以內容為基礎的影像檢索系統依照人眼的觀感符合之影像特徵來對影像資料庫進行檢索。本篇論文提出一個結合顏色和形狀資訊並結合多詢例來檢索影像的方法。鑒於使用者在每次的檢索所著重的特徵不盡相同，系統根據使用者所選取的檢索影像集合，自動判斷每種特徵在本次檢索的重要性，藉以調整最終的檢索結果。
在檢索的過程中，首先先分別計算各個查詢影像之間色彩和形狀特徵向量係數的相關程度，藉以給予不同的權重值，再分別以色彩和形狀特徵對查詢影像和資料庫影像之間的相似性程度作計算，並產生各自的檢索排名，最後利用加權總合結合兩種特徵排序以統整出最後的檢索結果。由實驗證實本研究方法確實可行。

In the design of content-based image retrieval (CBIR) system, it should extract features that reflect human perceptions and then performs retrieval based on user feedback information. A preprocessing is needed to perform foreground object segmentation such that the extracted features are not biased by image backgrounds. In this research, we have designed an image retrieval system that provides multiple instance query with reference to heterogeneous features. Both preprocessing and retrieval are fully automatic. Color and shape features are extracted from the segmented foreground for retrieval. The retrieval system first computes the color and shape feature correlations, respectively, among query images and assign different weightings. It then evaluates similarities between each query image and images in database to provide ranks for each image in database. The final ranks are generated by combining the feature weights and the individual ranks. Simulations show that the retrieval performance is largely improved as compared to retrieval by single feature or other method that provide queries with multiple features.

[1] Yong Rui, Thomas S. Huang and Shih-Fu Chang, “Image retrieval: past, present, and future,” International Symposium on Multimedia Information Processing, 1997.
[2] Yong Rui, Thomas S. Huang, Michael Ortega and Sharad Mehrotra. “Relevance feedback: a power tool in interactive content-based image retrieval,” IEEE Transactions on Circuits and Systems for Video Technology, 8(5): pp. 644-655, 1998.
[3] Yong Rui, Thomas S. Huang, and S. Mehrota, “Content-based image retrieval with relevance feedback in MARS,” Proc. of IEEE Workshop on Content-based Access of Image and Video Libraries, pp. 815-818, 1997.
[4] S. Mehrotra et al, “Multimedia analysis and retrieval system,” in The 3rd Int. Workshop on Information Retrieval Systems, 1997.
[5] G. Salton and M. J. McGill, Introduction to Morden Information Retrieval. McGill-Hill Book Company, 1983.
[6] L.Cieplinski et al, “MPEG-7 Visual part of eXperimentation Model Version 11.1,” ISO/IECJTC1/SC29/WG11 MPEG01/M7691, 2001.
[7] Cheng-Yi Liu, Jiann-Jone Chen and Feng-Cheng Chang “A dynamically adapted retrieval algorithm for multi-instances image query with heterogeneous features,” IEEE Consumer Communication and Networking Conference, 2004.
[8] Jiann-Jone Chen and C.-Y. Liu, “A universal query mechanism for similarity retrieval based on shape information in image database,” Proc. IEEE Int. Conf. Acoustic Speeches & Signal Processing, vol.3, pp. 3676-3679, May 2002.
[9] Shi-Kuo Chang, “Principles of pictorial information systems design,” Prentice-Hall, pp. 61-81, 1989.
[10] M. Stricker and M. Orengo. “Similarity of color images,” In Storage and Retrieval for Image and Video Databases III, SPIE 2420, pages 381-392, San Jose, CA, February 1995.
[11] Zhu, M. “Recall, precision and average precision,” Working Paper 2004-09, Department of Statistics and Actuarial Science, University of Waterloo, 2004.
[12] Abby A. Goodrum, “Image information retrieval: an overview of current research,” Information Science, vol. 3, no.2, 2000.
[13] John M. Zachary, Jr.,“An information theoretic approach to content based image retrieval,” B.S., Louisiana State University, Department of Computer Science Dissertation, September 2000.
[14] Michael Swan and Dana Ballard, “Color indexing,” International Journal of Computer Vision, 7(1), 1991.
[15] James Z. Wang and Yanping Du, “RF*IPF: a weighting scheme for multimedia information retrieval,” Proc. IEEE International Conference on Image Analysis and Processing (ICIAP), pp. 380-385, 2001.
[16] Wayne Niblack et al, “The QBIC project: querying images by content using color, texture, and shape,” In Proc. SPIE Electronic Imaging: Science 8 Technology, San Jose, CA, SPIE, February 1993.
[17] Yong Rui, Thomas S. Huang, Shih-Fu Chang, “Image retrieval: current techniques, promising directions, and open issues” Journal of visual communication and image representation, vol.10, pp.39-62, 1999.
[18] Chad Carson, Serge Belongie, Hayit Greenspan, and Jitendra Malik “Blobworld: image segmentation using expectation-maximization and its application to image querying,” IEEE Trans. PAMI, vol. 24, no. 8, August 2002.
[19] J. R. Smith, S. F. Chang, “An image and video search engine for the World-Wide Web,” Storage and Retrieval for Image and Video Database V (Sethi, I K and Jain, R C, eds), Proc SPIE 3022, pp. 84-95, 1997.
[20] J. R. Smith. “Integrated spatial and feature image systems: retrieval, compression and analysis,” PhD thesis, Graduate School of Arts and Sciences, Columbia University, February 1997.
[21] T. Gevers and A. W. M. Smeulders, “Pictoseek: combining color and shape invariant features for image retrieval,” IEEE Trans. Image Processing, vol. 9, no. 1, pp. 102-119, January 2000.
[22] A. Pentland, R. W. Picard, and S. Sclaroff, “Photobook: content-based manipulation of image databases,” International Journal of Computer Vision, vol. 18, no. 3, pp. 233-254, 1996.
[23] A. Gupta, “Visual information retrieval: a virage perspective,” Technical Report, Virage, Inc., 1995.
[24] Rafael C. Gonzalez, Richard E. Woods, “Digital image processing,” New York : Addision-Wesley, 1992.
[25] Vincenzo Di Lecce, Andrea Guerriero, “An evaluation of the effectiveness of image feature for image retrieval,” Journal of visral communication and image representation, vol. 10, 1999.