基于局部图像特征的目标识别和分类方法研究
|
摘要
目标识别和分类方法是当前光学、计算机视觉和人工智能等领域的研究热点,主要包括目标的表达和分类器的设计两个部分。近年来,基于局部图像特征的方法显著发展,本文就是以局部图像特征为基础,通过设计合适的目标表达模型,和适当的分类器,实现对特定目标的识别和分类。
首先对局部图像特征进行了较为深入的研究,好的局部图像特征应具有重复率高、速度快和对图像变换的不变性,从上述三个方面对SIFT, SURF, Daisy等三种当今流行的典型局部图像特征进行了比较。
提出了一种全新的图像点描述符(EPD),利用图像点周围特定窗口内采样像素点的颜色,梯度模值以及梯度方向构成的特征向量对图像点进行描述。将其与SIFT相比,在不变性方面与前者性能相近,但是其低维度在速度上更加具有优势。
EPD描述符不仅适用于描述图像的极值点,而且适用于描述一般的图像点。这一特性使其可以用于稠密立体匹配,并显示了良好的匹配效果。
对于局部图像特征的应用还可以延伸到伪造印章的识别领域,对于印文图像识别的配准难的问题,提出了全新的印章识别新体系,以随机生成的特征线一致性来判定印章的真伪,实验表明,这种方法适用于各种类型和内容的印章识别。
在目标识别研究中,提取了局部图像特征后,采用BoW方法对这些特征向量聚类,形成特征分布直方图；然后采用SVM作为分类器,并且得到了相应的平均分类准确率；最终实现基于局部特征的目标识别和分类。
Object recognition and classification is the hot issue in the fields of optical, computer vision and artificial intelligence etc.. It consists of object representation and classifier design. In recent years, the research of local image features developed fast. This paper presents object classification and recognition based on local image features.
This dissertation studies local image features, a well designed local image features should possess three typical characteristics:repeatable, fast and invariant descriptor to image transformations. We surveyed and compared three popular and widely used local image features using novel evaluation metrics we presented.
In this paper, we use neighborhood pixel characteristics, including HSV color space, Gaussian-weighted gradient magnitudes and orientations, sampled in specific window around interest point to enhance the description. Experimental results show that, the performance of EPD, in the distinctiveness and invariance aspects, is as good as SIFT, while the time cost of descriptor construction and matching is far less than it.
Moreover, the EPD combines more image characteristics, which makes it be able to describe common image points, but not limited to the image extreme points. These advantages make the EPD finding new applications in the field of dense stereo matching, and it shows good match results.
The application of local image features can also be extended to forged seal identification. The difficult problem of forged seal identification is image registration. We proposed the new system of seal identification, it can recognition by the consistency ratio of feature line randomly generated. The results show that this method is applicable to all types and content seals.
The Research in object recognition, after extracting the local image feature, we can use BoW to cluster of these feature vectors in the form of histograms, then use support vector machine as classifier. The goal is object recognition and classification.
首先对局部图像特征进行了较为深入的研究,好的局部图像特征应具有重复率高、速度快和对图像变换的不变性,从上述三个方面对SIFT, SURF, Daisy等三种当今流行的典型局部图像特征进行了比较。
提出了一种全新的图像点描述符(EPD),利用图像点周围特定窗口内采样像素点的颜色,梯度模值以及梯度方向构成的特征向量对图像点进行描述。将其与SIFT相比,在不变性方面与前者性能相近,但是其低维度在速度上更加具有优势。
EPD描述符不仅适用于描述图像的极值点,而且适用于描述一般的图像点。这一特性使其可以用于稠密立体匹配,并显示了良好的匹配效果。
对于局部图像特征的应用还可以延伸到伪造印章的识别领域,对于印文图像识别的配准难的问题,提出了全新的印章识别新体系,以随机生成的特征线一致性来判定印章的真伪,实验表明,这种方法适用于各种类型和内容的印章识别。
在目标识别研究中,提取了局部图像特征后,采用BoW方法对这些特征向量聚类,形成特征分布直方图；然后采用SVM作为分类器,并且得到了相应的平均分类准确率；最终实现基于局部特征的目标识别和分类。
Object recognition and classification is the hot issue in the fields of optical, computer vision and artificial intelligence etc.. It consists of object representation and classifier design. In recent years, the research of local image features developed fast. This paper presents object classification and recognition based on local image features.
This dissertation studies local image features, a well designed local image features should possess three typical characteristics:repeatable, fast and invariant descriptor to image transformations. We surveyed and compared three popular and widely used local image features using novel evaluation metrics we presented.
In this paper, we use neighborhood pixel characteristics, including HSV color space, Gaussian-weighted gradient magnitudes and orientations, sampled in specific window around interest point to enhance the description. Experimental results show that, the performance of EPD, in the distinctiveness and invariance aspects, is as good as SIFT, while the time cost of descriptor construction and matching is far less than it.
Moreover, the EPD combines more image characteristics, which makes it be able to describe common image points, but not limited to the image extreme points. These advantages make the EPD finding new applications in the field of dense stereo matching, and it shows good match results.
The application of local image features can also be extended to forged seal identification. The difficult problem of forged seal identification is image registration. We proposed the new system of seal identification, it can recognition by the consistency ratio of feature line randomly generated. The results show that this method is applicable to all types and content seals.
The Research in object recognition, after extracting the local image feature, we can use BoW to cluster of these feature vectors in the form of histograms, then use support vector machine as classifier. The goal is object recognition and classification.
引文
[1]焦李成,周伟达,张莉等.智能目标识别与分类[M].北京：科学出版社,2010.2-15
[2]张志禹,侣薇.一种基于混合匹配的指纹识别方法[J].微型机与应用,2011,30(2)：42-44
[3]杨定礼,严石,杨银贤.基于空间支持向量域分类器的人脸识别[J].计算机工程与应用,2011,47(2)：176-178
[4]杨晓敏,何小海,吴炜等.一种基于相似度判据的K近邻分类器的车牌字符识别方[J].四川大学学报(自然科学版),2006,43(5)：1043-1047
[5]彭志明,曲宁,崔欣辰.基于OCR的人机交互界面翻译系统[J].计算机应用.2009,29(S2)：388-390
[6]冯元华,王思华,柳宁等.机器视觉技术在博弈智能机器人设计中的应用[J].计算机工程与设计,2009,30(14)：3371-3379
[7]魏志强,黄磊,季筱鹏.基于点特征的序列图像匹配方法研究[J].中国图象图形学报.2009,14(3)：525-530
[8]施鹏.局部特征描述子算法研究[D].上海：上海交通大学,2008
[9]Moravec H, Obstacle avoidance and navigation in the real world by a seeing robot rover[R]. Pennsylvania:Carnegie Mellon University,1980
[10]张小洪,李博,杨丹.一种新的Harris多尺度角点检测[J].电子与信息学报,2007,29(7),1735-1738
[11]David G Lown. Object recognition from local scale-invariant features[A].In:Interna-tional Conference on Computer Vision[C]. Corfu:1999,1150-1157
[12]Herbert Bay, Tinne Tuytelaars, Lucvan Gool. SURF:Speeded up robust features[A]. In: Europeon Conference on Computer Vision [C]. Graz:2006,404-417
[13]Engin Tola, Vincent Lepetit. A fast local descriptor for dense matching[A]. In:Confer-ence on Computer Vision and Pattern Recognition[C]. Alaska:2008,1-8
[14]Shi Dong-cheng; Yan Guo-qing. Combining MSCR detector and PCA-SIFT descriptor for scene recognition[A]. In:2nd International Conference on Advanced Computer Control[C]. Shenyang:2010,136-141
[15]Yixiong Liang, Lingbo Liu, Ying Xu. Multi-task GLOH feature selection for human age estimation[A]. In:Conference on Computer Vision and Pattern Recognition[C]. USA:2011,28-32
[16]L Fei-Fei, R Fergus, P Perona. A Bayesian approach to unsupervised one-shot learning of object categories[A]. In:International Conference on Computer Vision [C]. Nice: 2003,1134-1141
[17]夏小玲,柴望.基于Shape Context的形状匹配方法的改进[J].东华大学学报(自然科学版),2009,35(1)：79-83
[18]程蕾,吴秀清.局部特征几何结构用于目标识别[J].计算机工程与应用,2010,46(26)：191-193
[19]熊亮,刘伟铭.基于背景Codebook模型的前景检测算法[J].科学技术与工程,2010,10(9)：2119-2121
[20]Faraj Alhwarin, Chao Wang, Danijela Ristic-Durrant. Improved SIFT-features matching for object recognition[A]. In:International Academic Conference-Visions of Computer Science[C]. Tokyo:2008,179-190
[21]Yufei Tao, Dimitris Papadias, Xiang Lian. Reverse kNN search in arbitrary dimensionality [A]. In:the Thirtieth international conference on Very large data bases[C]. Toronto:2004,744-755
[22]Leslie C, Eskin E, Noble W S. The spectrum kernel:A string kernel for SVM protein classification[A]. In:the Pacific Symposium on Biocomputing[C]. Singapore:2002, 564-575
[23]R Fergus, P Perona, A Zisserman. A sparse object category model for efficient learning and exhaustive recognition[A]. Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,380-387
[24]Yoav Freund, Robert E Schapire. Experiments with a New Boosting Algorithm. [A]. In: The Thirteenth International Confernce on Machine Learning[C]. Kononenko:1996, 148-156
[25]Son D, Larry Davis. Robust object tracking with regional affine invariant features[A]. In:International Conference on Computer Vision[C]. Brazil:2007,1-8
[26]Matthew Brown, David Lowe. Automatic panoramic image stitching using invariant features[J]. International Journal of Computer Vision,2007,74(1),59-73
[27]Oncel Tuzel, Fatih Porikli, Peter Meer. Region covariance:A fast descriptor for detection and classification[J]. Computer Science,2006,39(52),589-600
[28]Moravec H. Rover visual obstacle avoidance[A]. In:In International Joint Conference on Artificial Intelligence[C]. Vancouver:1981,785-790
[29]C Harris, M Stephens. A combined edge and corner detector[A]. In:the 4th Alvey Vision Conference[C]. Manchester:1988,147-151
[30]David G Lowe. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110
[31]蔺海峰,马宇峰,宋涛。基于SIFT特征目标跟踪算法研究[J]。自动化学报,2010,36(8),1204-1208
[32]T Lindeberg, Scale-space theory A basic tool for analysing structures at different scales. Journal of Applied Statistics,1994,21(2),224-270
[33]David G Lowe, Local feature view clustering for 3D object recognition In:Conference on Computer Vision and Pattern Recognition[C]. Kauai:2001,682-688
[34]Yan Ke, Rahul Sukthankar. PCA-SIFT:A more disitinctive representation for local image descriptors [A]. In:Conference on Computer Vision and Pattern Recognition[C]. Washington:2004,506-513
[35]Pierre Morels, Pietro Perona, Evaluation of features detectors and descriptors based on 3D objects[A]. In:International Conference on Computer Vision[C]. Beijing:2005, 800-807
[36]Krystian Mikolajczyk, Cordelia Schmid. A performance evaluation of local descriptors [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,10(27), 1615-1630
[37]Herbert Bay, Tinne Tuytelaars, Luc Van Gool, etc..Speeded-up robust features (SURF) original publication [J].Computer Vision and Image Understanding,2008,110 (3): 346-359
[38]Christopher Evans. Notes on the Open SURF Library [R]. University of Bristol,2009
[39]刘奇,何明一.基于SURF特征匹配的图像拼接算法[J].测控技术,2010,29(10)：27-31
[40]Engin Tola, Vincent Lepetit, Pascal Fua. Daisy:An efficient dense descriptor applied to wide baseline stereo[J]. Pattern Analysis and Machine Intelligence.2009,32(5), 815-830
[41]Cordelia Schmid, Roger Mohr, Christian Bauckage. Evaluation of interest point detectors [J] International Journal of Computer Vision,2000,37(2):151-172
[42]Krystian Mikolajczyk, Cordelia Schmid, An affine invariant interest point detector[A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002,128-142
[43]Simon Winder, Matthew Brown. Learning local image descriptor [A]. In:Conference on Computer Vision and Pattern Recognition[C].Minneapolis,2007,1-8
[44]Luo Juan, Oubong Gwun. A comparison of SIFT PCA-SIFT and SURF[J]. International Journal of Image Processing,2009,3(4):143-152
[45]Shivani Agarwa, Dan Roth. Learning a sparse representation for object detection [A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002,113-130
[46]杨恒,王庆.一种新的局部不变特征检测和描述算法[J].计算机学报,2010,33(5)：936-944
[47]http://www.robots.ox.ac.uk/～vgg/research/affine
[48]张真书,宋海龙,向晓燕等.采用快速SIFT算法实现目标识别[J].计算机系统应用,2010,6：82-85
[49]张洁玉,陈强,白小晶.一种新的局部不变特征检测和描述算法[J].光电子激光,2009,11：1-4
[50]王诗俊,杨树元.一种新的特征描述符提取和匹配方法[J].计算机工程和应用,2007,43(34)：78-80
[51]Frederik Schaffalitzky, Andrew Zisserman, Multi-View matching for unordered image sets [A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002, 414-431
[52]V Ferrari, T Tuytelaars, L Van Gool, Simultaneous object recognition and segmentation by image exploration[A]. In:Europeon Conference on Computer Vision [C]. Prague,2004,40-54
[53]J Sivic, A Zisserman. Video google:a text retrieval approach to object matching in Videos[A]. In:International Conference on Computer Vision[C]. Beijing,2003, 1470-1478
[54]Serge Belongie, Jitendra Malik, Jan Puzicha. Shape context:A new descriptor for shape matching and object recognition[A]. In:Neural Information Processing Systems[C].2000,831-837
[55]Tuzel O, Porikli F, Meer P, Region Covariance:A Fast descriptor for detection and classification[A]. In:Europeon Conference on Computer Vision [C]. Graz:2006, 589-600
[56]Forstner W, Moonen B. A metric for covariance matrices[R]. Stuttgart University,1999
[57]唐丽,吴成柯,刘侍刚.基于区域增长的立体像对稠密匹配算法[J].计算机学报,2004,27(7)：936-943
[58]赵聪,亓学鹏,柯晶.基于控制点约束及区域相关的立体匹配算法[J].山东理工大学学报(自然科学版),2008,22(6)：64-67
[59]白明,庄严,王伟.双目立体匹配算法的研究与进展[J].控制与决策,2008,23(7)：721-729
[60]杨保海,刘小莉,查代奉.基于视差空间采样的区域增长稠密立体匹配算法[J].计算机应用.2009,29(10)：2690-2692
[61]http://vision.middlebury.edu/stereo/
[62]Daniel Scharstein, Richard Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision,2002, 47(1-3):7-42
[63]印章防伪技术现状[N].中国防伪报道.2008(10)
[64]贾治辉.利用激光.光敏印章机伪造印章印文的鉴定[J].中国司法鉴定,2009,5：20-24
[65]王闯.印章防伪技术探析[J].吉林公安高等专科学校学报,2006,21(3)：46-47
[66]刘蓉,吴德俊.国库凭证真伪鉴别方法急需改进——由“陆峰诈骗案”想到的[J].预算管理与会计,2008,11(02)：54-55
[67]高树辉,谈伪造印章印文的检验[J].中国防伪报道,2009,4：37-39
[68]王树元,彭伟,段晓辉.印章识别方法及其系统[P].中国,110082,1995-02-29
[69]章毅,吕建成等.印章鉴别控制方法[P].中国,100568264,2009-12-09
[70]陈鲤江,刘铁根,陈嘉佳等.基于中心-射线模型的印鉴识别方法及其应用[J].光学技术,2006,32(4)：511-533
[71]刘文娟,何怡刚.印鉴识别系统中印鉴录入的研究[J].计算机科学,2008,35(8)：129-130
[72]倪琦,王新赛,李坚等.基于梯度分割和特征匹配的印章识别算法研究[J].计算机工程与设计,2008,29(20)：5400-5402
[73]戴新亮,孙卫真,关永.印鉴识别中图像预处理问题的研究[J].微计算机信息2007,27：305-306
[74]张栗,孙瑞芹,张凤元.印鉴识别中印章的提取和修复问题研究[J].中国科技信息,2008,17：125-126
[75]刘铁根,邓集杰,张忠传.基于平滑卷积定位的圆形印鉴提取方法研究[J].光电工程,2009,36(4)：1-6
[76]耿建玲,陈纯,陈耀武等.基于小波多尺度分解的印鉴图像配准[J].计算机工程与应用,2006,42(1)：34-36
[77]袁占亭,张秋余,靳艳峰.基于Delaunay与多边形三角剖分的印鉴识别算法[J].模式识别与人工智能,2007,20(2)：261-265
[78]谷斌,靳艳峰,王力娟.基于贪心算法与多边形剖分的印鉴匹配算法[J].计算机工程与设计,2008,29(12)：3136-3138
[79]陈维克,阎新庆,张柱根等.印鉴识别方法和技术研究[J].中国水运,2006,6(12)：134-135
[80]曾维亮,梁春生,张冉.基于边缘最大匹配的印鉴自动识别方法[J].实验科学与技术,2006,4(S1)：88-91
[81]李晗,窦爱萍,解争龙等.基于多特征的支持向量机印鉴识别[J].航空计算技术2006,36(4)：32-34
[82]L Fei-Fei, P Perona. A bayesian hierarchical model for learning natural scene categories [A]. In:Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,1-8
[83]L Fei-Fei, R Fergus, P Perona. Learning generative visual models from few training examples an incremental bayesian approach eested on 101 object categories [A]. In: Conference on Computer Vision and Pattern Recognition [C]. Washington:2004, 59-70
[84]李远宁,刘汀,蒋树强等.基于Bag of Words的视频匹配方法[JJ.通信学报,2007,28(12)：419-425
[85]刘堃.基于整体特征的人体动作的识别[D].南京：南京理工大学,2009
[86]Axel Pinz. Object Categorization[J]. Foundations and Trends in Computer Graphics and Vision,2005,1(4):255-353
[87]杨善林,李永森,胡笑旋等.K-means算法中的k值优化问题研究[J].系统工程理论与实践,2006,26(2)：97-101
[88]汪中,刘贵全,陈恩红.一种优化初始中心点的K-means算法[J].模式识别与人工智能,2009,22(2)：299-304
[89]张玉芳,毛嘉莉,熊忠阳.一种改进的K-means算法[J].计算机应用,2003,23(8)：31-33
[90]http://cat.cvc.uab.es/～joost/master.html
[92]Corinna Cortes,Vladimir Vapnik. Support Vector Networks. machine learning[J].1995, 20(3):273-297
[92]R Fergus, L Fei-Fei, P Perona, A Zisserman. Learning object categories from Google's image search[A]. In:International Conference on Computer Vision[C]. Beijing,2005: 1816-1823
[93]R Fergus, P Perona, A Zisserman. A visual category filter for Google images. [A]. In: Europeon Conference on Computer Vision [C]. Prague,2004,242-256
[94]Alexander C Berg, Tamara L Berg, Jitendra Malik. Shape matching and object recognition using low distortion correspondence [A]. In:Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,26-33
[2]张志禹,侣薇.一种基于混合匹配的指纹识别方法[J].微型机与应用,2011,30(2)：42-44
[3]杨定礼,严石,杨银贤.基于空间支持向量域分类器的人脸识别[J].计算机工程与应用,2011,47(2)：176-178
[4]杨晓敏,何小海,吴炜等.一种基于相似度判据的K近邻分类器的车牌字符识别方[J].四川大学学报(自然科学版),2006,43(5)：1043-1047
[5]彭志明,曲宁,崔欣辰.基于OCR的人机交互界面翻译系统[J].计算机应用.2009,29(S2)：388-390
[6]冯元华,王思华,柳宁等.机器视觉技术在博弈智能机器人设计中的应用[J].计算机工程与设计,2009,30(14)：3371-3379
[7]魏志强,黄磊,季筱鹏.基于点特征的序列图像匹配方法研究[J].中国图象图形学报.2009,14(3)：525-530
[8]施鹏.局部特征描述子算法研究[D].上海：上海交通大学,2008
[9]Moravec H, Obstacle avoidance and navigation in the real world by a seeing robot rover[R]. Pennsylvania:Carnegie Mellon University,1980
[10]张小洪,李博,杨丹.一种新的Harris多尺度角点检测[J].电子与信息学报,2007,29(7),1735-1738
[11]David G Lown. Object recognition from local scale-invariant features[A].In:Interna-tional Conference on Computer Vision[C]. Corfu:1999,1150-1157
[12]Herbert Bay, Tinne Tuytelaars, Lucvan Gool. SURF:Speeded up robust features[A]. In: Europeon Conference on Computer Vision [C]. Graz:2006,404-417
[13]Engin Tola, Vincent Lepetit. A fast local descriptor for dense matching[A]. In:Confer-ence on Computer Vision and Pattern Recognition[C]. Alaska:2008,1-8
[14]Shi Dong-cheng; Yan Guo-qing. Combining MSCR detector and PCA-SIFT descriptor for scene recognition[A]. In:2nd International Conference on Advanced Computer Control[C]. Shenyang:2010,136-141
[15]Yixiong Liang, Lingbo Liu, Ying Xu. Multi-task GLOH feature selection for human age estimation[A]. In:Conference on Computer Vision and Pattern Recognition[C]. USA:2011,28-32
[16]L Fei-Fei, R Fergus, P Perona. A Bayesian approach to unsupervised one-shot learning of object categories[A]. In:International Conference on Computer Vision [C]. Nice: 2003,1134-1141
[17]夏小玲,柴望.基于Shape Context的形状匹配方法的改进[J].东华大学学报(自然科学版),2009,35(1)：79-83
[18]程蕾,吴秀清.局部特征几何结构用于目标识别[J].计算机工程与应用,2010,46(26)：191-193
[19]熊亮,刘伟铭.基于背景Codebook模型的前景检测算法[J].科学技术与工程,2010,10(9)：2119-2121
[20]Faraj Alhwarin, Chao Wang, Danijela Ristic-Durrant. Improved SIFT-features matching for object recognition[A]. In:International Academic Conference-Visions of Computer Science[C]. Tokyo:2008,179-190
[21]Yufei Tao, Dimitris Papadias, Xiang Lian. Reverse kNN search in arbitrary dimensionality [A]. In:the Thirtieth international conference on Very large data bases[C]. Toronto:2004,744-755
[22]Leslie C, Eskin E, Noble W S. The spectrum kernel:A string kernel for SVM protein classification[A]. In:the Pacific Symposium on Biocomputing[C]. Singapore:2002, 564-575
[23]R Fergus, P Perona, A Zisserman. A sparse object category model for efficient learning and exhaustive recognition[A]. Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,380-387
[24]Yoav Freund, Robert E Schapire. Experiments with a New Boosting Algorithm. [A]. In: The Thirteenth International Confernce on Machine Learning[C]. Kononenko:1996, 148-156
[25]Son D, Larry Davis. Robust object tracking with regional affine invariant features[A]. In:International Conference on Computer Vision[C]. Brazil:2007,1-8
[26]Matthew Brown, David Lowe. Automatic panoramic image stitching using invariant features[J]. International Journal of Computer Vision,2007,74(1),59-73
[27]Oncel Tuzel, Fatih Porikli, Peter Meer. Region covariance:A fast descriptor for detection and classification[J]. Computer Science,2006,39(52),589-600
[28]Moravec H. Rover visual obstacle avoidance[A]. In:In International Joint Conference on Artificial Intelligence[C]. Vancouver:1981,785-790
[29]C Harris, M Stephens. A combined edge and corner detector[A]. In:the 4th Alvey Vision Conference[C]. Manchester:1988,147-151
[30]David G Lowe. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110
[31]蔺海峰,马宇峰,宋涛。基于SIFT特征目标跟踪算法研究[J]。自动化学报,2010,36(8),1204-1208
[32]T Lindeberg, Scale-space theory A basic tool for analysing structures at different scales. Journal of Applied Statistics,1994,21(2),224-270
[33]David G Lowe, Local feature view clustering for 3D object recognition In:Conference on Computer Vision and Pattern Recognition[C]. Kauai:2001,682-688
[34]Yan Ke, Rahul Sukthankar. PCA-SIFT:A more disitinctive representation for local image descriptors [A]. In:Conference on Computer Vision and Pattern Recognition[C]. Washington:2004,506-513
[35]Pierre Morels, Pietro Perona, Evaluation of features detectors and descriptors based on 3D objects[A]. In:International Conference on Computer Vision[C]. Beijing:2005, 800-807
[36]Krystian Mikolajczyk, Cordelia Schmid. A performance evaluation of local descriptors [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,10(27), 1615-1630
[37]Herbert Bay, Tinne Tuytelaars, Luc Van Gool, etc..Speeded-up robust features (SURF) original publication [J].Computer Vision and Image Understanding,2008,110 (3): 346-359
[38]Christopher Evans. Notes on the Open SURF Library [R]. University of Bristol,2009
[39]刘奇,何明一.基于SURF特征匹配的图像拼接算法[J].测控技术,2010,29(10)：27-31
[40]Engin Tola, Vincent Lepetit, Pascal Fua. Daisy:An efficient dense descriptor applied to wide baseline stereo[J]. Pattern Analysis and Machine Intelligence.2009,32(5), 815-830
[41]Cordelia Schmid, Roger Mohr, Christian Bauckage. Evaluation of interest point detectors [J] International Journal of Computer Vision,2000,37(2):151-172
[42]Krystian Mikolajczyk, Cordelia Schmid, An affine invariant interest point detector[A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002,128-142
[43]Simon Winder, Matthew Brown. Learning local image descriptor [A]. In:Conference on Computer Vision and Pattern Recognition[C].Minneapolis,2007,1-8
[44]Luo Juan, Oubong Gwun. A comparison of SIFT PCA-SIFT and SURF[J]. International Journal of Image Processing,2009,3(4):143-152
[45]Shivani Agarwa, Dan Roth. Learning a sparse representation for object detection [A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002,113-130
[46]杨恒,王庆.一种新的局部不变特征检测和描述算法[J].计算机学报,2010,33(5)：936-944
[47]http://www.robots.ox.ac.uk/～vgg/research/affine
[48]张真书,宋海龙,向晓燕等.采用快速SIFT算法实现目标识别[J].计算机系统应用,2010,6：82-85
[49]张洁玉,陈强,白小晶.一种新的局部不变特征检测和描述算法[J].光电子激光,2009,11：1-4
[50]王诗俊,杨树元.一种新的特征描述符提取和匹配方法[J].计算机工程和应用,2007,43(34)：78-80
[51]Frederik Schaffalitzky, Andrew Zisserman, Multi-View matching for unordered image sets [A]. In:Europeon Conference on Computer Vision [C]. Denmark,2002, 414-431
[52]V Ferrari, T Tuytelaars, L Van Gool, Simultaneous object recognition and segmentation by image exploration[A]. In:Europeon Conference on Computer Vision [C]. Prague,2004,40-54
[53]J Sivic, A Zisserman. Video google:a text retrieval approach to object matching in Videos[A]. In:International Conference on Computer Vision[C]. Beijing,2003, 1470-1478
[54]Serge Belongie, Jitendra Malik, Jan Puzicha. Shape context:A new descriptor for shape matching and object recognition[A]. In:Neural Information Processing Systems[C].2000,831-837
[55]Tuzel O, Porikli F, Meer P, Region Covariance:A Fast descriptor for detection and classification[A]. In:Europeon Conference on Computer Vision [C]. Graz:2006, 589-600
[56]Forstner W, Moonen B. A metric for covariance matrices[R]. Stuttgart University,1999
[57]唐丽,吴成柯,刘侍刚.基于区域增长的立体像对稠密匹配算法[J].计算机学报,2004,27(7)：936-943
[58]赵聪,亓学鹏,柯晶.基于控制点约束及区域相关的立体匹配算法[J].山东理工大学学报(自然科学版),2008,22(6)：64-67
[59]白明,庄严,王伟.双目立体匹配算法的研究与进展[J].控制与决策,2008,23(7)：721-729
[60]杨保海,刘小莉,查代奉.基于视差空间采样的区域增长稠密立体匹配算法[J].计算机应用.2009,29(10)：2690-2692
[61]http://vision.middlebury.edu/stereo/
[62]Daniel Scharstein, Richard Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision,2002, 47(1-3):7-42
[63]印章防伪技术现状[N].中国防伪报道.2008(10)
[64]贾治辉.利用激光.光敏印章机伪造印章印文的鉴定[J].中国司法鉴定,2009,5：20-24
[65]王闯.印章防伪技术探析[J].吉林公安高等专科学校学报,2006,21(3)：46-47
[66]刘蓉,吴德俊.国库凭证真伪鉴别方法急需改进——由“陆峰诈骗案”想到的[J].预算管理与会计,2008,11(02)：54-55
[67]高树辉,谈伪造印章印文的检验[J].中国防伪报道,2009,4：37-39
[68]王树元,彭伟,段晓辉.印章识别方法及其系统[P].中国,110082,1995-02-29
[69]章毅,吕建成等.印章鉴别控制方法[P].中国,100568264,2009-12-09
[70]陈鲤江,刘铁根,陈嘉佳等.基于中心-射线模型的印鉴识别方法及其应用[J].光学技术,2006,32(4)：511-533
[71]刘文娟,何怡刚.印鉴识别系统中印鉴录入的研究[J].计算机科学,2008,35(8)：129-130
[72]倪琦,王新赛,李坚等.基于梯度分割和特征匹配的印章识别算法研究[J].计算机工程与设计,2008,29(20)：5400-5402
[73]戴新亮,孙卫真,关永.印鉴识别中图像预处理问题的研究[J].微计算机信息2007,27：305-306
[74]张栗,孙瑞芹,张凤元.印鉴识别中印章的提取和修复问题研究[J].中国科技信息,2008,17：125-126
[75]刘铁根,邓集杰,张忠传.基于平滑卷积定位的圆形印鉴提取方法研究[J].光电工程,2009,36(4)：1-6
[76]耿建玲,陈纯,陈耀武等.基于小波多尺度分解的印鉴图像配准[J].计算机工程与应用,2006,42(1)：34-36
[77]袁占亭,张秋余,靳艳峰.基于Delaunay与多边形三角剖分的印鉴识别算法[J].模式识别与人工智能,2007,20(2)：261-265
[78]谷斌,靳艳峰,王力娟.基于贪心算法与多边形剖分的印鉴匹配算法[J].计算机工程与设计,2008,29(12)：3136-3138
[79]陈维克,阎新庆,张柱根等.印鉴识别方法和技术研究[J].中国水运,2006,6(12)：134-135
[80]曾维亮,梁春生,张冉.基于边缘最大匹配的印鉴自动识别方法[J].实验科学与技术,2006,4(S1)：88-91
[81]李晗,窦爱萍,解争龙等.基于多特征的支持向量机印鉴识别[J].航空计算技术2006,36(4)：32-34
[82]L Fei-Fei, P Perona. A bayesian hierarchical model for learning natural scene categories [A]. In:Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,1-8
[83]L Fei-Fei, R Fergus, P Perona. Learning generative visual models from few training examples an incremental bayesian approach eested on 101 object categories [A]. In: Conference on Computer Vision and Pattern Recognition [C]. Washington:2004, 59-70
[84]李远宁,刘汀,蒋树强等.基于Bag of Words的视频匹配方法[JJ.通信学报,2007,28(12)：419-425
[85]刘堃.基于整体特征的人体动作的识别[D].南京：南京理工大学,2009
[86]Axel Pinz. Object Categorization[J]. Foundations and Trends in Computer Graphics and Vision,2005,1(4):255-353
[87]杨善林,李永森,胡笑旋等.K-means算法中的k值优化问题研究[J].系统工程理论与实践,2006,26(2)：97-101
[88]汪中,刘贵全,陈恩红.一种优化初始中心点的K-means算法[J].模式识别与人工智能,2009,22(2)：299-304
[89]张玉芳,毛嘉莉,熊忠阳.一种改进的K-means算法[J].计算机应用,2003,23(8)：31-33
[90]http://cat.cvc.uab.es/～joost/master.html
[92]Corinna Cortes,Vladimir Vapnik. Support Vector Networks. machine learning[J].1995, 20(3):273-297
[92]R Fergus, L Fei-Fei, P Perona, A Zisserman. Learning object categories from Google's image search[A]. In:International Conference on Computer Vision[C]. Beijing,2005: 1816-1823
[93]R Fergus, P Perona, A Zisserman. A visual category filter for Google images. [A]. In: Europeon Conference on Computer Vision [C]. Prague,2004,242-256
[94]Alexander C Berg, Tamara L Berg, Jitendra Malik. Shape matching and object recognition using low distortion correspondence [A]. In:Conference on Computer Vision and Pattern Recognition[C]. San Diego:2005,26-33
© 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 |