影像檢索的目標為根據使用者的查詢條件，從一個影像資料集中尋找符合條件的影像，而本研究著重於發展一使用多重有興趣區域查詢的地標檢索系統。明確來說，使用者可以提供多個範例影像進行查詢，並且可選擇性地定義每張影像中其所感興趣之區域 (ROI)；因此，在我們的系統中，跟這些ROI最為相似的影像會被尋找出來。另一方面，雖然地標建築物通常很容易被人們所辨識出來，但是對於電腦來說，包含地標建築物的影像卻會由於拍攝時的天色變化、觀看角度、距離遠近…等因素而有很不同的呈現；為了解決在影像檢索時因此所造成的困難，我們採用不易受到影像改變影響的SIFT描述子。然而，一張影像會產生大量的SIFT描述子，而每一個SIFT描述子又是一個高維度的向量，因此採用SIFT描述子會使我們的方法具有很高的時間複雜度；為了改善我們系統的效率，我們提出透過使用合適的檢索結構及對應的技術來改善。實驗結果顯示，針對某些案例使用者能夠藉由系統檢索搜尋到想要的結果，此外我們提出的方法的確能夠改善影像檢索的效率。

The task of image retrieval is to extract matched images from a large image dataset according to the user query. In this work, we aim at developing a landmark image retrieval scheme which supports multi-ROI queries. Specifically, a user can provide more than one example images and then optionally define a region of interest (ROI) within each image to form his or her query. Consequently, images which are more similar to those ROIs can be returned in the proposed scheme. On the other hand, although landmarks are usually easily recognizable by human beings, images containing landmarks tend to with variant illumination, view angles, scaling and so on. To ease this difficulty, we adopt the SIFT descriptor due to its robust invariance to common image transforms. Nevertheless, the SIFT descriptor is with a high computation complexity since a mass of keypoints which are high dimensional vectors can usually be generated from a single image. To improve the efficiency of our retrieval scheme, we propose to properly utilize the indexing structure and corresponding techniques. Empirical studies show that our scheme can handle the image retrieval task both efficiently and effectively.

[1] A. E. Abdel-Hakim and A. A. Farag, "CSIFT: a SIFT Descriptor with Color Invariant Characteristics," Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:1978-1983, June 2006.
[2] ALIPR, http://alipr.com/.
[3] J. S. Beis and David G. Lowe, "Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1000-1006, June 1997.
[4] K.-Y. Cheng, "PhotoShoot: A Web-Game for User Assisted ROI Labeling," Master Thesis of the National Taiwan University Department of Information Management, June 2006.
[5] R. Datta, J. Li and J. Z. Wang, "Content-based Image Retrieval: Approaches and Trends of the New Age," Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval, pages 253-262, November 2005.
[6] T. Deselaers, D. Keysers and H. Ney, "Features for Image Retrieval: an Experimental Comparison," Information Retrieval, 11(2):77-107, April 2007.
[7] G. Dorkó and C. Schmid, "Object Class Recognition Using Discriminative Local Features," Technical Report RR-5497, February 2005.
[8] K. H. M. Eitz, T. Boubekeur and M. Alexa, "A Descriptor for Large Scale Image Retrieval based on Sketched Feature Lines," Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling, pages 29-36, August 2009.
[9] V. Ferrari, T. Tuytelaars and L. Gool, "Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views," International Journal on Computer Vision, 67:159-188, April 2006.
[10] Flickr, http://www.flickr.com/.
[11] J. J. Foo and R. Sinha, "Using Redundant Bit Vectors for Near-Duplicate Image Detection," Proceedings of the International Workshop on Scalable Web Information Integration and Service, 4443:472-484, April 2007.
[12] J. H. Friedman, J. L. Bentley and R. A. Finkel, "An Algorithm for Finding Best Matches in Logarithmic Expected Time," ACM Transactions on Mathematics Software, 3:209-226, September 1977.
[13] G. Fritz, C. Seifert, M. Kumar and L. Paletta, "Building Detection from Mobile Imagery Using Informative SIFT Descriptors," Proceedings of the 14th Scandinavian Conference on Image Analysis, 3540: 629-638, June 2005.
[14] K. Gao, S. Lin, Y.-d. Zhang, S. Tang and H. Ren, "Attention Model Based SIFT Keypoints Filtration for Image Retrieval," Proceedings of the Seventh IEEE/ACIS International Conference on Computer and Information Science, pages 191-196, May 2008.
[15] T. Goedeme, T. Tuytelaars and L. V. Gool, "Fast Wide Baseline Matching for Visual Navigation," Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:24-29, July 2004.
[16] M. Hughes, Gareth J. F. Jones and N. E. O’Connor, "Investigation of Image Models for Landmark Classification," in Proceedings of 4th International Workshop on Semantic Media Adaptation and Personalization, pages 50-55, December 2009.
[17] O. Huseyin, T. Chen and H.-R. Wu, "Performance Evaluation of Multiple Regions-of-interest Query for Accessing Image Databases," Proceedings of the 2001 International Symposium on Intelligent Multimedia, Video and Speech, pages 300-303, September 2001.
[18] C. Jaewoo and L. Ahreum, "Parallel High-dimensional Index Structure for Content-based Information Retrieval," Proceedings of the 8th IEEE International Conference on Computer and Information Technology, pages 101-106, July 2008.
[19] S. Junming, H. Dongjian and Y. Qinli, "Multi-semantic Scene Classification Based on Region of Interest," Proceedings of the 2008 International Conference on Computational Intelligence for Modelling Control & Automation, pages 732-737, December 2008.
[20] Y. Ke and R. Sukthankar, "PCA-SIFT: a More Distinctive Representation for Local Image Descriptors," Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:506-513, July 2004.
[21] V. Khanh, K. A. Hua and W. Tavanapong, "Image Retrieval Based on Regions of Interest," Proceedings of the IEEE Transactions on Knowledge and Data Engineering, 15:1045-1049, July 2003.
[22] Y. Kim, K. Lee, K. Choi and S. I. Cho, "Building Recognition for Augmented Reality Based Navigation System," Proceedings of the Sixth IEEE International Conference on Computer and Information Technology, pages 131-131, September 2006.
[23] G. Kootstra, J. Ypma and B. de Boer, "Active Exploration and Keypoint Clustering for Object Recognition," Proceedings of the 2008 IEEE International Conference on Robotics and Automation, pages 1005-1010, May 2008.
[24] S. Kumar and M. Hebert, "Man-made Structure Detection in Natural Images Using a Causal Multiscale Random Field," Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:119-126, May 2003.
[25] S. Lazebnik, C. Schmid, and J. Ponce, "A Sparse Texture Representation Using Affine-invariant Regions," Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:319-324, June 2003.
[26] M. Li, B. Hong and R. Luo, "Novel Method for Monocular Vision Based Mobile Robot Localization," Proceedings of the 2006 International Conference on Computational Intelligence and Security, pages 949-954, November 2006.
[27] Y.-F. Li, Y. Wang, W. Huang and Z.-L. Zhang, "Automatic Image Stitching Using SIFT," Proceedings of the 2008 International Conference on Audio, Language and Image Processing, pages 568-571, July 2008.
[28] Y.-R. Liao, Y.-C. Chen, K.-C. Chen and W.-G. Teng, "Supporting Landmark Image Retrieval with Skyline Extraction Techniques," Proceedings of the 2nd International Conference on Multimedia and Ubiquitous Engineering, pages 138-143, April 2008.
[29] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, 60:91-110, November 2004.
[30] D. G. Lowe, "Local Feature View Clustering for 3D Object Recognition," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 682-688, December 2001.
[31] D. G. Lowe, "Object Recognition from Local Scale-invariant Features," Proceedings of the Seventh IEEE International Conference on Computer Vision, 2:1150-1157, September 1999.
[32] K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors," Proceedings of the 2005 IEEE Transactions on Pattern Analysis and Machine Intelligence, 27:1615-1630, October 2005.
[33] K. Mikolajczyk, K., B. Leibe and B. Schiele, "Local Features for Object Class Recognition," Proceedings of the Tenth IEEE International Conference on Computer Vision, 2:1134-1141, October 2005.
[34] F. Monay and D. Gatica-Perez, "Modeling Semantic Aspects for Crossmedia Image Indexing," IEEE Transactions on Pattern Analysis and Machine Intelligence, October 2007.
[35] V. A. Nguyen and A. T. L. Phuan, "A Multi-processed Salient Point Detection System for Autonomous Navigation," Proceedings of the 10th International Conference on Control, Automation, Robotics and Vision, pages 2170-2175, December 2008.
[36] T. Qiu, X. Yiping and Z. Manli, "Robust Vehicle Tracking Based on Scale Invariant Feature Transform," Proceedings of the 2008 International Conference on Information and Automation, pages 86-90, June 2008.
[37] J. Sivic and A. Zisserman, "Video Google: a Text Retrieval Approach to Object Matching in Videos," Proceedings of the Ninth IEEE International Conference on Computer Vision, 2:1470-1477, October 2003.
[38] S. Stephen, D. Lowe and J. Little, "Global Localization Using Distinctive Visual Features," Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 1:226-231, October 2002.
[39] TinEye, http://www.tineye.com/.
[40] H.-H. Trinh, D.-N. Kim and K.-H. Jo, "Structural Analysis of Multiple Building for Mobile Robot Intelligence," Proceedings of the 2007 Annual Conference on Society of Instrument and Control Engineers, pages 2002-2007, September 2007.
[41] C.-F. Tsai, "A Review of Image Retrieval Methods for Digital Cultural Heritage Resources," Online Information Review, 31:185-198, 2007.
[42] T. Tuytelaars and L.V. Gool, "Matching Widely Separated Views Based on Affine Invariant Regions," International Journal on Computer Vision, 59:61-85, August 2004.
[43] N. Vasconcelos, "From Pixels to Semantic Spaces: Advances in Content-based Image Retrieval," Proceedings of the 2007 IEEE Computer Society, 40:20-26, July 2007.
[44] P. P. Vertongen and D. W. Hansen, "Location-based Services Using Image Search," Proceedings of the International Conference on Applications of Computer Vision, pages 1-6, january 2008.
[45] X. Wang, F. Hu and H. Yang, "A Novel Regions-of-interest Based Image Retrieval Using Multiple Features," Proceedings of the 12th International on Multi-Media Modeling Conference Proceedings, pages 377-380, January 2006.
[46] Y. Wang, K.-B. Jia and P.-Y. Liu, "A Novel ROI Based Image Retrieval Algorithm," Proceedings of the Second International Conference on Innovative Computing, Information and Control, pages 57-57, September 2007.
[47] Z.-Z. Wang, K.-B. Jia and P.-Y. Liu, "A Novel Image Retrieval Algorithm Based on ROI by Using SIFT Feature Matching," Proceedings of the 2008 International Conference on MultiMedia and Information Technology, pages 338-341, December 2008.
[48] Z.-Z. Wang, K.-B. Jia and P.-Y. Liu, "An Effective Web Content-based Image Retrieval Algorithm by Using SIFT Feature," Proceedings of WRI World Congress on Software Engineering, pages 291-295, May 2009.
[49] Wikipedia, http://en.wikipedia.org/.
[50] W. Xu, J. Wu, X. Liu, L. Zhu and G. Shi, "Application of Image SIFT Features to the Context of CBIR," Proceedings of the 2008 International Conference on Computer Science and Software Engineering, pages 552-555, December 2008.
[51] X. Yuan and C.-T. Li, "CBIR Approach to Building Image Retrieval Based on Invariant Characteristics in Hough Domain," Proceedings of the 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 1209-1212, March 2008.
[52] W. Zhang and J. Koˇseck´a, "Localization Based on Building Recognition," Proceedings of IEEE Computer Society Conference Workshops on Computer Vision and Pattern Recognition, pages 21-21, June 2005.
[53] W. Zhang and J. Koˇseck´a, "Image Based Localization in Urban Environments," Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission, pages 33-40, June 2006.
[54] W. Zhang and J. Koˇseck´a, "Hierarchical Building Recognition," Image Vision Computing, 25:704-716, May 2007.
[55] ZuBuD image dataset, http://www.vision.ee.ethz.ch/datasets/index.en.html.