近年來，隨著電腦科技的進步，數位影像資訊的快速累積，但如何在這龐大的影像資料庫中，快速又精確地找到需要的影像定位資訊，使得定位用影像檢索技術是一個值得深入研究的議題，以影像內容做為影像資料庫檢索(Content-Based Image Retrieval)已經成為影像檢索的重要方式。
一般來說，以內容(Content-Based)為主的影像檢索技術，會遵循著兩個步驟來進行影像檢索。首先針對每張影像作特徵的計算，並將特徵儲存在特徵庫中，此步驟稱為索引(indexing)；第二步驟稱為搜尋(searching)，檢索者選擇要使用的特徵擷取方法，並提供一張影像給系統進行搜尋，系統將比較此張特徵與資料庫中的特徵比較。根據步驟可發現，若影像資料庫越龐大，便會影響搜尋影像時的效率。
本論文將利用影像低階特徵擷取方法，包含顏色(color)、形狀(shape)、空間關係(spatial relationship)，透過影像的相似特徵，將我們所建立的影像資料庫縮減，並且使用SURF進行特徵點匹配，驗證此縮減後之影像資料庫仍足以代表原影像資料庫，藉此達到增加爾後影像資料庫搜尋的效率，並達到一個優良的定位效果。

In recent years, with advanced technology in computer, information of digital images accumulates rapidly. But how to find the information you need in the huge image positioning database quickly and accurately making image positioning retrieval technology a topic worthy of further research. Using image content as image database retrieval has become an important way of image retrieval.
Generally speaking, Content-Based Image Retrieval technology has two steps for image retrieval. First, it calculates each feature of every image and stores those features in the database; this step is called indexing. Second step is called searching. Searchers choose which way they would use for feature extraction and provide an image for the system to search. The system will relate the features of the image provided with those in the database. According to these steps, we can find that the larger is the image database, the more easily it lowers the efficiency of image searching.
This paper will use the extraction methods of low-level image feature, including colors, shapes, and spatial relationships. With similar features of images, we reduced the original image database we had built, and we used SURF to conduct feature point matching. It is to verify that the reduced image database is still qualified to represent the original one; therefore it can increase the efficiency in image database searching. The experimental results show higher navigation accuracy.

[1] M. Lux and S.A. Chatzichristofis, “Lire：Lucene image retrieval – an extensible java cbir library”, in ACM MM08., pp1085-1087, 2008.
[2] W. Niblack, R. Barber, W. Equitz, E. Glasman , D. Petkovic, P .Yanker, C.Faloutsos, and G. Taubin.“The QBIC project：Querying images by content using color, texture and shape”,In Proc. SPIE Storage and Retrieval for Image and Video Databases, February 1994.
[3] R. C. Agarwal, C. C. Aggarwal, V. V. V. Prasad. “Depth first generation of long patterns” , In Proc. of the 6th ACM SIGKDD Int. Conf. on knowledge Discovery and Data Mining, pages 108-118, 2000.
[4] G. Ashwin, T.V. Ghosal, S. "An image retrieval system with automatic query modification". Multimedia, IEEE Transactions, Volume: 4, Issue: 2, page: 201-214, Jun 2002
[5] H.P. Morevec, “Towards automatic visual obstacle avoidance ”,
Proceedings of 5th International Joint Conference on Artificial Intelligence, pp.584, 1977.
[6] C. Harris and M. Stephens, “A combined corner and edge detector”, In Alvey Vision Conference, pp. 147-151, 1988.
[7] D. G. Lowe. “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[8] H. Bay, A. Ess, T. Tuytelaars and L. V. Gool, “SURF: Speeded-Up Robust Features”, Computer Vision and Image Understanding, vol.110, pp.346-359, 2008.
[9] D.S. Zhang, A. Wong, M. Indrawan, G. Lu, Content based image retrieval using Gabor texture features. In: Proc. of 1st IEEE Pacific Rim Conference on Multimedia (PCM), pp. 392–395, 2000.
[10] G. J. G. Upton and B. Fingleton. Spatial Data Analysis by Example. Vol I. John Wiley & Sons, 1985.
[11] J. Huang, S.R. Kumar, M. Mitra, W.J Zhu, and R. Zabih, “Image indexing using color correlograms”,Proc.16th IEEE conf. On Computer Vision and Pattern Recognition, pp.762-768, 1997.
[12] M. J. Swain, D. H. Ballard, “Color indexing”, Int. J. Comput. Vis., Vol. 7, no. 1, pp 11-32, 1991.
[13] R. Sandler and M. Lindenbaum, “Optimizing gabor filter design
for texture edge detection and classification, ”International Journal of Computer Vision, Vol.84,No.3,pp.308-324, 2009.
[14] L.L Shen, and Z. Ji, “Gabor wavelet selection and SVM classification for object recognition, ” Acta Automatica Sinica, Vol. 35, No.4, pp.350-355, 2009
[15] Y. Zheng, “Breast cancer deterction with gabor features from digital mammograms,” Algorithms，Vol. 31, No.1, pp.44-62, 2009.
[16] X. Gao, B. Xiao, Ｄ. Tao, and X.Li, “Image categorization：graph edit distance+Edge direction histogram, ”pattern Recognition, Vol. 41,No.10,pp.3179-3191, 2008
[17] R. phan, D. Androutsos, “Content-based retrieval of logo and trademarks in unconstrained color image databases using color edge gradient co-occurrence histograms,” Computer Vision and Image Understanding, Vol.114, No,pp.66-84, 2009.
[18] 林承翰，「基於相鄰投票法之自動化圖像註解」，碩士論文，國立台北科技大學，台北 2011。
[19] P. Howarth and S. Ruger ,“ Evaluation of Texture Features for Content-Based Image Retrieval ,”CIVR 2004,LNCS 3115, pp. 326-334, 2004
[20] J. Li and J. Z. Wang. Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. Pattern Anal. Mach. Intell., 25:1075-1088, September 2003.
[21] 張宇宏，「基於顏色與SURF特徵之球場廣告看板內容辨識與計次系
統」，碩士論文，國立台北科技大學，台北 2011。
[22] J.M. Martinez, “MPEG-7 Overview (version 10)”,
http://mpeg.chiariglione.org/standards/mepg-7/mpeg-7.htm
[23] Wiki YCbCr色彩空間http://en.wikipedia,org/wiki/YCbCr
[24] Wiki CIE LUV色彩空間http://en.wikipedia,org/wiki/CIELUV
[25] http://wwwqbic.almaden.ibm.com/
[26] http://www.techbang.com/posts/11045-hard-to-see-google-street-view-
fleet-fifth-generation-high-definition-street-view-images-on-location
[27] 胡皓翔，「運用街景影像資料庫的智慧手機定位」，碩士論文，國
立台灣科技大學，台北 2013。