臺灣博碩士論文加值系統

隨著電腦上的多媒體應用發展快速，以及網際網路的普及化，讓多媒體資訊之使用日漸廣泛，舉凡視訊、音訊、影像等，提供使用者在網路上做存取。因此有許多以資訊本身內容為搜尋依據的搜尋系統可幫助使用者能夠更正確的找到真正需要的資料。然而，對於現今日趨複雜的多媒體資訊而言，僅使用單一特徵的方法是無法對各式各樣的多媒體資訊都有極佳的相似模型序列，因此希望能利用組合多種不同性質特徵的方法以達到更好的相似模型序列。
在本論文中，提出一個整合三維模型特徵之演算法，首先提出自動選擇相關及不相關模型的方法(Automatic Relevant/Irrelevant Models Selection，ARMS)，其中我們利用交互查詢方法，進一步改善選擇出的相關及不相關模型。系統根據所選出的相關及不相關模型決定每一個特徵向量的權重值，利用加權後的特徵，計算各特徵加權總合的距離來做搜尋。同時系統也利用改良式查詢特徵調整(Adaptive Query Point Movement，AQPM)，把查詢模型的特徵向量往相關模型移動，遠離不相關模型。
在傳統檢索系統中必須由使用者輸入回饋次數，本論文提出一個自動停止檢索方法，不需人為輸入回饋次數即可達到最佳檢索效果。我們使用三個三維模型資料庫，來測試本論文中所提出的方法。實驗結果顯示我們提出的整合三維模型特徵之演算法可提高檢索的效能。

With the development of the Internet, a large amount of digital multimedia data, can be accessed through the Internet. The primary challenge to a content-based multimedia retrieval system is to extract a set of proper features for effectively discriminating distinct types of multimedia data. Prior researches in multimedia retrieval have shown that no feature alone can provide satisfactory retrieval performance. Therefore, it is expected that the retrieval accuracy can be improved if information fusion schemes were employed to integrate the information provided by different features.
In this thesis, 3D model features fusion algorithm (FFA) will be proposed to improve the retrieval accuracy. First, base on the proposed double query algorithm, the automatic relevant/irrelevant models selection (ARMS) approach is used to automatically select the relevant and irrelevant models in a 3D model retrieval system without any user interaction. A weighted distance measure, in which the weight associated with each individual descriptor is learnt automatically according to the selected relevant and irrelevant models, is used to measure the distance between two 3D models. Furthermore, a descriptor-dependent adaptive query point movement approach is employed to update every feature vector. This set of new feature vectors will be used to index 3D models in the next search process. Finally, a new approach is proposed to automatically stop retrieval process. Experimental results show the proposed methods produce good performances.

摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vi
表目錄 vii
壹、 簡介 1
1.1 查詢特徵調整方法 4
1.2 相關/不相關模型選擇 5
1.3 特徵合併方法 6
貳、 整合三維模型特徵之演算法(3D Model Features Fusion Algorithm，FFA) 7
2.1 以單一特徵產生獨立的相似模型序列 8
2.2 自動相關/不相關模型選擇(Automatic Relevant/Irrelevant Models Selection，ARMS) 8
2.2.1 單一特徵產生獨立的相似模型序列 8
2.2.2 交互查詢 11
2.2.3 整合模型相似分數與出現次數 13
2.3 加權特徵整合(Feature Re-weighting，FRW) 14
2.4 改良式查詢特徵調整(Adaptive Query Point Movement，AQPM) 15
2.5 整合FRW和AQPM 16
2.6 自動停止檢索 16
參、 實驗結果 19
3.1 第一個實驗資料庫，PSB資料庫 20
3.2 第二個實驗資料庫，ESB資料庫 23
3.3 第三個實驗資料庫，SHREC-W資料庫 24
3.4 自動停止檢索 26
肆、 結論 31
附錄 32
1) 完整檢索數據 32
參考文獻 39

[1] T. W. Chiang, T. W. Tsai and M. J. Hsiao, “Improving content-based image retrieval with query-candidate relationship,” in IEEE Region Conference, pp. 1-4, Oct, 2007.
[2] P. Shilane, P. Min, M. Kazhdan, and T. Funkhouser, “The Princeton shape benchmark,” in Proc. Shape Modeling Application., 2004, pp. 167-178.
[3] S. Jayanti, K. Kalyanaraman, N. Iyer, and K. Ramani, “Developing an Engineering Shape Benchmark for CAD Models,” Computer-Aided Design, Vol. 38, No. 9, pp. 939-953, Sept. 2006.
[4] R. C. Veltkamp and F.B. ter Haar, eds., “SHREC 2007: 3D Shape Retrieval Contest,” Technical Report UUCS-2007-015, pp. 5-10, June 2007.
[5] Y. Gao, M. Wang, “Less is More: Efficient 3-D Object Retrieval With Query View Selection,” IEEE Transactions on Multimedia, Vol. 13, No. 5,pp. 1007-1018, Oct. 2011.
[6] Y. Wang, M. Ding, C. Zhou and Y. Hu, “Interactive relevance feedback mechanism for image retrieval using rough set,” Computer Vision and Image Understanding, Vol. 88, Issue 2, pp. 55-75, Nov. 2002.
[7] K. Porkaew and K. Chakrabarti, “Query refinement for multimedia similarity retrieval in MARS,” In Proceedings of the 7th ACM Multimedia Conference, Orlando, Florida, pp. 235–238, 1999.
[8] Y. Rui, T. Huang, and S. Mehrotra, “Content-based image retrieval with relevance feedback in MARS,” In Proceedings of IEEE International Conference on Image Processing ’97. Santa Barbara, CA, Oct. 1997.
[9] J.J. Rocchio Jr., “Relevance feedback in information retrieval, in: G. Salton (Ed.),” The SMART System, Prentice Hall Inc., Englewood Cliffs, NJ, pp. 313–323, 1971.
[10] Y. Gao, J. Tang, “Camera Constraint-Free View-Based 3-D Object Retrieval,” IEEE Transactions on Image Processing, Vol. 21, No. 4, pp. 2269-2281, Apr. 2012.
[11] M. M. Monwar and M. L. Gavrilova, “Multimodal biometric system using rank-level fusion approach,” IEEE Trans. Syst. Man Cybern. B Cybern., Vol. 39, No 4, pp. 867-78, Mar. 2009.
[12] P. C. Cheng, B. C. Chien, H. R. Ke and W. P. Yang, “A two-level relevance feedback mechanism for image retrieval”, Expert Systems with Applications, Vol. 34, Issue 3, pp. 2193-2200, Apr. 2008.
[13] H. J. Escalante, C. Hernandez, E. Sucar and M. Montes, “Late fusion of heterogeneous methods for multimedia image retrieval,” in Proc. 1st ACM Int’l Conf. Multimedia information retrieval, Vancouver, Canada, pp. 172–179, 2008.
[14] P. C. Cheng, B. C. Chien, H. R. Ke and W. P. Yang, “A two-level relevance feedback mechanism for image retrieval,” Expert Systems with Applications, Vol. 34, Issue 3, pp. 2193-2200, Apr. 2008.
[15] G. Das and S. Ray, “A comparison of relevance feedback strategies in CBIR,” 6th IEEE/ACIS International Conference on Computer and Information Science, pp. 100 – 105, Jul. 2007.
[16] P. Y. Yin and S. H. Li, “Content-based image retrieval using association rule mining with soft relevance feedback,” Journal of Visual Communication and Image Representation, Vol. 17, Issue 5, pp. 1108-1125, Oct. 2006.
[17] G. Giacinto and F. Roli, “Instance-based relevance feedback for image retrieval”, In Advances in Neural Processing Systems, Vol. 17, Cambridge, MA, pp. 489–496, 2005.
[18] R. Ohbuchi, Y. Hata, “Combining Multiresolution Shape Descriptors for 3D Model Retrieval,” in Proc WSCG 2006, 2006.
[19] R. Nuray and F. Can, “Automatic ranking of information retrieval systems using data fusion,” Information Processing and Management, Vol. 42, No. 3, pp. 595-614, May 2006.
[20] M. Jovic, Y. Hatakeyama, F. Dong and K. Hirota, “Image Retrieval Based on Similarity Score Fusion from Feature Similarity Ranking Lists,” Proc. 3rd Int’l Conf. Fuzzy Systems and Knowledge Discovery, pp. 461-470, 2006
[21] G. Das and S. Ray, Feature re-weighting in content-based image retrieval. In Proceedings of International Conference on Image and Video Retrieval, Arizona State University Tempe AZ, pp. 387–391,Jul. 13-15 2006.
[22] Y. Wu and A. Zhang. “A feature re-weighting approach for relevance feedback in image retrieval”, In IEEE International Conference on Image Processing (ICIP’02), Rochester, New York, pp. 581–584, Sep. 2002.
[23] Khotanzad andY.H.Hong, “Invariant image recognition by Zernike moments,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 12, No. 5, pp. 489–497, May 1990.
[24] R. Yan, A. Hauptmann, and R. Jin. “Multimedia search with pseudo-relevance feedback,” In CIVR, pp. 649-654, 2003.
[25] J. L. Shih, C. H. Lee and C. H. Chuang, “A 3D Model Retrieval Approach Based on the Combination of PCA Plane Projections,” Journal of Information Technology and Applications, Vol. 5, No. 2, pp. 46-102, 2011.
[26] J. Ricard, D. Coeurjolly and A. Baskurt, “ART extension for description, indexing and retrieval of 3D objects,” in Proc. of 17th Int. Conf. Pattern Recognition, Vol. 3, pp. 79-82, 2004.
[27] J. L. Shih and H. Y. Chen, “A 3D model retrieval approach using the interior and exterior 3D shape information,” Multimedia Tools Applicat., Vol. 43, No. 1, pp. 45-62, May 2009.
[28] J. L. Shih, C. H. Lee, and J. T. Wang, “3D object retrieval system based on grid D2,” Electron. Lett., Vol. 41, No. 4, pp. 23-24, Feb. 2005.
[29] M. Reisert and H. Burkhardt “Second order 3D shape features: an exhaustive study,” Comput. &; Graph., Vol. 30, No. 2, pp. 197-206, Apr. 2006.
[30] J. L. Shih and W. C.Wang, “A 3D model retrieval approach based on the principal plane descriptor,” in Proc. 2nd Int. Conf. Innovative Computing, Inform. Control, 2007.
[31] B. K. P. Horn, “Extended Gaussian images,” in Proc.of IEEE, Vol. 72, No. 12, pp. 1671-1686, Dec. 1984.
[32] P. Papadakis, I. Pratikakis, S. Perantonis, T. Theoharis, “Efficient 3D shape matching and retrieval using a concrete radicalized spherical projection representation,” Pattern Recognition, Vol. 40, No. 9, pp. 2437-2452, Sep. 2007.
[33] D. V. Vranic, “3D model retrieval,” Ph.D. Dissertation, University of Leipzig, Department of Computer Science, 2004.
[34] C. B. Akgul, B. Sankur, Y. Yemez, and F. Schmitt, “3D model retrieval using probability density-based shape descriptors,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 31, No. 6, pp. 1117-1133, Jun. 2009.
[35] M. Kazhdan, T. Funkhouser, and S. Rusinkiewicz, “Rotation invariant spherical harmonic representation of 3D shape descriptors,” in Proc. of Eurographics/ACM SIGGRAPH symp. Geometry process., pp. 156-164, 2003.
[36] D. Y. Chen, X. P. Tian, Y. T. Shen, and M. Ouhyoung, “On visual similarity based 3D model retrieval,” Comput. Graph. Forum, Vol. 22, No. 3, pp. 223-232, Sep. 2003.
[37] H. Laga, H. Takahashi, and M. Nakajima, “Spherical wavelet descriptors for content-based 3D model retrieval,” in Proc. of IEEE Int. Conf. Shape Modeling and Applicat., 2006.
[38] C. T. Kuo and S. C. Cheng, “3D model retrieval using principal plane analysis and dynamic programming,” Pattern Recognition, Vol. 40, No. 2, pp. 742-755, Feb. 2007.
[39] M. Ankerst, G. Kastenmüller, H. P. Kriegel, and T. Seidl, “3D shape histograms for similarity search and classification in spatial databases,” Proc. 6th Int. Symp. Advances in Spatial Databases, pp. 207-226, 1999.
[40] T. Zaharia and F. J. Preteux, “Shape-based retrieval of 3D mesh models,” in Proc. of IEEE Int’l Conf. Multimedia and Expo, Vol. 1, pp. 437-440, 2002.
[41] E. Paquet and M. Rioux, “Nefertiti: A Query by Content Software for Three-Dimensional Models Databases Management,” in Proc. Int. Conf. Recent Advances in 3D Digital Imaging and Modeling, pp. 345-352, 1997.
[42] D. V. Vranic, “An Improvement of Rotation Invariant 3D Shape Descriptor Based on Functions on Concentric Spheres,” in Proc. of IEEE Int. Conf. Image Process., pp. 757-760, Sep. 2003.
[43] T. F. Ansary, M. Daoudi, and J.-P. Vandeborre, ”3D Model Retrieval Based on Adaptive Views Clustering,” LNCS 3687, pp. 473–483, 2005.
[44] R. M. Rustamov, ”Template Based Shape Descriptor,” in Proc. of Eurographics Workshop on 3D Object Retrieval, 2009.