跳到主要內容

臺灣博碩士論文加值系統

(35.173.42.124) 您好!臺灣時間:2021/07/26 12:16
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:劉英和
研究生(外文):Ying-Ho Liu
論文名稱:使用具鑑別力原型之物件辨識方法
論文名稱(外文):Object Recognition Using Discriminative Prototypes
指導教授:李瑞庭李瑞庭引用關係
學位類別:博士
校院名稱:國立臺灣大學
系所名稱:資訊管理學研究所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:英文
論文頁數:86
中文關鍵詞:具鑑別力的區域顯著區域Crisp Construction Process演算法原型C4.5決策樹
外文關鍵詞:discriminative regionsalient regionCrisp Construction Process algorithmprototypeC4.5 decision tree
相關次數:
  • 被引用被引用:0
  • 點閱點閱:126
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
許多物件辨識方法利用物件上的顯著區域(salient region)增進它們辨識形變後或被遮蔽物件的穩定性。但如果不同的物件擁有相同或是類似的顯著區域,這些方法將難以辨識這些物件。此外,如果沒有非常仔細地挑選顯著區域,辨識的效果也將會大打折扣。
因此在本論文中,我們利用具鑑別力的區域(discriminative region)來進行物件辨識。我們提出的方法包括訓練及測試兩階段。在訓練階段,我們利用不同大小的移動視窗(sliding window)在訓練物件上循序取出一個一個區域。接著將每個區域轉換成一個特徵向量,而每一個特徵向量包括color histogram、intensity moments、affine invariant moments及SIFT descriptor四種特徵。然後,我們應用Crisp Construction Process演算法,從訓練特徵向量中,為每一個訓練物件取出一組原型(prototype)。所取出的原型可用來區分此物件與其他物件,也就是說,這些原型即是此物件上具鑑別力的區域。在測試階段,我們同樣使用移動視窗在測試物件上循序取出一個一個區域,然後,將每個區域轉成特徵向量並找出它最接近的原型,亦即測試物件上此區域屬於該原型所代表的區域。因此,我們可以為每個訓練物件與該測試物件計算一個分數,以代表它們之間的相似程度。我們利用訓練物件的面積、測試物件的面積、測試物件上屬於訓練物件的區域的面積及該訓練物件上為測試物件所屬的區域的面積來計算分數,然後將測試物件歸屬於得分最高的訓練物件。另外,我們亦採用C4.5決策樹(C4.5 decision tree)以加速辨識流程。我們的方法對於形變後、被遮蔽、有光影變化及複雜背景的物件具有極佳的辨識能力。對於被噪訊干擾及受JPEG壓縮過後的影像也有很好的辨識能力。
實驗結果顯示,我們的方法在辨識COIL-100及ZuBuD資料庫上,表現均優於其他物件辨識方法。若採用C4.5決策樹加速,辨識速度可提升五至八倍。
Many previously proposed methods of object recognition use the salient regions of the objects to improve their robustness to distortion and occlusion. The methods based on salient regions inevitably encounter the difficulties if several different objects share identical or similar salient regions. Moreover, if the salient regions cannot be selected very carefully, the performance will be deteriorated incredibly.
Therefore, in this dissertation, we propose a method which uses discriminative regions rather than salient regions to perform object recognition. Our proposed method consists of two phases, namely, training and testing. In the training phase, we first use sliding windows of different sizes to retrieve a number of regions from an object. For each region retrieved, we extract a feature vector, each of which contains four types of descriptors, namely, color histogram, intensity moments, affine invariant moments, and SIFT descriptor. Then, the Crisp Construction Process algorithm is applied to these training feature vectors to generate a number of prototypes for each model object. The prototypes of a model object can be used to discriminate it from the others. That is, the prototypes are the discriminative regions of the model object. In the testing phase, we also use sliding windows to extract the feature vectors of a test object. For each feature vector extracted, we find its nearest prototype and assign it to the discriminative region represented by the nearest prototype. Then, we compute a score for each model object according to the area of the model object, the area of the test object, the area covered by the feature vectors that are assigned to the model object, and the area covered by the assigned discriminative regions. The test object is considered as the model object with the highest score. Moreover, we adopt C4.5 decision tree to speed up the recognition process. Our proposed method is robust to distortion, occlusion, illumination changes, and cluttered background. Noisy and compressed images can also be well recognized.
The experimental results show that our proposed method outperforms the comparing methods in the COIL-100 and ZuBuD datasets in terms of recognition rates. By adopting the C4.5 decision tree, the recognition process becomes 5 - 8 faster.
論文摘要 i
Dissertation Abstract ii
Table of Contents iv
List of Figures vi
List of Tables viii
Chapter 1 Introduction 1
1.1 Motivations 3
1.2 Problem Statement 5
1.3 Overview of the Proposed Method 6
1.4 Contributions 8
1.5 Terminologies 9
1.6 Dissertation Layout 11
Chapter 2 Background and Literature Survey 12
2.1 Geometry-based Methods 12
2.2 Appearance-based Methods 15
2.3 Discussion 19
Chapter 3 The Proposed Method 23
3.1 The Feature Extraction Component 26
3.1.1 Color histogram in the HSV color space 28
3.1.2 Intensity moments 29
3.1.3 Affine invariant moments 30
3.1.4 Scale invariant feature transform (SIFT) 30
3.1.5 Summary 33
3.2 The Learning Component 33
3.3 The Recognition Component 39
Chapter 4 Acceleration Techniques 42
4.1 Accelerating the Learning Process 42
4.2 Incremental Learning 44
4.3 Decision Tree Acceleration Technique 45
Chapter 5 Performance Evaluation 48
5.1 Datasets and Experiment Setup 48
5.2 Descriptor Selections 51
5.3 Recognition without the Decision Tree Acceleration Technique 55
5.3.1 Recognition performance on the COIL-100 dataset 55
5.3.2 Recognition performance on the ZuBuD dataset 58
5.4 Recognition with the Decision Tree Acceleration Technique 59
5.4.1 Selecting the value of the threshold L 59
5.4.2 Recognition performance on the COIL-100 dataset 61
5.4.3 Recognition performance on the ZuBuD dataset 63
5.5 Recognition of Occluded Objects 63
5.6 The Incremental Learning of the Proposed Method 65
5.7 Recognition of Scaled Objects 65
5.8 Recognition of Noisy and Compressed Images 68
5.9 Summary 70
Chapter 6 Conclusions and Future Work 73
References 76
[1]S. Agarwal and D. Roth, “Learning a sparse representation for object detection,” In Proc. European Conference on Computer Vision, pp. 113-130, 2002.
[2]A.R. Ahmadyfard and J. Kittler, “Using relaxation technique for region-based object recognition,” Image and Vision Computing, vol. 20, pp. 769-781, 2002.
[3]P.N. Belhumeur, J. Hespanda, and D. Kriegeman, “Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, 1997.
[4]A. Berg, T. Berg, and J. Malik, “Shape matching and object recognition using low distortion correspondence,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 26-33, 2005.
[5]M. Bertozzi, A. Broggi, M. Del Rose, M. Felisa, A. Rakotomamonjy, and F. Suard, “A pedestrian detector using histograms of oriented gradients and a support vector machine classifier,” In Proc. Intelligent Transportation Systems Conference, pp. 143-148, 2007.
[6]I. Biederman, “Recognition-by-components: A theory of human image understanding,” Psychological Review, vol. 94, no. 2, pp. 115-147, 1987.
[7]J.A. Bilmes, “A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models,” Technical Report TR-97-021, International Computer Science Institute and Computer Science Division, University of California at Berkeley, April 1998.
[8]J. Burianek, A. Ahmadyfard, and J. Kittler, “SOIL-47, the surrey object image library,” Centre for Vision, Speach and Signal Processing, University of Surrey, http://www.ee.surrey.ac.uk/Research/VSSP/demos/colour/soil47/
[9]B. Caputo, J. Hornegger, D. Paulus, and H. Niemann, “A spin-glass Markov random field for 3-D object recognition,” Technical Report LME-TR-2002-01, Lehrstuhl für Mustererkennung, Institut für Informatik, Universität Erlangen-Nürnberg, 2002.
[10]O. Carmichael and M. Hebert, “Shape-based recognition of wiry objects,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 26, pp. 1537-1552, 2004.
[11]C.H. Chou, C.C. Lin, Y.H. Liu, and F. Chang, “A prototype classification method and its use in a hybrid solution for multiclass pattern recognition,” Pattern Recognition, vol. 39, no. 4, pp. 624-634, 2006.
[12]D. Comaniciu and P. Meer, “Robust analysis of feature spaces: Color image segmentation,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 750-755, 1997.
[13]N. Dalal and B. Triggs, “Histogram of oriented gradients for human detection,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 886-893, 2005.
[14]P. David and D. DeMenthon, “Object recognition in high clutter images using line features,” In Proc. International Conference on Computer Vision, vol. 2, pp. 1581-1588, 2005.
[15]G.Y. Dorkó and C. Schmid, “Selection of scale-invariant parts for object class recognition,” In Proc. International Conference on Computer Vision, pp. 634-640, 2003.
[16]R.O. Duda, P.E. Hart, and D.G. Stork, Pattern Classification, 2nd edition, New York: John Wiley & Sons Inc., 2001.
[17]J.C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters,” Journal of Cybernetics, vol. 3, pp. 32-57, 1974.
[18]B. Epshtein and S. Ullman, “Feature hierarchies for object classification,” In Proc. International Conference on Computer Vision, pp. 220-227, 2005.
[19]R. Fay, F. Schwenker, and G. Palm, “Incremental learning in hierarchical neural networks for object recognition,” In Proc. International Conference on Informatics in Control, pp. 298-303, 2005.

[20]L. Fei-Fei, R. Fergus, and P. Perona. “Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 178-178, 2004.
[21]R. Fergus, P. Perona, and A. Zisserman, “Object class recognition by unsupervised scale-invariant learning,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 264-271, 2003.
[22]R. Fergus, P. Perona, and A. Zisserman, “A visual category filter for google images,” In Proc. European Conference on Computer Vision, pp. 242-256, 2004.
[23]R. Fergus, P. Perona, and A. Zisserman, “A sparse object category model for efficient learning and exhaustive recognition,” In Proc. International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 380-387, 2005.
[24]V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid. “Groups of adjacent contour segments for object detection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30, pp. 36-51, 2008.
[25]C. Fraley, “Algorithms for model-based gaussian hierarchical clustering,” SIAM Journal on Scientific Computing, vol. 20, pp. 270-281, 1999.
[26]Y. Freund and R. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, vol. 55, pp. 119-139, 1997.
[27]B.J. Frey and D. Dueck, “Clustering by passing messages between data points,” Science, vol. 315, pp. 972-976, 2007.
[28]M. Fritz, B. Leibe, B. Caputo, and B. Schiele, “Integrating representative and discriminant models for object category detection,” In Proc. International Conference on Computer Vision, pp. 1363-1370, 2005.
[29]G. Fritz, C. Seifert, and L. Paletta, “A mobile vision system for urban detection with informative local descriptors,” In Proc. International Conference on Computer Vision Systems, pp. 30-30, 2006.

[30]K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd edition, New York: Academic Press, 1990.
[31]B.V. Funt and G.D. Finlayson, “Color constant color indexing,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 17, pp. 522-529, 1995.
[32]J.M. Geusebroek, G.J. Burghouts, and A.W.M. Smeulders, “The Amsterdam library of object images,” International Journal of Computer Vision, vol. 61, no. 1, pp. 103-112, 2005.
[33]T. Goedeme, T. Tuytelaars, and L. van Gool, “Fast wide baseline matching for visual navigation,” In Proc. International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 24-29, 2004.
[34]R. Gomes, M. Welling, and P. Perona, “Incremental learning of nonparametric bayesian mixture models,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[35]N.J.C. Groeneweg, B. de Groot, A.H.R. Halma, B.R. Quiroga, M. Tromp, and F.C.A. Groen, “A fast offline building recognition application on a mobile telephone,” Lecture Notes in Computer Science, vol. 4179, pp. 1122-1132, 2006.
[36]A. Haar, Zur Theorie der orthogonalen Funktionensysteme, (German) Mathematische Annalen, vol. 69, no. 3, pp. 331-371, 1910.
[37]R.M. Haralick and L.G. Shapiro, Computer and Robot Vision, Vol. I, Boston: Addison Wesley Longman Publishing Co., Inc., 1992.
[38]G. Healey and D.A. Slater, “Using illumination invariant color histogram descriptors for recognition,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 355-360, 1994.
[39]J. Holland, “Adaptation in Neural and Artificial Systems,” Michigan: University of Michigan Press, 1975.
[40]A. Holub and P. Perona, “A discriminative framework for modelling object classes,” in Proc. International Conference on Computer Vision and Pattern Recognition, pp. 664-671, 2005.

[41]A.D. Holub, M. Welling, and P. Perona, “Combining generative models and fisher kernels for object recognition,” In Proc. International Conference on Computer Vision, vol. 1, pp. 136-143, 2005.
[42]D. Hoffman and W. Richards, “Parts of recognition,” In A. Pentland (ed), From Pixels to Predicates, Norwood: Ablex Publishing, 1985.
[43]M.K. Hu, “Visual pattern recognition by moment invariants,” IRE Trans. on Information Theory, pp. 179-187, 1962.
[44]J. Huang, S. Kumar, M. Mitra, W.J. Zhu, and R. Zabih, “Image indexing using color correlogram,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 762-768, 1997.
[45]F.J. Huang, and Y. LeCun, “Large-scale learning with SVM and convolutional nets for generic object categorization,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 284-291, 2006.
[46]A.K. Jain and F. Farrokhnia, “Unsupervised texture segmentation using Gabor filters,” Pattern Recognition, vol. 24, no. 12, pp. 1167-1186, 1991.
[47]L. Kaufman and P. Rousseau, Finding Groups in Data, New York: John Wiley and Sons, 1990.
[48]T.C. Kietzmann, S. Lange, and M. Riedmiller, “Incremental GRLVQ: Learning relevant features for 3D object recognition,” Nurocomputing, vol. 71, pp. 2868-2879, 2008.
[49]T.K. Kim, J. Kittler, and R. Cipolla, “Discriminative learning and recognition of image set classes using canonical correlations,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1005-1018, 2007.
[50]T.K. Kim, J. Kittler, and R. Cipolla, “Incremental learning of locally orthogonal subspaces for set-based object recognition,” In Proc. British Machine Vision Conference, pp. 559-568, 2006.
[51]P. Kohli, J. Rihan, M. Bray, and P.H.S. Torr, “Simultaneous segmentation and pose estimation of humans using dynamic graph cuts,” International Journal of Computer Vision, vol. 79, no. 3, pp. 285-298, 2008.
[52]T. Kohonen, “Self-organizing maps,” Series in Information Sciences, vol. 30, Heidelberg: Springer, 1997.
[53]D. Koubaroulis, J. Matas, and J. Kittler, “Evaluating colour-based object recognition algorithms using the SOIL-47 Database,” In Proc. Asian Conference on Computer Vision, pp. 840-845, 2002.
[54]Y. LeCun, F.J. Huang, and L. Bottou, “Learning methods for generic object recognition with invariance to pose and lighting,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 97-104, 2004.
[55]B. Leibe, A. Leonardis, and B. Schiele, “Combined object categorization and segmentation with an implicit shape model,” In Proc. European Conference on Computer Vision, pp. 17-32, 2004.
[56]B. Leibe and B. Schiele, “Scale-invariant object categorization using a scale-adaptive mean-shift search,” In Proc. German Association on Pattern Recognition, pp. 145-153, 2004.
[57]T.K. Leung, M.C. Burl, and P. Perona, “Probabilistic affine invariants for recognition,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 678-684, 1998.
[58]Q. Liu, H. Jin, X. Tang, H. Lu, and S. Ma, “A new extension of kernel feature and its application for visual recognition,” Neurocomputing, vol. 71, pp. 1850-1856, 2008.
[59]X. Liu and A. Srivastava. “A spectral representation for appearance-based classification and recognition,” In Proc. International Conference on Pattern Recognition, pp. 37-40, 2002.
[60]Y.H. Liu, C.C. Lin, W.H. Lin, and F. Chang, “Accelerating feature-vector matching using multiple-tree and sub-vector methods,” Pattern Recognition, vol. 40, no. 9, pp. 2392-2399, 2007.
[61]Y.H. Liu, C.C. Lin, W.H. Lin, and F. Chang, “Fast vector matching methods and their applications to handwriting recognition,” In Proc. International Conference on Document Analysis and Recognition, pp. 871-875, 2005.
[62]D.G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 2, no .60, pp. 91-110, 2004.
[63]D.G. Lowe, “Object recognition from local scale-Invariant features,” In Proc. International Conference on Computer Vision, pp. 1150-1157, 1999.
[64]J.B. MacQueen, “Some methods for classification and analysis of multivariate observations,” In Proc. Berkeley Symposium on Mathematical Statistics and Probability, Berkeley: University of California Press, vol. 1, pp. 281-297, 1966.
[65]R. Maree, P. Geurts, J. Piater, and L. Wehenkel, “Decision trees and random subwindows for object recognition,” In Proc. International Conference on Machine Learning, pp. 13-18, 2005.
[66]R. Maree, P. Geurts, J. Piater, and L. Wehenkel, “Random subwindows for robust image classification,” In. Proc. International Conference on Computer Vision, pp. 34-40, 2005.
[67]K. Mikolajczyk and C. Schmid, “A performance evaluation of local descriptors,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1615-1630, 2005.
[68]K. Mikolajczyk and C. Schmid, “Indexing based on scale invariant interest points,” In Proc. International Conference on Computer Vision, pp. 525-531, 2001.
[69]K. Mikolajczyk and C. Schmid, “An affine invariant interest point detector,” In Proc. European Conference on Computer Vision, pp. 128-142, 2002.
[70]G. Mori, S. Belongie, and J. Malik, “Shape contexts enable efficient retrieval of similar shapes,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 723-730, 2005.
[71]S.A. Nene, S.K. Nayar, and H. Murase, “Columbia object image library (COIL-100),” Technical Report CUCS-006-96, February 1996.
[72]C.L. Novak and S.A. Shafer, "Anatomy of a color histogram," In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 599-605, 1992.
[73]S. Obdržálek, “Object recognition using local affine frames,” Ph.D. Thesis, Czech Technical University, Czech Republic, 2006.
[74]S. Obdržálek and J. Matas, “Object recognition using local affine frames on distinguished regions,” In Proc. of the British Machine Vision Conference, pp. 113-122, 2002.
[75]S. Obdržálek and J. Matas, “Object recognition using local affine frames on maximally stable extremal regions,” In J. Ponce, M. Hebert, C. Schmid, and A. Zisserman, editors, Toward Category-Level Object Recognition, Lecture Notes in Computer Science, vol. 4522, pp. 83-104, 2006.
[76]A. Opelt, A. Pinz, M. Fussenegger, and P. Auer, “Generic object recognition with boosting,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 28, no. 3, pp. 416-431, 2006.
[77]A. Opelt, A. Pinz, and A. Zisserman, “A boundary-fragment-model for object detection,” In Proc. European Conference on Computer Vision, vol. 2, pp. 575-588, 2006.
[78]A. Opelt, A. Pinz, and A. Zisserman, “Fusing shape and appearance information for object category detection,” In Proc. British Machine Vision Conference, pp. 117-127, 2006.
[79]A. Opelt, A. Pinz, and A. Zisserman, “Incremental learning of object detectors using a visual shape alphabet,” In Proc. International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 3-10, 2006.
[80]M.P. Kumar, P.H.S. Torr, and A. Zisserman, “An object category specific MRF for segmentation,” Lecture Notes in Computer Science, vol. 4170, pp. 596-616, 2006.
[81]J.R. Quinlan, C4.5: Programs for Machine Learning, San Francisco: Morgan Kaufmann Publishers Inc., 1993.

[82]J.R. Quinlan, “Improved use of continuous attributes in C4.5,” Journal of Artificial Intelligence Research, vol. 4, pp. 77-90, 1996.

[83]H. Shao, T. Svoboda, and L. Van Gool, “ZuBuD - Zurich buildings database for image based recognition,” Technical Report 260, Computer Vision Laboratory, Swiss Federal Institute of Technology, 2003. http://www.vision.ee.ethz.ch/showroom/zubud.
[84]H. Shao, T. Svoboda, T. Tuytelaars, and L. Van Gool, “HPAT indexing for fast object/scene recognition based on local appearance,” In Proc. International Conference on Image and Video Retrieval, pp. 71-80, 2003.
[85]P. Shih and C. Liu, “Face detection using discriminating feature analysis and support vector machine,” Pattern Recognition, vol. 39, no. 11, pp. 260-276, 2006.
[86]I. Shimshoni and A. Sasporta, “Object recognition using point uncertainty regions as pose uncertainty regions,” Image and Vision Computing, vol. 24, pp. 192-201, 2006.
[87]J. Shotton, A. Blake, and R. Cipolla, “Contour-based learning for object detection,” In Proc. International Conference on Computer Vision, pp. 503-510, 2005.
[88]A.R. Smith, “Color gamut transform pairs,” Computer Graphics, vol. 12, no. 3, pp. 12-19, 1978.
[89]M.J. Swain and D.H. Ballard, “Indexing via color histograms,” In Proc. International Conference on Computer Science, pp. 390-393, 1990.
[90]M.J. Swain and D.H. Ballard, “Color indexing,” International Journal on Computer Vision, vol. 7, pp. 11-32, 1991.
[91]H. Tamura, S. Mori, and T. Yamawaki, “Textural features corresponding to visual perception,” IEEE Trans. on Systems, Man, and Cybernetics, vol. 8, no. 6, pp. 460-472, 1978.
[92]C.E. Thomaz, R.Q. Feitosa, and A. Veiga, “Design of radial basis function network as classifier in face recognition using eigenfaces,” In Proc. Brazilian Symposium on Neural Network, pp. 118-123, 1998.
[93]M. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, pp. 71-86, 1991.
[94]M. Turk and A. Pentland, “Face recognition using Eigenfaces,” in Proc. International Conference on Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[95]V. Vapnik, The Nature of Statistical Learning Theory, New York: Springer Verlag, 1995.
[96]N. Vasconcelos, P. Ho, and P.J. Moreno, “The Kullback-Leibler kernel as a framework for discriminant and localized representations for visual recognition,” In Proc. European Conference on Computer Vision, pp. 430-441, 2004.
[97]P. Viola, M.J. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance,” In Proc. International Conference on Computer Vision, vol. 1, pp. 734-741, 2003.
[98]P. Viola, M.J. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance,” In Proc. International Journal of Computer Vision, vol. 63, pp. 153-161, 2005.
[99]M. Weber, M. Welling, and P. Perona, “Unsupervised learning of models for recognition,” In Proc. European Conference on Computer Vision, pp. 18-32, 2000.
[100]M.Weber, M. Welling, and P. Perona, “Towards automatic discovery of object categories,” In Proc. International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2101-2109, 2000.
[101]R. Xiao, M.J. Li, and H.J. Zhang, “Robust multi-pose face detection in images,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 31-41, 2004.
[102]M. H. Yang, D. Roth, and N. Ahuja, “Learning to recognize 3D objects with SNoW,” In Proc. European Conference on Computer Vision, pp. 439-454, 2000.

[103]H. Zhang, A. Berg, M. Maire, and J. Malik, “SVM-KNN: discriminative nearest neighbor classification for visual category recognition,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 2126-2136, 2006.
[104]L. Zhao and L.S. Davis, “Closely coupled object detection and segmentation,” In Proc. International Conference on Computer Vision, pp. 454-461, 2005.
[105]Q. Zhu, M. Yeh, K. Cheng, and S. Avidan, “Fast human detection using a cascade of histograms of oriented gradients,” In Proc. International Conference on Computer Vision and Pattern Recognition, pp. 1491-1498, 2006.
[106]http://www.honda-taiwan.com.tw/tech/asimo/ASIMO01.html
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top