這篇論文提出以影像的區域對應為基礎之影像擷取以及相關回饋。一開始我們利用mean-shift方法做區域分割，對於每個區域我們去計算特徵值，包括了顏色(color)，材質(texture)，以及空間分佈，為了有效的建立資料庫，我們把每一種特徵值的分佈表示成高斯混和模型。
為了找出區域對應，我們利用無向圖來表示影像：每個節點表示影像中的區域，每個邊表示區域的相鄰關係。利用無向圖表示法，我們把區域對應問題轉換成一個無向圖對應問題。為了去更準確的找到區域的對應關係，我們希望在找區域對應時同時考慮到區域的相似度以及其與周遭區域的相鄰關係。因此我們修改一個配對無向圖的演算法來解決我們的區域對應問題。

緊接著我們利用maximum likelihood架構來表示相關回饋。藉著使用者從搜尋的結果回饋出相關的影像，我們從這些回饋影像中去尋找使用著的理想搜尋影像，可以達到這相使用者所回饋的影像的最大可能性，接著再利用理想搜尋影像重複做搜尋。

實驗顯示我們方法在不同種類的影像中都有很好的結果。

This thesis presents a region-based image retrieval approach with relevance feedback by taking the region correspondence into consideration. Region representation in image retrieval has been popular issues in the recent works because global features are insufficient to describe the local variations within images. Region correspondence estimation is one of the critical problems in region-based image similarity comparison. Intuitively, we can estimate the region correspondence by minimizing the matching error of matched regions. Since human perception matches images depending not only on their local attributes but also on their interrelationships, we must take the relationships of region connectivity into consideration when estimating the region correspondence.
To estimate the region correspondence by considering the region attributes and the relationships of region connectivity, we represent images by graphs in which the nodes represent the regions and the edges represent the relationships of region connectivity. We then solve the region correspondence estimation problem via graph matching technique. However, the graph matching technique, which matches non-attributed graphs, does not completely solve our region correspondence problem. Thus, we modify the graph matching algorithm to satisfy our requirements.

To further improve the retrieval results, we formulate the relevance feedback process as a maximum likelihood framework. We show that the maximization of the likelihood function has a closed form solution. The ideal query image, the region weights, and the feature weights are updated by the feedback images and their region correspondences.

In experimental results, a series of experiments show that the proposed approach achieves good performance for various natural images with complex contents.

[1] J. R. Smith, C. S. Li, "Image Classification and Querying Using Composite Region Templates," Journal of Computer Vision and Image Understanding, 2000.
[2] C. Carson, S. Belongie, H. Greenspan, and J. Malik “Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, No.8, pp.1026 -1037, August 2002.
[3] H. Lee and Y. Ho “A Region-Based Image Retrieval System Using Salient Point Extraction and Image Segmentation,” IEEE Pacific Rim Conference on Multimedia 2002, pp. 209-216.
[4] C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Region-Based Image Querying,” Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries, pp. 42-49, June 1997.
[5] G. Pass, R. Zabih, J. Miller, “Comparing Images using Color Coherence Vectors,” Proc. Fourth ACM International Conference on Multimedia, p.65-73, November 18-22, 1996.
[6] G. Pass, R. Zabih, “Histogram Refinement for Content-Based Image Retrieval,” Third IEEE Workshop on Applications of Computer Vision, December, 1996.
[7] C. Schmid and R. Mohr, “Local Grayvalue Invariants for Image Retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 19, No. 5, May 1997.
[8] S. Bhattacharjee, “Image Retrieval Based on Structural Content,” Workshop on Image Analysis for Multimedia Interactive Service, 1999.
[9] J. Li, J. Z. Wang, and G. Wiederhold, “IRM: Integrated Region Matching for Image Retrieval,” Proc. Eighth ACM International Conference on Multimedia 2000, pp. 147-156.
[10] H. Greenspan, G. Dvir, and Y. Rubner, “Region Correspondence for Image Matching via EMD Flow,” CVPR 2000 Workshop on Content-Based Access of Image and Video Libraries, pp. 27-31, 2000.
[11] H. Greenspan, S. Gordon and J. Goldberger, “Probabilistic Models for Generating, Modeling and Matching Image Categories," International Conference on Pattern Recognition 2002.
[12] N. Vasconcelis and A. Kippman, “A Probabilistic Architecture for Content-Based Image Retrieval,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, June 2000.
[13] B. Luo and E. R. Hancock, “Structural Graph Matching Using the EM Algorithm and Singular Value Decomposition,” IEEE Trans. Pattern Analysis And Machine Intelligence, Vol. 23, No. 10, October 2001.
[14] H. Greenspan, J. Goldberger and Lenny Ridel, “A Continuous Probabilistic Framework for Image Matching," Journal of Computer Vision and Image Understanding, 1-23, Dec. 2001.
[15] D. Comaniciu and P. Meer, “Mean shift: A robust approach toward feature space analysis,” IEEE Trans. Pattern Anal. Machine Intell., Vol. 23, No. 5, pp. 603-619, 2002.
[16] E. Bengoetxea, “Inexact Graph Matching Using Estimation of Distribution Algorithms,” Submitted to the Ecole Nationale Supérieure des Télécommunications, for the Degree of Doctor of Philosophy, Département Traitement du Signal et des Images.
[17] Y. Chen and J. Z. Wang, “A Region-Based Fuzzy Feature Matching Approach to Content-Based Image Retrieval,” IEEE Trans. Pattern Anal. Machine Intell., Vol. 24, No. 9, September 2002.
[18] A. Mojsilovic, J. Hu, and E. Soljanin, “Extraction of Perceptually Important Colors and Similarity Measurement for Image Matching, Retrieval, and Analysis,” IEEE Trans. Image Processing, Vol. 11, No. 11, pp. 1238-1248, November 2002.
[19] A. Hlaoui and S. Wang, “A New Algorithm for Graph Matching with Application to Content-based Image Retrieval,” International Conference on Pattern Recognition, 2002.
[20] M. L. Kherfi, D. Ziou, and A. Bernardi, “Learning from Negative Example in Relevance Feedback for Content-Based Image Retrieval,” Pattern Recognition, 2002.
[21] Y. Rui and T.S. Huang, "Optimizing Learning in Image Retrieval," Proc. CVPR, June 2000.
[22] I. J. Cox, M. L. Miller, T. P. Minka, T. V. Papathomas, and P. N. Yianilos, "The Bayesian Image Retrieval System, PicHunter: Theory, Implementation, and Psychophysical Experiments," IEEE Trans. Image Processing, vol. 9, no 1, pp. 20-37, January 2000.
[23] I. J. Cox, M. L. Miller, T.P. Minka, and P. N. Yianilos, “An Optimized Interaction Strategy for Bayesian Relevance Feedback,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1998.
[24] Y. Isikawa, R. Subramanya, and C. Faloutsos, "MindReader: Querying database through multiple examples," Proc. VLDB, 1998.
[25] G. L. Scott and H.C. Longuet-Higgins, “An Algorithm for Associating the Features of 2 Images,” Proc. Royal Soc. London Series B, vol. 244, no. 1309, pp. 21-26, 1991.
[26] L.G. Shapiro and G.C. Stockman, Computer vision, Prentice Hall, 2001.