跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/07/30 01:24
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:楊子緯
研究生(外文):Tzu-Wei Yang
論文名稱:使用輪廓特質應用在3D圖片搜尋之研究
論文名稱(外文):Using Shape Context for 3D Image Retrieval
指導教授:賴源泰
指導教授(外文):Yen-Tai Lai
學位類別:碩士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2008
畢業學年度:96
語文別:英文
論文頁數:44
中文關鍵詞:3D影像擷取輪廓特質
外文關鍵詞:shape context3D image retrieval
相關次數:
  • 被引用被引用:0
  • 點閱點閱:171
  • 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
本篇論文使用一種記錄輪廓特質的方法,來當圖形的形狀描述子。這個方法是將輪廓用 n 個不連續的點表示,對於每一個參考點,記錄剩下n – 1個點和參考點的相對位置。可以由研究發現,當輪廓被旋轉時,這樣的記錄結果也會被旋轉,因此,如果這些結果彼此有旋轉關係的話,就把他群聚在一起,並且用一個來符號表示。所以,本來輪廓是由 n 個點來表示的,現在變成用n個符號來表示。對於每個輪廓,統計這些符號出現的次數後再與資料庫中的圖片做比對,就可以快速地找到輪廓相似,或是輪廓經由旋轉過後相似的圖。
本篇論文把這種輪廓比對的技巧,套用在3D影像擷取系統中,這個系統是將3D圖片轉換成2D圖片,以各種不同角度的2D圖片來呈現3D圖片的場景,是一個符合人類思考模式的系統。如此一來,對於3D影像擷取的結果將會有很高的準確性。
In this work we use shape context as our shape descriptor. The representation for a shape is a discrete set of n points. For each of these points, the shape context is a histogram of the relative positions of the remaining points. When a shape is rotated, the shape context is rotated too. We group the rotated shape contexts together and then label each group by an integer. Therefore, a shape is represented by a set of label. Using the histogram of label frequencies can quickly and efficiently search for similar or rotational shapes.
We use this shape retrieval method to integrate with an 3D existent retrieval system. This system transforms the 3D pictures to the 2D pictures, using each kind of different angle's 2D pictures to present scenes of 3D pictures. The system will learn the user’s semantic subjectivity. Hence, well accuracy is demonstrated in the results of image retrieval.
摘要
ABSTRACT
CONTENTS
LIST OF FIGURES

Chapter 1 Introduction 1
1.1 Image Retrieval System 1
1.2 Feature Descriptor 4
1.3 Organization of the Thesis 5

Chapter 2 Region-Based Image Retrieval Using Shape Context 6
2.1 Region-Based Image Retrieval System Overview 6
2.1.1 Image Segmentation 7
2.1.2 Feature extraction 7
2.1.3 Feature Matching 8
2.2 Shape Context 8
2.3 Rotation Invariance 11
2.3.1 Properties of Rotational Shape Context 12
2.3.2 Similarity Measure 13
2.4 Modified K-Means Cluster 14

Chapter 3 Reflection Invariance 22
3.2 Viewpoints 23
3.3 Rotation Invariance 28
3.4 New 3D Image Retrieval System 30

Chapter 4 Experimental Results 31

Chapter 5 Conclusions 39

REFERENCES 40
[1]A. Ghosh and N. Petkov, “Robuatness of Shape Descriptors to Incomplete Contour Representations,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 27, pp. 1793-1804, 2005.

[2]A. Thayananthan, B. Stenger, “Shape Context and Chamfer Matching in Cluttered Scenes,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 127-133, 2003.

[3]B. Leibe and B. Schiele, “Analyzing Appearance and Contour Based Methods for Object Categorization,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 409 – 415, 2003.

[4]C. Faloutsos, R. Barber, M. Flickner, J. Hafner, W. Niblack, D. Petkovic and W. Equitz, “Efficient and Effective Querying by Image Content,” Journal of Intelligent Systems, pp. 231-262, 1994.

[5]C. T. Hsu, “Research of Multimedia Processing Laboratory,” (http://mp.cs.nthu.edu.tw/research.htm)

[6]D. Liu and T. Chen, “Soft Shape Context for Iterative Closest Point Registration,” International Conf. Image Processing, vol. 2, pp. 24-27, 2004.

[7]F. Jing, M. Li, H. J. Zhang, and B. Zhang, “Relevance Feedback in Region-Based Image Retrieval,” IEEE Trans. Circuits and Systems for Video Technology, vol. 14, pp. 672 – 681, 2004.

[8]F. Jing, M. Li, H. J. Zhang, and B. Zhang, “An Efficient and Effective Region-Based Image Retrieval Framework,” IEEE Trans. Image Processing, vol. 13, pp. 699 – 709, 2004.

[9]F. Mokhtarian and A. K. Mackworth, “A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, pp. 789-805, 1992.

[10]F. Jing, M. Li, H. J. Zhang, and B. Zhang, “Unsupervised Image Segmentation Using Local Homogeneity Analysis,” Proc. IEEE Int. Symp. Circuits and Systems, vol. 2, pp. 456 – 459, 2003.

[11]F. Mokhtarian and R. Suomela, “Robust Image Corner Detection Through Curvature Scale Space,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 20, pp. 1376-1381, 1998.

[12]G. Mori, S. Belongie and J. Malik, “Shape Contexts Enable Efficient Retrieval of Similar Shapes,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 723-730, 2001.

[13]G. Mori, S. Belongie and J. Malik, “Efficient Shape Matching Using Shape Contexts,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 27, pp. 1832-1837, 2005.

[14]G. Carneiro and A. D. Jepson, “Pruning Local Feature Correspondences Using Shape Context,” Proc. Int. Conf. Pattern Recognition, vol. 3, pp. 16-19, 2004.

[15]H. Zhang and J. Malik, “Learning A Discriminative Classifier Using Shape Context Distances,” Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 242-247, 2003.

[16]J. Huang, S. R. Kumar, M. Mitra, W.-J. Zhu, and R. Zabih, “Image Indexing Using Color Correlograms,”Proc. IEEE Comp. Soc. Conf. Computer Vision and Pattern Recognition, pp. 762-768, 1997.

[17]J. Z. Wang, J. Li, and G. Wiederhold, ”SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, pp. 947 – 963, 2001.

[18]J. Li, J. Z. Wang, and G. Wiederhold, “IRM: Integrated Region Matching for Image Retrieval,” Proc. of the 8th ACM Int. Conf. on Multimedia, pp. 147 – 156, 2000.

[19]K. Vu, K. A. Hua, and W. Tavanapong, “Image Retrieval Based on Regions of Interest,” IEEE Trans. Knowledge and Data Engineering, vol. 15, pp. 1045 – 1049, 2003.

[20]M. Stricker and M. Orengo, “Similarity of Color Images,” Proc. SPIE Storage and Retrieval for Image and Video Databases III, vol. 2420, pp. 381 – 392, 1995..

[21]M. Yusuf and T. Haider, “Recognition of Handwritten Urdu Digits Using Shape Context,” Proc. Int. Multitopic Conference, pp. 569-572, 2004.

[22]R. Baeza-Yates and B. Ribeiro-Neto, Modern Information Retrieval. Reading, MA: Addison-Wesley, 1999

[23]S. Belongie and J. Malik, “Matching with Shape Contexts,” IEEE proc. Content-Based Access of Image and Video Libraries, pp. 20-26, 2000.

[24]S. Belongie, J. Malik and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts,” IEEE trans. Pattern Analysis and Machine Intelligence, vol. 24, pp. 509-522, 2002.

[25]“The Math Works,” (http://www.mathworks.com/)

[26]W. C. Yen, “Image Retrieval by Using Shape Context,” Department of E.E. NCKU, Tainan, Taiwan, R.O.C., 2006.

[27]X. J. Qiu, Z. Q. Wang, S. H. Xia and J. T. Li, “Estimating Articulated Himan Pose from Video Using Shape Context,” Proc. IEEE Int. Symp. Signal Processing and Information Technology, pp. 583-588, 2005.

[28]Y. Deng, B. S. Manjunath, C. Kenney, M.S. Moore and H. Shin, “An Efficient Color Representation for Image Retrieval,” IEEE Trans. Image Processing, vol. 10, pp. 140-147, 2001.

[29]Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen and Ming Ouhyoung, “Shape Distributions,” Computer Graphics Forum (EUROGRAPHICS'03), Vol. 22, No. 3, pp. 223-232, Sept. 2003.

[30]Johan W.H. Tangelder, Remco C. Veltkamp, “A survey of content based 3D shape retrieval methods,” Shape Modeling Applications, Proceedings 2004 pp. 145-156, 2004.

[31]Yi Liu, Jiantao Pu, Guyu Xin, Hongbin Zha, Weibin Liu, Yusuke Uehara, “A Robust Method for Shape-based 3D Model Retrieval,” Computer Graphics and Applications, 2004. PG 2004. Proceedings. 12th Pacific Conference on 6-8 Oct. 2004, pp. 3-9.

[32]Dong Xu, Hua Li, Zongkai Lin, “Content-based 3-D Shape Retrieval for Pervasive Computing,” Pervasive Computing and Applications, 2006 1st International Symposium on 3-5 Aug. 2006, pp. 206-211.

[33]3DCAFE, http://www.3dcafe.com.

[34]Chia-Hui Lin, “Region-Based Image Retrieval Using Shape Context,” Department of E.E. NCKU, Tainan, Taiwan, R.O.C., 2007.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top