尺寸不變特徵點轉換在圖像辨識的領域中已經是被廣泛使用的方法。利用尺寸不變性徵點轉換來擷取圖像經過縮放、旋轉、仿射模糊、光線變化後的特徵點，這些特徵點仍然是不變的。因此尺寸不變特徵點轉換用來搜索相似圖像是非常可靠的。但是傳統的尺寸不變特徵點是基於歐幾里得空間的特徵向量距離來做比較，因此當圖像數量增加時是很難擴充的。在本篇論文裡，我們提出了一種新穎的方法把尺寸不變特徵點存放在Hbase當中，不管資料庫裡面存放的圖像數量有多少，搜索特徵點的時間都可以在（O（1））時間內。在我們的實驗裡，藉由我們的方法可以達到在1000萬張圖像內搜索尺寸不變特徵點均控制在常數時間。

The Scale Invariance Feature Transform (SIFT) image descriptors have been widely used in the image recognition applications. The feature keypoints extracted by SIFT are invariant to scaling, rotation, affine distortion, and illumination changes. So the SIFT descriptors are very reliable for near duplicate image search. However, the traditional SIFT descriptors comparison is based on Euclidean distance of their feature vectors and thus is not scalable when the number of images increases. In this paper, we present a novel way to store the SIFT image descriptors in Hbase that facilitates constant (O(1)) descriptor lookup time irrelevant to the number of images stored in the databases. Our experiments in the scale of 10M images support that constant time SIFT descriptor lookup is achievable by our proposed method.

[1]. David G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, 2004.
[2]. Scale-invariant feature transform, http://en.wikipedia.org/wiki/Scale-invariant_feature_transform, referenced on June 12th, 2015.
[3]. Ian T. Joliffe, “Principal Component Analysis,” Springer-Verlag, 1986.
[4]. Yan Ke and Rahul Sukthankar, “PCA-SIFT: A More Distinctive Representation for Local Image Descriptors,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
[5]. Marcus, Adam. “The NoSQL Ecosystem,” The Architecture of Open Source Applications, 2011.
[6]. Fay Chang, Jeffrey Dean, Sanjay Ghemawat, Wilson C. Hsieh, Deborah A. Wallach, Mike Burrows, Tushar Chandra, Andrew Fikes, and Robert E. Gruber, “Bigtable: A distributed storage system for structured data,” ACM Transactions on Computer Systems, 2008.
[7]. Dhruba Borthakur, “HDFS architecture guide,” HADOOP APACHE PROJECT http://hadoop. apache. org/common/docs/current/hdfs design, 2008.
[8]. Nicole B Ellison. “Social network sites: Definition, history, and scholarship,” Journal of Computer‐Mediated Communication 13.1, 2007.
[9]. Michael Armbrust. “A view of cloud computing,” Communications of the ACM, 2010.
[10]. Jing Han, Haihong E, Guan Le, and Jian Du, “Survey on NoSQL database,” Pervasive computing and applications (ICPCA), 2011 6th international conference on. IEEE, 2011.
[11]. Christian S. Jensen, Dan Lin, and Beng Chin Ooi “Query and update efficient B+-tree based indexing of moving objects,” Proceedings of the Thirtieth international conference on Very large data bases-Volume 30. VLDB Endowment, 2004.
[12]. Imagemagick http://www.imagemagick.org/script/index.php, referenced on June 16th, 2015.
[13]. David G. Lowe, “Object recognition from local scale-invariant features,” International Conference on Computer Vision, 1999.
[14]. Tsung-Da Ho, “A Scalable Indexing Method for Local Invariant Features,” Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, 2008.
[15]. Lars George, “HBase: the definitive guide,” O'Reilly Media, Inc., 2011.
[16]. Kevin Wilkinson, Craig Sayers, Harumi Kuno, and Dave Reynolds, “Efficient RDF Storage and Retrieval in Jena2,” SWDB. Vol. 3, 2003.
[17]. Guoshen Yu and Jean-Michel Morel, “ASIFT: An Algorithm for Fully Affine Invariant Comparison,” Image Processing On Line, 2011.
[18]. Alaa E. Abdel-Hakim and Aly A. Farag “CSIFT: A SIFT Descriptor with Color Invariant Characteristics,” Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006.
[19]. Herbert Bay1, Tinne Tuytelaars, and Luc Van Gool, “SURF: Speeded Up Robust Features,” Computer Vision and Image Understanding, 2008.