這篇論文提出了使用尺寸不變特徵點轉換可能會出現的弱點。
尺寸不變特徵點轉換在影像辨識的領域中已經是被廣泛使用的方法。尺寸不變性徵點轉換是用來擷取影像中的特徵點，用此方法取出的特徵點用於不同影像之間的辨識具有相當的可靠性；用此方法取出的特徵點不受尺寸縮放、旋轉等變化影響。然而其關鍵點描述子有128維，要儲存此資料將花費大量空間。因此，利用主成份分析將維度下降至36維的方式也被提出。
而利用主成份分析後的資料是常態分佈，非常適合使用二值化將其化簡，並使用完美雜湊法儲存資料，將可快速查詢。我們希望能增加二值化後的成功率，並發現了二值化並使用完美雜湊法後會出現的缺點。並且指出使用尺寸不變特徵點轉換時，圖片內的物件角度、光源方向以及圖片尺寸都可能影響結果。

The SIFT have been widely used in the image recognition applications. The feature keypoints extracted by SIFT are invariant to image scaling and rotation. But we need a lot of storage to store the keypoint descriptors with 128 dimensions. A method was proposed that using the Principal Component Analysis (PCA) to reduce the dimension to 36.
Observing that the PCA-SIFT keypoint descriptors is in normal distribution, we propose to simplify the descriptors using binarization and store the binarized descriptors by perfect hash to speed up the query time. However, to improve the accuracy after binarization we identify several weaknesses after applying the perfect hash technique. Through extensive experiments, the results suggest that the robustness of the SIFT descriptors are greatly affected by the angle of objects to be recognized, the lighting directions, and the size of the input images. Therefore, we conjecture that the applications of using SIFT for object recognition in 3D environment are limited and should be designed under scrutiny.

[1]Photosynth - Capture your world in 3D, http://www.photosynth.net/, referenced on May 1st, 2012.
[2]Photo Tourism, http://phototour.cs.washington.edu/, referenced on May 1st, 2012.
[3]G. Yu and J.-M. Morel, “ASIFT: An Algorithm for Fully Affine Invariant Comparison,” Image Processing On Line, 2011.
[4]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, 2006.
[5]H. Bay, A. Ess, T. Tuytelaars, L. V. Gool, "SURF: Speeded Up Robust Features", Computer Vision and Image Understanding, 2008
[6]Y. Ke and R. Sukthankar, “PCA-SIFT: A More Distinctive Representation for Local Image Descriptors,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004.
[7]A. M. Bronstein, M. M. Bronstein, L. J. Guibas and M. Ovsjanikov, “Shape Google: geometric words and expressions for invariant shape retrieval”, ACM Transactions on Graphics, 2011.
[8]Y. Usui and K. Kondo, “3D Object Recognition Based on Confidence LUT of SIFT Feature Distance”, World Congress on Nature and Biologically Inspired Computing, 2010.
[9]R. Zhou, J. Wu, Q. He, C. Hu and Z. Yu, “Approach of Human Face Recognition Based on SIFT Feature Extraction and 3D Rotation Model”, International Conference on Information and Automation, 2011.
[10]D. G. Lowe, “Object recognition from local scale-invariant features,” International Conference on Computer Vision, 1999.
[11]D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, 2004.
[12]I. T. Joliffe, “Principal Component Analysis,” Springer-Verlag, 1986.
[13]P. Indyk and R. Motwani, “Approximate nearest neighbors: towards removing the curse of dimensionality,” Proceedings of the thirtieth annual ACM Symposium on Theory of Computing, 1998.
[14]Alex Andoni’s LSH page, http://web.mit.edu/andoni/www/LSH/index.html, reference on May 1st, 2012.
[15]Y. Ke, R. Sukthankar and L. Huston, “An efficient parts-based near-duplicate and sub-image retrieval system,” Proceedings of the 12th annual ACM International Conference on Multimedia, 2004
[16]T.-D. 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
[17]K. Lin, “A Scalable Indexing Method for SIFT using Two-tier Hashing,” Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, 2009.
[18]SIFT Library, http://blogs.oregonstate.edu/hess/code/sift/, referenced on May 1st, 2012.
[19]R. Hess, “An Open Source SIFT Library,” ACM Multimedia 2010, 2010.
[20]ImageMagick, http://www.imagemagick.org/script/index.php, referenced on May 1st, 2012.
[21]Y. Ke and R. Sukthankar, PCA-SIFT, http://www.cs.cmu.edu/~yke/pcasift/, referenced on May 1st, 2012.
[22]CMPH - C Minimal Perfect Hashing Library, http://cmph.sourceforge.net/, referenced on May 1st, 2012.
[23]Scale-invariant feature transform, http://en.wikipedia.org/wiki/Scale-invariant_feature_transform, referenced on May 1st, 2012.