEEE International Conference on Image Processing.Los Alamitos,CA,USA,IEEE Computer Society Press,1999:320-323.
[19]P.Bas,J.Chassery,B.Macq.Geometrically invariant watermarking using feature points[J].IEEE Transactions on Image Processing,2002,11(9):1014-1028.
[20]M.Celik,E.Saber,G.Sharma,et al.Analysis of feature-based geometry invariant watermarking.Security and Watermarking of Multimedia Contents.San Jose,CA:Society of Photo-Optical Instrumentation Engineers,2001:261-268.
[21]胡慧博,刘琚,孙建德.基于ICA的抗拷贝攻击的数字水印方案[J].电子与信息学报,2005,27(7):1035-1038.
[22]欧阳建权.压缩域体育视频摘要技术研究[D].北京:中国科学院计算技术研究所,2005.
[23]J.Law-To,V.Gouet-Brunet,O.Buisson et al.Labeling Behaviour of Local Descriptors for Selective Video Content Retrieval[C].Proceedings of the 18th International Conference on Pattern Recognition(03),2006:232-235.
[24]黄祥林,沈兰荪.基于内容的图像检索技术研究[J].电子学报,2002,30(7):1065-1071.
[25]C.Schmid,R.Mohr.Local grayvalue invariants for image retrieval[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(5):530-535.
[26]T.Tuytelaars,L.Van Gool.Content-based image retrieval based on local affinely invariant regions [J].Lecture notesin computer science,1999,(1614):493-500.
[27]J.Sivic,A.Zisserman.Video Google:A Text Retrieval Approach to Object Matching in Videos[C].Proceedings of the Ninth IEEE International Conference on Computer Vision(3),2003:1470-1477.
[28]J.Sivic,F.Schaffalitzky,A.Zisserman.Object level grouping for video shots[C].Proceedings of the 8th European Conference on Computer Vision,Prague,Czech Republic,2004:724-734.
[29]J.Phiibin,O.Chum,M.Isard,et al.Object Retrieval with Large Vocabularies and Fast Spatial Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[30]何家峰,叶虎年,叶妙元.一种基于小波变换的虹膜识别方法[J].仪器仪表学报,2002,23(3):196-198.
[31]辛国栋,王巍.计算机辅助虹膜诊断中特征提取方法研究[J].计算机工程与设计,2006,27(18):3321.3323.
[32]于昕,韩崇昭,雷明明.支持向量机在目标分类中的应用[J].电光与控制,2006,13(4):14-25.
[33]刘丽丽,邹北骥,刘相滨等.视频监控系统中的运动目标分类技术研究[J].工程图学学报,2007.6.80-84.
[34]G.Csurka,C.Dance,C.Bray,L.Fan.Visual categorization with bags of keypoints[C].Proceedings of the Workshop on Statistical Learning in Computer Vision,2004.
[35]G.Dorko,C.Schmid.Selection of scale invariant neighborhoods for object class recognition[C].Proceedings of the International Conference on Computer Vision,Nice,France,2003:634-640.
[36]R.Fergus,P.Perona,A.Zisserman.Object class recognition by unsupervised scale invariant learning[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Madison(2),Wisconsin,USA,2003:264-271.
[37]A.Opelt,M.Fussenegger,A.Pinz et al.Weak Hypotheses and Boosting for Genetic Object Detection and Recognition[C].Proceedings of the European Conference on Computer Vision,Prague,Czech Republic,2004:71-84.
[38]S.Agarwal,A.Awan,D.Roth.Learning to detect objects in images via a sparse,part-based representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.26(11),2004:1475-1490.
[39]N.Dalai,B.Triggs.Histograms of oriented gradients for human detection[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:886-893.
[40]D.Feltzenswalb.Pictorial structures for object recognition[J].International Journal of Computer Vision,61(1),2005:55-79.
[41]R.Fergus,P.Perona,A.Zisserman.A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:380-387.
[42]B.Leibe,E.Seemann,B.Schiele.Pedestrian detection in crowded scenes[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:878-885.
[43]J.Sivic,A.Zisserman.Video data mining using configurations of viewpoint invariant regions[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(I),2004:488-495.
[44]刘扬.黄庆明.高文等.自适应高斯混合模型球场检测算法及其在体育视频分析中的应用[J].计算机研究与发展,2006,43(7):1207-1215.
[45]董立岩,刘光远,苑森淼等.可视化数据挖掘技术[J].吉林大学学报(信息科学版),2006,24(6):567-571.
[46]V.Ferrari,T.Tuytelaars,L.Van Gool.Simultaneous object recognition and segmentation by image exploration.In Proceedings European Conference on Computer Vision,Prague,Czech Republic,2004:40-54.
[47]V.Ferrari,T.Tuytelaars,L.Van Gool.Simultaneous object recognition and segmentation from single or multiple model views.In International Journal of Computer Vision,2005,67(2):1573-1405.
[48]S.Obdr(?)z'alek,J.Matas.Object recognition using local affine frames on distinguished regions.In Proceedings of the British Machine Vision Conference,Cardiff,UK,2002:113-122.
[49]F.Rothganger,S.Lazebnik,C.Schmid et al.3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints.In Proceedings of IEEE Conference on Computer VisionandPatternRecognition,Madison,Wisconsin,USA.2003:272-277.
[50]F.Schaffalitzky,A.Zisserman.Automated Location Matching in Movies.In Computer Vision and Image Understanding,2003,92(2):236-264.
[51]M.Brown,D.Lowe.Recognizing panoramas.In Proceedings of the International Conference on Computer Vision,Nice,France.2003:1218-1225.
[52]S.Lazebnik,C.Schmid,J.Ponce.A sparse texture representation using affine-invariant regions.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,USA.2003:319-324.
[53]S.Lazebnik,C.Schmid,J.Ponce.Affine-invariant local descriptors and neighborhood statistics for texture recognition.In Proceedings of the International Conference on Computer Vision,Nice,France.2003:649-655.
[54]S.Se,D.Lowe,J.Little.Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks.International Journal of Robotics Research.2002,21(8):735-758.
[55]T.Tuytelaars,L.Van Gool.L.D'haene et al.Matching ofAffinely Invariant Regions for Visual Servoing.IEEE International Conference on Robotics and Automation,1999,2:1601-1606.
[56]A.Turina,T.Tuytelaars,L.Van Gool,Efficient Grouping under Perspective Skew.In Proceedings IEEE Conference on Computer Vision and Pattern Recognition,Hawaii,USA.2001:247-254.
[57]H.Moravec.Towards Automatic Visual Obstacle Avoidance[C].Proceedings of the 5th International Joint Conference on Artificial Intelligence,Cambridge,1977:584-590.
[58]H.Moravec.Rover visual obstacle avoidance[C].Proceedings of the 7th International Joint Conference on Artificial Intelligence,Vancouver,1981:785-790.
[59]C.Harris,M.Stephens.A combined corner and edge detector[C].Proceedings of the 4th Alvey Vision Conference,Mancheste,1988:147-151.
[60]C.Schimid,R.Molar,C.Bauckhage.Evaluation of interest point detectors[J].International Journal of Computer Vision,2000,37(2):151-172.
[61]L.Hae-Yeoun,K.In Koo,L.Heung-Kyu etal.Evaluation ofFea~areExtractionTechniques for Robust Watermarking[J].Lecture Notes in Computer Science.Germany:Springer,2005(3710):418-431.
[62]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.
[63]宋利,周源华,周军.基于特征匹配的鲁棒图像镶嵌[J].38(5),2004:783-786.
[64]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.
[65]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.
[66]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).34(4),2007:465-468.
[67]L.Yua,D.Zhanga,E.Holdenb.A fast and fully automatic registration approach based on point features for multi-source remote-sensing images[J].Computers & Geosciences,2007:1-11.
[68]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.
[69]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.
[70]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.
[71]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.
[72]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.
[73]彭勃,周文晖,刘济林.基于Harris角点检测的立体视觉里程计[J].兵工学报.2007,28(12):1498-1502.
[74]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.
[75]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.
[76]Xuan Zhao,Shengjin Wang,Xiaoqing Ding.A dynamic generating graphical model for point-sets matching[J].Applied Mathematics and Computation.2007,185:1109-1119.
[77]A.Lumini,L.Nanni.Detector of image orientation based on Borda Count[J].Pattern Recognition Letters.2006,27:180-186.
[78]Z.Zhen,H.Wang,E.Teoh.Analysis of gray level comer detection[J].Pattern Recognition Letters.1999,20(2):149-162.
[79]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.
[80]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.
[81]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.
[82]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.
[83]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.
[84]王君秋,查红彬.结合兴趣点和边缘的建筑物和物体识别方法[J].计算机辅助设计与图形学 学报.2006,18(8):1257-1263.
[85]宋辉,李弼程.一种使用Harris特征点的区域图像检索算法[J].计算机工程.2006,32(7):202-203.
[86]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.
[87]Q.Xiaojun,Q.Ji.A robust content-based digital image watermarking scheme[J].Signal Processing.2007,87:1264-1280.
[88]胡海峰,侯晓微.一种自动检测棋盘角点的新算法[J].计算机工程.2004,30(14):19-21.
[89]张桦,孙济州,谭磊.一种有效的全景图拼合预处理算法[J].光电子·激光.2007,18(6):747-749
[90]S.M.Smith,J.M.Brady.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision.1997,23(1):45-78.
[91]张迁,刘政凯,庞彦伟等.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.
[92]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.
[93]王荣本,余天洪,顾柏园.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.
[94]H.Mauricio,M.Geovanni.Facial feature extraction based on the Smallest Univalue Segment Assimilating Nucleus(SUSAN) Algorithm[C].Proceedings of the International Conference on Picture Coding Symposiump,2004:261-266.
[95]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.
[96]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.
[97]V.Etienne,L.Robert.Detecting and matching feature points[J].Journal of Visual Communication and Image Representation.2005,16(1):38-54.
[98]C.Kyu-Yeol,D.Won-Pyo,J.Chang-Sung.SUSAN window based cost calculation for fast stereo matching[C].Proceedings of the International Conference on Computational Intelligence and Security.2005,3802:947-952.
[99]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.
[100]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.
[101]W.Xun,J.Jianqiu,L.Yun,et al.Multi-feature SUSAN comer detection method[C].Proceedings of the International Society for Optical Engineering.2005,6044:1-7.
[102]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.
[103]M.Trajkovic,M.Hedley.Fast comerdetection[J].Image and Vision Computing.1998,16(2):75-87.
[104]陈静.图像配准特征点提取算法研究[M].南京理工大学.2006.
[105]王建琦,邓雁萍,李介谷.一种改进的角点提取方法[J].上海交通大学学报.2000,34(7):913-916.
[106]陈利军,刘侍刚.一种改进的MIC的角点提取方法[J].电子科技.2004,180:34-37.
[107]伊世明.立体匹配中的若干问题研究IM].国防科学技术大学.2006.
[108]M.Armstrong,A.Zisserman.Robust object tracking[C].Proceedings of Second Asian Conference on Computer Vision.Singapore,1995:58-62.
[109]E.Rosten,T.Drummond.Machine learning for high-speed comer detection[C].Proceedings of the European Conference on Computer Vision,2006,1(1):430-443.
[110]E.Rosten.High performance rigid body tracking[D].UK:Churchill College University of Cambridge,2006.
[111]J.R.Quinlan.Induction ofdecisiontrees.Mach.Learn(l),1986:81-106.
[112]张玉冰,罗青山,曾贵华.基于部件的对象实时跟踪.计算机工程与应用[J].2008,44(7):69-71.
[113]E.Rosten,T.Drummond.Fusing points and lines for high performance tracking.Proceedings of the 10th IEEE International Conference on Computer Vision(2),2005:1508-1515.
[114]E.Rosten,G.Reitmayr,T.Drummond.Real-Time Video Annotations for ugmented Reality.Lecture Notes in Computer Science,Advances in Visual Computing(3804),2005:294-302.
[115]P.R.Beaudet.Rotational invariant image operators[C].Proceedings of the IEEE International Conference on Pattern Recognition,1978:579-583.
[116]L.Dreschler,H.Nagel.Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene[J].Computer Graphics and Image Processing.1982,20(3):199-228.
[117]R.Deriche,G.Giraudon.Accurate comer detection:an analytical study[C].Proceedings of the IEEE International Conference on Computer Vision,1990:66-70.
[118]R.Deriche,G.Giraudon.A computational approach for comer and vertex detection[J].International Journal Computer Vision.1993.10(2):101-124.
[119]L.Kitchen,A.Rosenfeld.Gray-level comer detection.Pattern RecognitionLetters.1982,1(2):95-102.
[120]C.Chin-Hsing,L.Jiann-Shu,S.Yung-Nien.Wavelet transformation for gray-level comer detection.Pattern Recognition.1995,28(6):853-861.
[121]W.F(o|¨)rstner,E.G(u|¨)lch.A fast operator for detection and precise location of distinct points,corners and centres of circular features,ISPRS Intercommission Conf.Fast Processing Photogrammetric Data,1987:281-305.
[122]H.Wang,M.Brady.Real-time corner detection algorithm for motion estimation.Image and Vision Computing.1995,13(9):695-703.
[123]F.Mokhtarian,R.Suomela.Robust Image Corner Detection through Curvature Scale Space.IEEE Transactions on pattern analysis and machine intelligence.1998,20(12):1376-1381.
[124]F.Mokhtarian,F.Mohanna.Performance evaluation of corner detectors using consistency and accuracy measures.Computer Vision Image Understand.2006,102(1):81-94.
[125]J.L.Crowley,A.C.Parker.A representation for shape based on peaks and ridges in the difference of low-pass transform [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(2):156-170.
[126]D.Lowe.Object recognition from local scale-invariant features[C].Proceedings of the International Conference on Computer Vision,Corfu,1999:1150-1157.
[127]A.Basharat,Y.Zhai,M.Shah.Content based video matching using spatiotemporal volumes[J].Computer Vision and Image Understanding.2007:1-18.
[128]M.Moradi,P.Abolmaesumi.Medical image registration based on distinctive image features from scale-invariant(SIFT)key-points[J].Proceedings of 19th Computer-Assisted Radiology and Surgery Conference.2005(1281):1292.
[129]霍春雷,周志鑫,刘青山,卢汉清．基于SIFT特征和广义紧互对原型对距离的遥感图像配准方法遥感技术与应用[J]．2007,22(4)：524-530．
[130]E.Delponte,F.Isgro,F.Odone et al.SVD-matching using SIFT features [J].Graphical Models,2006,68(5-6):415-431.
[131]Y.Ke,R.Sukthankar.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors[C].Proceedings of the Conference on Computer Vision and Pattern Recognition.2004:511-517.
[132]M.Artaˇc,A.Leonardis.Outdoor mobile robot localization using global and local features[C].Proceedings of the 9th Computer Vision Winter Workshop,Slovenian Pattern Recognition Society,Piran,2004:175-184.
[133]L.Ledwich,S.Williams.Reduced SIFT features for image retrieval and indoor localization[C].Proceedings of Australian Conference on Robotics and Automation,2004.
[134]D.Cobzas,H.Zhang.Using image-based panoramic models for 2D robot localization [C].Proceedings of the Conference on Western Computing Graphics Symposium,Panorama Mountain Village,Canada,2000:1-7.
[135]H.Tamimi,H.Andreasson,A.reptowetal.Localization of mobile robots with omnidirectional vision using Particle Filter and iterative SIFT [J].Robotics and Autonomous Systems.2006,54(9):758-765.
[136]K.Mikolajczyk,C.Schmid.Indexing based on scale invariant interest points[C].Proceedings of the IEEE International Conference on Computer Vision,2001:525-531.
[137]H.V.Netoa,U.Nehmzowb.Visual novelty detection with automatic scale selection [J].Robotics and Autonomous Systems(55),2007:693-701.
[138]陈白帆,蔡自兴.基于尺度空间理论的Harris角点检测[J].中南大学学报(自然科学版).2005,36(5):751-754.
[139]T.Lindeberg.Feature detection with automatic scale selection[J].International Journal of Computer Vision,1998,30(2):77-116.
[140]K.Mikolajczyk,C.Schmid.Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.
[141]P.Moreels,P.Perona.Evaluation of Features Detectors and Descriptors based on 3D Objects [J].International Journal of Computer Vision.2007,73(3).263-284.
[142]M.Tone.N.Hamada.Scale Change and Rotation Invariant Digital Image Watermarking Method [J].Systems and Computers in Japan.2007,38(10):1-9.
[143]H.Bay,A.Ess,T.Tuytelaars etal.Speeded-Up Robust Features(SURF)[C].Proceedings of the 9th European Conference on Computer Vision,2006:404-417.
[144]Z.Chang,C.Yaowu,K.JayLin.Fast detection of overlapped areas in smart camera network [J].Chinese Journal of Scientific Instrument.2007,28(7):1153-1158.
[145]K.Mikolajczyk,T.Tuytelaars,C.Schmid et al.A comparison of affine region detectors [J].International Journal on Computer Vision,2005,65(1/2):43-72.
[146]L.Jing,N.Allinson.A comprehensive review of current local features for computer vision [J].Neurocomputing,2008(2):1-17.
[147]T.Tuytelaars,L.Van Gool.Matching Widely Separated Views based on Affine Invariant Regions [J].International Journal on Computer Vision,2004,59(1):61-85.
[148]M.Banerjee,M.K.Kundu.Edge based features for content based imagere trieval[J].Pattern Recognition,2003,36(11):2649-2661.
[149]L.Hua,Y.Shui-Cheng,P.Li-Zhong.Robust non-frontal face alignment with edge based texture [J].Journal of Computer Science and Technology,2005,20(6):849-854.
[150]K.Mikolajczyk,A.Zisserman,C.Schmid.Shape recognition with edge-based features[C].Proceedings of the British Machine Vision Conference,2003,2:779-788.
[151]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.
[152]P.Michal,M.Jiri,O.Stepan.Stable Affine Frames on Isophotes[C].Proceedings of the IEEE 11th International Conference on Computer Vision,2007:1-8.
[153]F.Per-Erik.Maximally Stable Colour Regions for Recognition and Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[154]T.Kadir,M.Brady,Scale,Saliency and image description[J].International Journal of Computer Vision.2001,45(2):83-105.
[155]T.Kadir,A.Zisserman,M.Brady.An affine invariant salient region detector[C].Proceedings of the 8th European Conference on Computer Vision,2004:345-457.
[156]袁武钢,卢正鼎,凌贺飞等.抗几何失真的局部数字水印算法[J].计算机仿真.2008,25(2):157-160.
[157]单列,刘政凯.显著区域检测的建筑物检索[J].声学技术.2007,26(6):1145-1149.
[158]孙即祥.模式识别中的特征提取与计算机视觉不变量.北京:国防工业出版社,2001.
[159]T.Iijima.Basic theory of pattern normalization(for the case of a typical one dimensional pattern)[J].Bulletin oftheElectro-technical laboratory.1962,26:368-388.
[160]M.Nagao.Edge Preserving Smoothing[J].CGIP,1979,9:394-407.
[161]D.Marr,E.Hildreth.Theory of Edge Detection[C].Proceedings of the Royal Society of London.Series B,Biological Sciences,1980,207(1167):187-217.
[162]T.Lindeberg.Scale-space for discrete signals.IEEE Trans.PAMI,1980,207:187-217.
[163]A.Witkin.Scale-space Filtering[C].International Joint Conference on Artificial Intelligence,Karlsruhe,West Germany.1983:1019-1022.
[164]J.Koenderink.The structure of images.Biological Cybernetics,1984,50:363-396.
[165]T.Lindeberg.Detecting salient blob-like image structures and their scales with a scale-space primal sketch:A method for focus-of-attention.International Journal of Computer Vision,1993,11(3):283-318.
[166]T.Lindeberg.Scale-space theory:A basic tool for analysing structures at different scales.Journal of Applied Statistics,1994,21(2):224-270.
[167]T.Lindeberg.Scale space:A frame work for handling image structures at multiple scales.Porc.CERN school of Computering,the Netherlands,1996:695-702.
[168]T.Lindeberg.Edge detection and ridge detection with automatic scale selection[A].IEEE Conf Computer Vision Pattern Recognition[C].SanFrancisco:IEEE CS Press.1996.
[169]L.Bretzner,T.Lindeberg.Feature tracking with automatic selection of spatial scales[J].Computer Vision and Image Understanding,1998,71(3):385-392.
[170]I.Laptev,T.Lindeberg.Tracking of Multi-state Hand Models Using Particle Filtering and a Hierarchy of Multi-scale Image Features[C].Proceedings of the 3rd International Conference on Scale Space and Morphology in Computer Vision,Vancouver,2001:63-74.
[171]孙剑,徐宗本.计算机视觉中的尺度空间方法.工程数学学报.2005,22(6):951-962.
[172]章毓晋.图像工程.北京:清华大学出版社,2007.
[173]夏良正.数字图像处理修订版.南京:东南大学出版社,1999.
[174]阮秋琦.数字图像处理学.北京:电子工业出版社,2001.
[175]K.Castleman著,朱志刚等译.数字图像处理.北京:电子工业出版社,1998.
[176]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京:清华大学出版社,2006.
[177]K.Rangarajan,M.Shah,D.Brackle.Optimal corner detector.Computer Vision,Graphics,and Image Processing.1989,48(2):230-245.
[178]R.Mehrotra,S.Nichani,N.Ranganathan.Corner detection.Pattern Recognition.1990,23(11):1223-1233.
[179]孙即祥.图像分析.北京:科学出版社,2005。
[180]R.Hartley,A.Zisserman.Multipl View Geometry in Computer Vision.Cambridge University Press:2000.
[181]B.Bracewell.Two-Dimensional Imaging.Prentice Hall:1995.
[182]M.Hu.Visual Pattern Recognition by Moment Invariants,IRE Trans.Inform.Theory,1962,IT-8(2):179-187.
[183]Y.Hel-Or,C.Teo.PatrickA.Common Frarnework for Steerability,Motion Estimation,and Invariant Feature Detection.Proceeding of the IEEE International Symposium on Circuits and System,1998:337-340.
[184]Y.Zhengwei,S.Fernand.Cross-Weighted Moments and Afrine Invariants for Image Registration and Matching.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(8):804-814.
[185]陈涛.图像仿射不变特征提取方法研究[D].国防科技大学.2006年.
[186]L.Vincent,P.Soille.Watersheds in digital spaces:an efficient algorithm based on immersion simulations.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[187]T.Cormen,C.Leiserson,R.Rivest,et al.Introduction to Algorithms.MIT Press and McGraw-Hill Book Co.,second edition:2001.
[188]E.Murphy-Chutorian,M.Trivedi.N-tree disjoint-set foreset for maximally stable extremal regions.Proceedings of the British Machine Vision Conference,2006.
[189]R.Tarjan.Worst-cases analysis of set union algorithms.J.ACM.1984,31(2):245-281.
[190]Z.Galil.Data structures and algorithms for disjoint set union problems.ACM,Computing Surveys,1991,23(3):320-344.
[191]L.Najman,M.Couprie.Quasi-linear algorithm for the component tree.In SPIE Vision Geometry,2004,5300(Ⅻ):98-107.
[192]牛津大学机器人研究小组:http://www.robots.ox.ac.uk/-vgg/research/affine/index.html
[193]彭勃,周文晖,刘济林.基于Harris角点检测的立体视觉里程计[J].兵工学报,2007,28(12):1498-1502.
[194]K.Mikolajczyk.Interest point detection invariant to affine transformations[D].Institut National Polytechnique de Grenoble:2002.
[195]王向阳.邬俊.侯丽敏.一种基于图像特征点的数字水印潜入方法.电子学报.2007,35(7):1318-1322.
[196]R.Duda.P.Hart.Pattern Classification and Scene Analysis.Wiley-Interscience:1973.
[197]O.Chomat,V.Verdiere,D.Hall et al.Local scale selection for Gaussian based description techniques[C].Proceedings of the 6th European Conference on Computer Vision.Dublin,Ireland,2000:117-133.
[198]T.Lindeberg,J.Garding,Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure.Image and Vision Computing,1997,15(6):415-434.
[199]F.Schaffalitzky,A.Zisserman.Multi-view matching for unordered image sets.In Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002:414-431.
[200]K.Mikolajczyk,C.Schmid.An affine invariant interest point detector.In Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002,I:128-142.
[201]A.Blaser.Data Base Techniques for Pictorial Applications.Lecture Notes in Computer Science,Springer Verlag,New York,Inc.Secaucus,NJ,USA,1980.
[202]S.Ravela,R.Manmatha.Image retrieval by Appearance,ACMSIGIR97,Philadephia PA,USA,278-285.
[203]H.Tamura,N.Yokoya.Image Database System:A Survey.Pattern Recognition,1984,17(1):29-43.
[204]A.Smeuders,M.Worring,S.Santini.Content-Based Image Retrieval at the End of the Early Years[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2000,22(12):1349-1380.
[205]M.Lew,N.Sebe,J.Eakins.Challenges of Image and Video Retrieval [A].Image and Video Retrieval.Lecture Notes in Computer Science,Springer,2002:211-231.
[206]Blobworld,Image retrieval using regions[EB/OL].[2006-12-01].http://elib.cs.berkelev.edu/blobworld/
[207]C.Carson,S.Belongie,H.Greenspan.Blobworld:image segmentation using expectation-maximizations and its application to image querying [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(8):1026-1038.
[208]J.Wang,J.Li,G.Wiederhold.SIMPLIcity:Semantics-Sensitive Integrated Matching for Picture Libraries [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2001,23(9):947-963.
[209]W.Ma,B.Manjunath.Netra:A Toolbox for Navigating Large Image Databases.Multimedia systems,1999,7(3):184-198.
[210]G.Aggarwal,T.V.Ashwin,S.Ghosal.An Image Retrieval System with Automatic Query Modification.IEEE Transaction On Multimedia,2002,4(2),201-214.
[211]G.Aggarwal,P.Dubey,S.Ghosal et al.iPURE:Perceptual and User-friendly Retrieval of Images.Proceedings of IEEE Conference on ICME,NY USA,Aug.2000:693-697.
[212]Photosynth Technology[EB/OL].[2006-12-08].http://labs.live.com/photosynth/.
[213]Autostitch:A new dimension in automatic image stitching[EB/OL].[2006-12-17]Http://www.cs.ubc.ca/～mbrown/autostitch/autostitch.html.
[214]Matthew Brown' s Research Page [EB/OL].[2006-12-18].Http://www.s.bc.a/～mbrown/research/research.html.
[215]Q.Tian,Y.Wu,T.Huang.Combine User Defined Region-of-Interest and Spatial Layout for Image Retrieval[A].IEEE 2000 International Conference on Image Processing(ICIP2000),Vancouver,BC,Cananda,2000,3:746-749.
[216]张健沛,闫锐,杨静.基于兴趣区域的图像检索方法的研究[J].哈尔滨工程大学学报,2003,24(3):283-286.
[217]斯白露.基于感兴趣区域的图像检索方法[D].北京:中科院计算技术研究所,2002.
[218]R.Yates,B.Nero.Modern Information Retfieval.ACM Press,ISBN:020139829,1999.
[219]章毓晋.基于内容的视觉信息检索.北京:科学出版社,2003.
[220]汪彦龙,刘金华,王丽萍.基于对象空间关系的图像检索方法研究[J].计算机技术与发展,16(1),2006:66-69.
[221]E.Sviascio,F.DOnini,M.Mongiello.Spatial layout representation for query-by-sketch content-based image retrieval.Physical Review Letters,2002,23(13):1599-1612.
[222]http://www.qbic.almaden.ibm.com/
[223]董卫军,周明全,耿国华.基于形状-空间关系的图像检索技术[J].计算机工程.31(20),2005:170-172.
[224]孙君顶,毋小省.基于颜色分布特征的图像检索[J].光电子·激光.17(8),2006:1009-1013.
[225]黄元元,何云峰.一种基于颜色特征的图像检索方法[J].中国图象图形学报.11(12),2006:1768-1774.
[226]http://www.ctr.columbia.edu/VisualSEEK/
[227]曾智勇,张学军,崔江涛等.基于显著兴趣点颜色及空间分布的图像检索新方法[J].光子学报.35(2),2006:309-311.
[228]孟繁杰,郭宝龙.一种基于兴趣点颜色及空间分布的图像检索方法[J].西安电子科技大学学报(自然科学版).32(2),2005:751-753.
[229]韩东峰,李文辉,郭武.基于潜在局部区域空间关系学习的物体分类算法[J].计算机学报.30(8),2007:7820-7828.
[230]张健沛,闫锐,杨静.基于兴趣区域的图像检索方法的研究.哈尔滨工程大学学报.24(3),2003:283-286.
[231]李向阳,庄越挺,潘云鹤.基于内容的图像检索技术与系统[J].计算机研究与发展,2001(3):344-354.
[232]J.Sivic,B.Russell,A.Efros et al.Discovering objects and their locationin images,Proceedings of International Conference Computer Vision,2005:370-377.
[2]贾涛,陈涛,杨润奎.基于仿射不变量的长基线立体匹配[J].仪器仪表学报,2005,26(8):623-624.
[3]P.Pritchett.A.Zisserman.Wide baseline stereo matching[C].Proceedings of the 6th International Conference on Computer Vision,Bombay,India,1998:754-760.
[4]T.Tuytelaars,L.Van Gool.Wide baseline stereo matching based on local,affinely invariant regions[C].Proceedings of the 11th British Machine Vision Conference,Bristol,UK,2000:412-425.
[5]Y.Dufoumaud,C.Schmid,R.Horaud.Matching images with different resolutions[C].Proceedings of the Conference on Computer Vision and Pattern Recognition,Hilton Head Island,South Carolina,USA,2000:612-618.
[6]D.Lowe.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[7]J.Matas,O.Chum,M.Urban et al.Robust wide-baseline stereo from maximally stable extremal regions[J].Image andVisionComputing,2004,22(10):761-767.
[8]M.Donoser,H.Bischof.Efficient Maximally Stable Extremal Region(MSER)Tracking[C].Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2006,(1):553-560.
[9]E.Chutorian,M.Trivedi.N-tree Disjoint-Set Forests for Maximally Stable Extremal Regions[C].Proceedings of the British Machine Vision Conference,Edinburgh,2006,(Ⅱ):739-748.
[10]A.Vedaldi.An Implementation of Multi-Dimensional Maximally Stable Extremal Regions.http://vision.ucla.edu/～vedaldi/code/mser/mser.html
[11]P.Michal,M.Jiri,O.Stepan.Stable AffineFrames on Isophotes[C].Proceedings of the IEEE 11th International Conference on Computer Vision,Rio de Janeiro,2007:1-8.
[12]F.Per-Erik.Maximally Stable Colour Regions for Recognition and Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Minneapolis,2007:1-8.
[13]F.Schaffalitzky,A.Zisserman.Multi-view matching for unordered image sets,or "How do I organize my holiday snaps?"[C].Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002:414-431.
[14]刘曙,罗予频,杨士元.基于临界特征点的图像匹配算法[J].计算机工程,2007,33(19):173-174.
[15]J.You,P.Bhattacharya.Wavelet-based Coarse-to-fine Image Matching Scheme in a Parallel Virtual Machine Environment[J].IEEE Trans.On Image Processing,2000,9(9):1547-1559.
[16]孙向军,曹立鑫,刘凤山.基于角仿射不变的特征匹配[J].中国图像图形学报,2004,9(5): 589-593.
[17]刘瑞祯,谭铁牛.数字图像水印研究综述[J].通信学报,2000,21(8):39-48.
[18]M.Kutter,S.Bhattacharjee,T.Ebrahimi.Towards second generation watermarking schemes[C].Proceedings of the IEEE International Conference on Image Processing.Los Alamitos,CA,USA,IEEE Computer Society Press,1999:320-323.
[19]P.Bas,J.Chassery,B.Macq.Geometrically invariant watermarking using feature points[J].IEEE Transactions on Image Processing,2002,11(9):1014-1028.
[20]M.Celik,E.Saber,G.Sharma,et al.Analysis of feature-based geometry invariant watermarking.Security and Watermarking of Multimedia Contents.San Jose,CA:Society of Photo-Optical Instrumentation Engineers,2001:261-268.
[21]胡慧博,刘琚,孙建德.基于ICA的抗拷贝攻击的数字水印方案[J].电子与信息学报,2005,27(7):1035-1038.
[22]欧阳建权.压缩域体育视频摘要技术研究[D].北京:中国科学院计算技术研究所,2005.
[23]J.Law-To,V.Gouet-Brunet,O.Buisson et al.Labeling Behaviour of Local Descriptors for Selective Video Content Retrieval[C].Proceedings of the 18th International Conference on Pattern Recognition(03),2006:232-235.
[24]黄祥林,沈兰荪.基于内容的图像检索技术研究[J].电子学报,2002,30(7):1065-1071.
[25]C.Schmid,R.Mohr.Local grayvalue invariants for image retrieval[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(5):530-535.
[26]T.Tuytelaars,L.Van Gool.Content-based image retrieval based on local affinely invariant regions [J].Lecture notesin computer science,1999,(1614):493-500.
[27]J.Sivic,A.Zisserman.Video Google:A Text Retrieval Approach to Object Matching in Videos[C].Proceedings of the Ninth IEEE International Conference on Computer Vision(3),2003:1470-1477.
[28]J.Sivic,F.Schaffalitzky,A.Zisserman.Object level grouping for video shots[C].Proceedings of the 8th European Conference on Computer Vision,Prague,Czech Republic,2004:724-734.
[29]J.Phiibin,O.Chum,M.Isard,et al.Object Retrieval with Large Vocabularies and Fast Spatial Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[30]何家峰,叶虎年,叶妙元.一种基于小波变换的虹膜识别方法[J].仪器仪表学报,2002,23(3):196-198.
[31]辛国栋,王巍.计算机辅助虹膜诊断中特征提取方法研究[J].计算机工程与设计,2006,27(18):3321.3323.
[32]于昕,韩崇昭,雷明明.支持向量机在目标分类中的应用[J].电光与控制,2006,13(4):14-25.
[33]刘丽丽,邹北骥,刘相滨等.视频监控系统中的运动目标分类技术研究[J].工程图学学报,2007.6.80-84.
[34]G.Csurka,C.Dance,C.Bray,L.Fan.Visual categorization with bags of keypoints[C].Proceedings of the Workshop on Statistical Learning in Computer Vision,2004.
[35]G.Dorko,C.Schmid.Selection of scale invariant neighborhoods for object class recognition[C].Proceedings of the International Conference on Computer Vision,Nice,France,2003:634-640.
[36]R.Fergus,P.Perona,A.Zisserman.Object class recognition by unsupervised scale invariant learning[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Madison(2),Wisconsin,USA,2003:264-271.
[37]A.Opelt,M.Fussenegger,A.Pinz et al.Weak Hypotheses and Boosting for Genetic Object Detection and Recognition[C].Proceedings of the European Conference on Computer Vision,Prague,Czech Republic,2004:71-84.
[38]S.Agarwal,A.Awan,D.Roth.Learning to detect objects in images via a sparse,part-based representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.26(11),2004:1475-1490.
[39]N.Dalai,B.Triggs.Histograms of oriented gradients for human detection[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:886-893.
[40]D.Feltzenswalb.Pictorial structures for object recognition[J].International Journal of Computer Vision,61(1),2005:55-79.
[41]R.Fergus,P.Perona,A.Zisserman.A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:380-387.
[42]B.Leibe,E.Seemann,B.Schiele.Pedestrian detection in crowded scenes[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(1),2005:878-885.
[43]J.Sivic,A.Zisserman.Video data mining using configurations of viewpoint invariant regions[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition(I),2004:488-495.
[44]刘扬.黄庆明.高文等.自适应高斯混合模型球场检测算法及其在体育视频分析中的应用[J].计算机研究与发展,2006,43(7):1207-1215.
[45]董立岩,刘光远,苑森淼等.可视化数据挖掘技术[J].吉林大学学报(信息科学版),2006,24(6):567-571.
[46]V.Ferrari,T.Tuytelaars,L.Van Gool.Simultaneous object recognition and segmentation by image exploration.In Proceedings European Conference on Computer Vision,Prague,Czech Republic,2004:40-54.
[47]V.Ferrari,T.Tuytelaars,L.Van Gool.Simultaneous object recognition and segmentation from single or multiple model views.In International Journal of Computer Vision,2005,67(2):1573-1405.
[48]S.Obdr(?)z'alek,J.Matas.Object recognition using local affine frames on distinguished regions.In Proceedings of the British Machine Vision Conference,Cardiff,UK,2002:113-122.
[49]F.Rothganger,S.Lazebnik,C.Schmid et al.3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints.In Proceedings of IEEE Conference on Computer VisionandPatternRecognition,Madison,Wisconsin,USA.2003:272-277.
[50]F.Schaffalitzky,A.Zisserman.Automated Location Matching in Movies.In Computer Vision and Image Understanding,2003,92(2):236-264.
[51]M.Brown,D.Lowe.Recognizing panoramas.In Proceedings of the International Conference on Computer Vision,Nice,France.2003:1218-1225.
[52]S.Lazebnik,C.Schmid,J.Ponce.A sparse texture representation using affine-invariant regions.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,USA.2003:319-324.
[53]S.Lazebnik,C.Schmid,J.Ponce.Affine-invariant local descriptors and neighborhood statistics for texture recognition.In Proceedings of the International Conference on Computer Vision,Nice,France.2003:649-655.
[54]S.Se,D.Lowe,J.Little.Mobile robot localization and mapping with uncertainty using scale-invariant visual landmarks.International Journal of Robotics Research.2002,21(8):735-758.
[55]T.Tuytelaars,L.Van Gool.L.D'haene et al.Matching ofAffinely Invariant Regions for Visual Servoing.IEEE International Conference on Robotics and Automation,1999,2:1601-1606.
[56]A.Turina,T.Tuytelaars,L.Van Gool,Efficient Grouping under Perspective Skew.In Proceedings IEEE Conference on Computer Vision and Pattern Recognition,Hawaii,USA.2001:247-254.
[57]H.Moravec.Towards Automatic Visual Obstacle Avoidance[C].Proceedings of the 5th International Joint Conference on Artificial Intelligence,Cambridge,1977:584-590.
[58]H.Moravec.Rover visual obstacle avoidance[C].Proceedings of the 7th International Joint Conference on Artificial Intelligence,Vancouver,1981:785-790.
[59]C.Harris,M.Stephens.A combined corner and edge detector[C].Proceedings of the 4th Alvey Vision Conference,Mancheste,1988:147-151.
[60]C.Schimid,R.Molar,C.Bauckhage.Evaluation of interest point detectors[J].International Journal of Computer Vision,2000,37(2):151-172.
[61]L.Hae-Yeoun,K.In Koo,L.Heung-Kyu etal.Evaluation ofFea~areExtractionTechniques for Robust Watermarking[J].Lecture Notes in Computer Science.Germany:Springer,2005(3710):418-431.
[62]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.
[63]宋利,周源华,周军.基于特征匹配的鲁棒图像镶嵌[J].38(5),2004:783-786.
[64]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.
[65]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.
[66]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).34(4),2007:465-468.
[67]L.Yua,D.Zhanga,E.Holdenb.A fast and fully automatic registration approach based on point features for multi-source remote-sensing images[J].Computers & Geosciences,2007:1-11.
[68]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.
[69]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.
[70]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.
[71]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.
[72]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.
[73]彭勃,周文晖,刘济林.基于Harris角点检测的立体视觉里程计[J].兵工学报.2007,28(12):1498-1502.
[74]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.
[75]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.
[76]Xuan Zhao,Shengjin Wang,Xiaoqing Ding.A dynamic generating graphical model for point-sets matching[J].Applied Mathematics and Computation.2007,185:1109-1119.
[77]A.Lumini,L.Nanni.Detector of image orientation based on Borda Count[J].Pattern Recognition Letters.2006,27:180-186.
[78]Z.Zhen,H.Wang,E.Teoh.Analysis of gray level comer detection[J].Pattern Recognition Letters.1999,20(2):149-162.
[79]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.
[80]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.
[81]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.
[82]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.
[83]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.
[84]王君秋,查红彬.结合兴趣点和边缘的建筑物和物体识别方法[J].计算机辅助设计与图形学 学报.2006,18(8):1257-1263.
[85]宋辉,李弼程.一种使用Harris特征点的区域图像检索算法[J].计算机工程.2006,32(7):202-203.
[86]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.
[87]Q.Xiaojun,Q.Ji.A robust content-based digital image watermarking scheme[J].Signal Processing.2007,87:1264-1280.
[88]胡海峰,侯晓微.一种自动检测棋盘角点的新算法[J].计算机工程.2004,30(14):19-21.
[89]张桦,孙济州,谭磊.一种有效的全景图拼合预处理算法[J].光电子·激光.2007,18(6):747-749
[90]S.M.Smith,J.M.Brady.SUSAN-a new approach to low level image processing[J].International Journal of Computer Vision.1997,23(1):45-78.
[91]张迁,刘政凯,庞彦伟等.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.
[92]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.
[93]王荣本,余天洪,顾柏园.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.
[94]H.Mauricio,M.Geovanni.Facial feature extraction based on the Smallest Univalue Segment Assimilating Nucleus(SUSAN) Algorithm[C].Proceedings of the International Conference on Picture Coding Symposiump,2004:261-266.
[95]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.
[96]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.
[97]V.Etienne,L.Robert.Detecting and matching feature points[J].Journal of Visual Communication and Image Representation.2005,16(1):38-54.
[98]C.Kyu-Yeol,D.Won-Pyo,J.Chang-Sung.SUSAN window based cost calculation for fast stereo matching[C].Proceedings of the International Conference on Computational Intelligence and Security.2005,3802:947-952.
[99]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.
[100]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.
[101]W.Xun,J.Jianqiu,L.Yun,et al.Multi-feature SUSAN comer detection method[C].Proceedings of the International Society for Optical Engineering.2005,6044:1-7.
[102]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.
[103]M.Trajkovic,M.Hedley.Fast comerdetection[J].Image and Vision Computing.1998,16(2):75-87.
[104]陈静.图像配准特征点提取算法研究[M].南京理工大学.2006.
[105]王建琦,邓雁萍,李介谷.一种改进的角点提取方法[J].上海交通大学学报.2000,34(7):913-916.
[106]陈利军,刘侍刚.一种改进的MIC的角点提取方法[J].电子科技.2004,180:34-37.
[107]伊世明.立体匹配中的若干问题研究IM].国防科学技术大学.2006.
[108]M.Armstrong,A.Zisserman.Robust object tracking[C].Proceedings of Second Asian Conference on Computer Vision.Singapore,1995:58-62.
[109]E.Rosten,T.Drummond.Machine learning for high-speed comer detection[C].Proceedings of the European Conference on Computer Vision,2006,1(1):430-443.
[110]E.Rosten.High performance rigid body tracking[D].UK:Churchill College University of Cambridge,2006.
[111]J.R.Quinlan.Induction ofdecisiontrees.Mach.Learn(l),1986:81-106.
[112]张玉冰,罗青山,曾贵华.基于部件的对象实时跟踪.计算机工程与应用[J].2008,44(7):69-71.
[113]E.Rosten,T.Drummond.Fusing points and lines for high performance tracking.Proceedings of the 10th IEEE International Conference on Computer Vision(2),2005:1508-1515.
[114]E.Rosten,G.Reitmayr,T.Drummond.Real-Time Video Annotations for ugmented Reality.Lecture Notes in Computer Science,Advances in Visual Computing(3804),2005:294-302.
[115]P.R.Beaudet.Rotational invariant image operators[C].Proceedings of the IEEE International Conference on Pattern Recognition,1978:579-583.
[116]L.Dreschler,H.Nagel.Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene[J].Computer Graphics and Image Processing.1982,20(3):199-228.
[117]R.Deriche,G.Giraudon.Accurate comer detection:an analytical study[C].Proceedings of the IEEE International Conference on Computer Vision,1990:66-70.
[118]R.Deriche,G.Giraudon.A computational approach for comer and vertex detection[J].International Journal Computer Vision.1993.10(2):101-124.
[119]L.Kitchen,A.Rosenfeld.Gray-level comer detection.Pattern RecognitionLetters.1982,1(2):95-102.
[120]C.Chin-Hsing,L.Jiann-Shu,S.Yung-Nien.Wavelet transformation for gray-level comer detection.Pattern Recognition.1995,28(6):853-861.
[121]W.F(o|¨)rstner,E.G(u|¨)lch.A fast operator for detection and precise location of distinct points,corners and centres of circular features,ISPRS Intercommission Conf.Fast Processing Photogrammetric Data,1987:281-305.
[122]H.Wang,M.Brady.Real-time corner detection algorithm for motion estimation.Image and Vision Computing.1995,13(9):695-703.
[123]F.Mokhtarian,R.Suomela.Robust Image Corner Detection through Curvature Scale Space.IEEE Transactions on pattern analysis and machine intelligence.1998,20(12):1376-1381.
[124]F.Mokhtarian,F.Mohanna.Performance evaluation of corner detectors using consistency and accuracy measures.Computer Vision Image Understand.2006,102(1):81-94.
[125]J.L.Crowley,A.C.Parker.A representation for shape based on peaks and ridges in the difference of low-pass transform [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(2):156-170.
[126]D.Lowe.Object recognition from local scale-invariant features[C].Proceedings of the International Conference on Computer Vision,Corfu,1999:1150-1157.
[127]A.Basharat,Y.Zhai,M.Shah.Content based video matching using spatiotemporal volumes[J].Computer Vision and Image Understanding.2007:1-18.
[128]M.Moradi,P.Abolmaesumi.Medical image registration based on distinctive image features from scale-invariant(SIFT)key-points[J].Proceedings of 19th Computer-Assisted Radiology and Surgery Conference.2005(1281):1292.
[129]霍春雷,周志鑫,刘青山,卢汉清．基于SIFT特征和广义紧互对原型对距离的遥感图像配准方法遥感技术与应用[J]．2007,22(4)：524-530．
[130]E.Delponte,F.Isgro,F.Odone et al.SVD-matching using SIFT features [J].Graphical Models,2006,68(5-6):415-431.
[131]Y.Ke,R.Sukthankar.PCA-SIFT:A More Distinctive Representation for Local Image Descriptors[C].Proceedings of the Conference on Computer Vision and Pattern Recognition.2004:511-517.
[132]M.Artaˇc,A.Leonardis.Outdoor mobile robot localization using global and local features[C].Proceedings of the 9th Computer Vision Winter Workshop,Slovenian Pattern Recognition Society,Piran,2004:175-184.
[133]L.Ledwich,S.Williams.Reduced SIFT features for image retrieval and indoor localization[C].Proceedings of Australian Conference on Robotics and Automation,2004.
[134]D.Cobzas,H.Zhang.Using image-based panoramic models for 2D robot localization [C].Proceedings of the Conference on Western Computing Graphics Symposium,Panorama Mountain Village,Canada,2000:1-7.
[135]H.Tamimi,H.Andreasson,A.reptowetal.Localization of mobile robots with omnidirectional vision using Particle Filter and iterative SIFT [J].Robotics and Autonomous Systems.2006,54(9):758-765.
[136]K.Mikolajczyk,C.Schmid.Indexing based on scale invariant interest points[C].Proceedings of the IEEE International Conference on Computer Vision,2001:525-531.
[137]H.V.Netoa,U.Nehmzowb.Visual novelty detection with automatic scale selection [J].Robotics and Autonomous Systems(55),2007:693-701.
[138]陈白帆,蔡自兴.基于尺度空间理论的Harris角点检测[J].中南大学学报(自然科学版).2005,36(5):751-754.
[139]T.Lindeberg.Feature detection with automatic scale selection[J].International Journal of Computer Vision,1998,30(2):77-116.
[140]K.Mikolajczyk,C.Schmid.Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.
[141]P.Moreels,P.Perona.Evaluation of Features Detectors and Descriptors based on 3D Objects [J].International Journal of Computer Vision.2007,73(3).263-284.
[142]M.Tone.N.Hamada.Scale Change and Rotation Invariant Digital Image Watermarking Method [J].Systems and Computers in Japan.2007,38(10):1-9.
[143]H.Bay,A.Ess,T.Tuytelaars etal.Speeded-Up Robust Features(SURF)[C].Proceedings of the 9th European Conference on Computer Vision,2006:404-417.
[144]Z.Chang,C.Yaowu,K.JayLin.Fast detection of overlapped areas in smart camera network [J].Chinese Journal of Scientific Instrument.2007,28(7):1153-1158.
[145]K.Mikolajczyk,T.Tuytelaars,C.Schmid et al.A comparison of affine region detectors [J].International Journal on Computer Vision,2005,65(1/2):43-72.
[146]L.Jing,N.Allinson.A comprehensive review of current local features for computer vision [J].Neurocomputing,2008(2):1-17.
[147]T.Tuytelaars,L.Van Gool.Matching Widely Separated Views based on Affine Invariant Regions [J].International Journal on Computer Vision,2004,59(1):61-85.
[148]M.Banerjee,M.K.Kundu.Edge based features for content based imagere trieval[J].Pattern Recognition,2003,36(11):2649-2661.
[149]L.Hua,Y.Shui-Cheng,P.Li-Zhong.Robust non-frontal face alignment with edge based texture [J].Journal of Computer Science and Technology,2005,20(6):849-854.
[150]K.Mikolajczyk,A.Zisserman,C.Schmid.Shape recognition with edge-based features[C].Proceedings of the British Machine Vision Conference,2003,2:779-788.
[151]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.
[152]P.Michal,M.Jiri,O.Stepan.Stable Affine Frames on Isophotes[C].Proceedings of the IEEE 11th International Conference on Computer Vision,2007:1-8.
[153]F.Per-Erik.Maximally Stable Colour Regions for Recognition and Matching[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2007:1-8.
[154]T.Kadir,M.Brady,Scale,Saliency and image description[J].International Journal of Computer Vision.2001,45(2):83-105.
[155]T.Kadir,A.Zisserman,M.Brady.An affine invariant salient region detector[C].Proceedings of the 8th European Conference on Computer Vision,2004:345-457.
[156]袁武钢,卢正鼎,凌贺飞等.抗几何失真的局部数字水印算法[J].计算机仿真.2008,25(2):157-160.
[157]单列,刘政凯.显著区域检测的建筑物检索[J].声学技术.2007,26(6):1145-1149.
[158]孙即祥.模式识别中的特征提取与计算机视觉不变量.北京:国防工业出版社,2001.
[159]T.Iijima.Basic theory of pattern normalization(for the case of a typical one dimensional pattern)[J].Bulletin oftheElectro-technical laboratory.1962,26:368-388.
[160]M.Nagao.Edge Preserving Smoothing[J].CGIP,1979,9:394-407.
[161]D.Marr,E.Hildreth.Theory of Edge Detection[C].Proceedings of the Royal Society of London.Series B,Biological Sciences,1980,207(1167):187-217.
[162]T.Lindeberg.Scale-space for discrete signals.IEEE Trans.PAMI,1980,207:187-217.
[163]A.Witkin.Scale-space Filtering[C].International Joint Conference on Artificial Intelligence,Karlsruhe,West Germany.1983:1019-1022.
[164]J.Koenderink.The structure of images.Biological Cybernetics,1984,50:363-396.
[165]T.Lindeberg.Detecting salient blob-like image structures and their scales with a scale-space primal sketch:A method for focus-of-attention.International Journal of Computer Vision,1993,11(3):283-318.
[166]T.Lindeberg.Scale-space theory:A basic tool for analysing structures at different scales.Journal of Applied Statistics,1994,21(2):224-270.
[167]T.Lindeberg.Scale space:A frame work for handling image structures at multiple scales.Porc.CERN school of Computering,the Netherlands,1996:695-702.
[168]T.Lindeberg.Edge detection and ridge detection with automatic scale selection[A].IEEE Conf Computer Vision Pattern Recognition[C].SanFrancisco:IEEE CS Press.1996.
[169]L.Bretzner,T.Lindeberg.Feature tracking with automatic selection of spatial scales[J].Computer Vision and Image Understanding,1998,71(3):385-392.
[170]I.Laptev,T.Lindeberg.Tracking of Multi-state Hand Models Using Particle Filtering and a Hierarchy of Multi-scale Image Features[C].Proceedings of the 3rd International Conference on Scale Space and Morphology in Computer Vision,Vancouver,2001:63-74.
[171]孙剑,徐宗本.计算机视觉中的尺度空间方法.工程数学学报.2005,22(6):951-962.
[172]章毓晋.图像工程.北京:清华大学出版社,2007.
[173]夏良正.数字图像处理修订版.南京:东南大学出版社,1999.
[174]阮秋琦.数字图像处理学.北京:电子工业出版社,2001.
[175]K.Castleman著,朱志刚等译.数字图像处理.北京:电子工业出版社,1998.
[176]龚声蓉,刘纯平,王强等.数字图像处理与分析.北京:清华大学出版社,2006.
[177]K.Rangarajan,M.Shah,D.Brackle.Optimal corner detector.Computer Vision,Graphics,and Image Processing.1989,48(2):230-245.
[178]R.Mehrotra,S.Nichani,N.Ranganathan.Corner detection.Pattern Recognition.1990,23(11):1223-1233.
[179]孙即祥.图像分析.北京:科学出版社,2005。
[180]R.Hartley,A.Zisserman.Multipl View Geometry in Computer Vision.Cambridge University Press:2000.
[181]B.Bracewell.Two-Dimensional Imaging.Prentice Hall:1995.
[182]M.Hu.Visual Pattern Recognition by Moment Invariants,IRE Trans.Inform.Theory,1962,IT-8(2):179-187.
[183]Y.Hel-Or,C.Teo.PatrickA.Common Frarnework for Steerability,Motion Estimation,and Invariant Feature Detection.Proceeding of the IEEE International Symposium on Circuits and System,1998:337-340.
[184]Y.Zhengwei,S.Fernand.Cross-Weighted Moments and Afrine Invariants for Image Registration and Matching.IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(8):804-814.
[185]陈涛.图像仿射不变特征提取方法研究[D].国防科技大学.2006年.
[186]L.Vincent,P.Soille.Watersheds in digital spaces:an efficient algorithm based on immersion simulations.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[187]T.Cormen,C.Leiserson,R.Rivest,et al.Introduction to Algorithms.MIT Press and McGraw-Hill Book Co.,second edition:2001.
[188]E.Murphy-Chutorian,M.Trivedi.N-tree disjoint-set foreset for maximally stable extremal regions.Proceedings of the British Machine Vision Conference,2006.
[189]R.Tarjan.Worst-cases analysis of set union algorithms.J.ACM.1984,31(2):245-281.
[190]Z.Galil.Data structures and algorithms for disjoint set union problems.ACM,Computing Surveys,1991,23(3):320-344.
[191]L.Najman,M.Couprie.Quasi-linear algorithm for the component tree.In SPIE Vision Geometry,2004,5300(Ⅻ):98-107.
[192]牛津大学机器人研究小组:http://www.robots.ox.ac.uk/-vgg/research/affine/index.html
[193]彭勃,周文晖,刘济林.基于Harris角点检测的立体视觉里程计[J].兵工学报,2007,28(12):1498-1502.
[194]K.Mikolajczyk.Interest point detection invariant to affine transformations[D].Institut National Polytechnique de Grenoble:2002.
[195]王向阳.邬俊.侯丽敏.一种基于图像特征点的数字水印潜入方法.电子学报.2007,35(7):1318-1322.
[196]R.Duda.P.Hart.Pattern Classification and Scene Analysis.Wiley-Interscience:1973.
[197]O.Chomat,V.Verdiere,D.Hall et al.Local scale selection for Gaussian based description techniques[C].Proceedings of the 6th European Conference on Computer Vision.Dublin,Ireland,2000:117-133.
[198]T.Lindeberg,J.Garding,Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structure.Image and Vision Computing,1997,15(6):415-434.
[199]F.Schaffalitzky,A.Zisserman.Multi-view matching for unordered image sets.In Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002:414-431.
[200]K.Mikolajczyk,C.Schmid.An affine invariant interest point detector.In Proceedings of the 7th European Conference on Computer Vision,Copenhagen,Denmark,2002,I:128-142.
[201]A.Blaser.Data Base Techniques for Pictorial Applications.Lecture Notes in Computer Science,Springer Verlag,New York,Inc.Secaucus,NJ,USA,1980.
[202]S.Ravela,R.Manmatha.Image retrieval by Appearance,ACMSIGIR97,Philadephia PA,USA,278-285.
[203]H.Tamura,N.Yokoya.Image Database System:A Survey.Pattern Recognition,1984,17(1):29-43.
[204]A.Smeuders,M.Worring,S.Santini.Content-Based Image Retrieval at the End of the Early Years[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2000,22(12):1349-1380.
[205]M.Lew,N.Sebe,J.Eakins.Challenges of Image and Video Retrieval [A].Image and Video Retrieval.Lecture Notes in Computer Science,Springer,2002:211-231.
[206]Blobworld,Image retrieval using regions[EB/OL].[2006-12-01].http://elib.cs.berkelev.edu/blobworld/
[207]C.Carson,S.Belongie,H.Greenspan.Blobworld:image segmentation using expectation-maximizations and its application to image querying [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(8):1026-1038.
[208]J.Wang,J.Li,G.Wiederhold.SIMPLIcity:Semantics-Sensitive Integrated Matching for Picture Libraries [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2001,23(9):947-963.
[209]W.Ma,B.Manjunath.Netra:A Toolbox for Navigating Large Image Databases.Multimedia systems,1999,7(3):184-198.
[210]G.Aggarwal,T.V.Ashwin,S.Ghosal.An Image Retrieval System with Automatic Query Modification.IEEE Transaction On Multimedia,2002,4(2),201-214.
[211]G.Aggarwal,P.Dubey,S.Ghosal et al.iPURE:Perceptual and User-friendly Retrieval of Images.Proceedings of IEEE Conference on ICME,NY USA,Aug.2000:693-697.
[212]Photosynth Technology[EB/OL].[2006-12-08].http://labs.live.com/photosynth/.
[213]Autostitch:A new dimension in automatic image stitching[EB/OL].[2006-12-17]Http://www.cs.ubc.ca/～mbrown/autostitch/autostitch.html.
[214]Matthew Brown' s Research Page [EB/OL].[2006-12-18].Http://www.s.bc.a/～mbrown/research/research.html.
[215]Q.Tian,Y.Wu,T.Huang.Combine User Defined Region-of-Interest and Spatial Layout for Image Retrieval[A].IEEE 2000 International Conference on Image Processing(ICIP2000),Vancouver,BC,Cananda,2000,3:746-749.
[216]张健沛,闫锐,杨静.基于兴趣区域的图像检索方法的研究[J].哈尔滨工程大学学报,2003,24(3):283-286.
[217]斯白露.基于感兴趣区域的图像检索方法[D].北京:中科院计算技术研究所,2002.
[218]R.Yates,B.Nero.Modern Information Retfieval.ACM Press,ISBN:020139829,1999.
[219]章毓晋.基于内容的视觉信息检索.北京:科学出版社,2003.
[220]汪彦龙,刘金华,王丽萍.基于对象空间关系的图像检索方法研究[J].计算机技术与发展,16(1),2006:66-69.
[221]E.Sviascio,F.DOnini,M.Mongiello.Spatial layout representation for query-by-sketch content-based image retrieval.Physical Review Letters,2002,23(13):1599-1612.
[222]http://www.qbic.almaden.ibm.com/
[223]董卫军,周明全,耿国华.基于形状-空间关系的图像检索技术[J].计算机工程.31(20),2005:170-172.
[224]孙君顶,毋小省.基于颜色分布特征的图像检索[J].光电子·激光.17(8),2006:1009-1013.
[225]黄元元,何云峰.一种基于颜色特征的图像检索方法[J].中国图象图形学报.11(12),2006:1768-1774.
[226]http://www.ctr.columbia.edu/VisualSEEK/
[227]曾智勇,张学军,崔江涛等.基于显著兴趣点颜色及空间分布的图像检索新方法[J].光子学报.35(2),2006:309-311.
[228]孟繁杰,郭宝龙.一种基于兴趣点颜色及空间分布的图像检索方法[J].西安电子科技大学学报(自然科学版).32(2),2005:751-753.
[229]韩东峰,李文辉,郭武.基于潜在局部区域空间关系学习的物体分类算法[J].计算机学报.30(8),2007:7820-7828.
[230]张健沛,闫锐,杨静.基于兴趣区域的图像检索方法的研究.哈尔滨工程大学学报.24(3),2003:283-286.
[231]李向阳,庄越挺,潘云鹤.基于内容的图像检索技术与系统[J].计算机研究与发展,2001(3):344-354.
[232]J.Sivic,B.Russell,A.Efros et al.Discovering objects and their locationin images,Proceedings of International Conference Computer Vision,2005:370-377.
© 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 |