隨著科技的進步，人們的生活已經離不開手持3C裝置，而辨識技術的需求也日趨增加。辨識技術的應用相當廣泛，其應用包含機器人辨識、人臉辨識、指紋辨識和商品辨識。本論文提出了一個商品辨識系統，其中結合了尺度不變特徵轉換符，辭典包裹及支持向量機。由於傳統的尺度不變特徵轉換符僅使用於灰階圖影像處理，沒有考慮到其特徵點周圍顏色的資訊。就影像處理來說，顏色對於一張影像是一項極為重要的訊息。假如沒有顏色的資訊，此系統將無法對形狀相似但顏色不同的物件進行辨識。因此，本論文提出顏色尺度不變特徵轉換描述器，此描述器以原本的尺度不變特徵轉換符為基礎加以改進，並結合了特徵點附近的顏色資訊加於原本的128維度特徵符號後方，並考量到硬體的友善性和傳輸的資訊量，將描述器做了二值化的處理，成為一個新的特徵符號表示法。透過本文提出的特徵符號描述器，我們將可篩選在顏色資訊上不信任的特徵點，進而增加匹配的信任度。在實驗結果方面，本論文也和目前最新穎的兩種特徵符描述方法做比較，證明在不同情況下的辨識率上有有所提升，且實驗出在描述器二值化的情況下仍有一定的辨識率。

The smart technologies realized in smart devices for human assistances and the demands of recognition technologies increase daily in recent years. The applications of recognition are wide, including robots recognition, face recognition, fingerprint recognition and commodity recognition. This thesis proposed a commodity recognition system which combines SIFT, Bag of Words and SVM. Because of traditional SIFT processes image in the gray scale, by this way, the color information is missing. In image processing, color information is an important data for an image. Thus, a color-SIFT descriptor which is based on the traditional SIFT is proposed. Color-SIFT descriptor combines original 128 dims descriptor of SIFT with color information around the feature points. Then, the descriptor is binarized for hardware and transmission friendly. Through the color-SIFT, we can discard the unreliable matching in the color domain, and increase the robustness of matching tasks. In experimental results, the proposed system is compared with two other systems, prove it still has high recognition rate in different situations.

[1] D. Lowe, “Object Recognition from Local Scale-invariant Features”, Proceedings of the International Conference on Computer Vision,” pp. 1150–1157, 1999.
[2] D. Lowe, “Distinctive Image Features From Scale-invariant Key-points”, International Journal of Computer Vision, Vol. 60, No. 2, pp.91–110, 2004.
[3] S. Josef, Z. Andrew, “Efficient Visual Search of Videos Cast as Text Retrieval,” IEEE transactions on pattern analysis and machine intelligence, Vol. 31, No. 4, pp.591-605, 2009
[4] D. Nister and H. Stewenius, “Scalable Recognition with a vocabulary tree” in Proc. of IEEE Conference CVPR, pp. 2161-2168, 2006
[5] J.H Park, S.H Baeg, J. Koh, K.W Park, M.H. Beag, “A New Object Recognition System for Service Robots in the Smart Environment”, International Conference on Control, Automation and Systems, pp. 17-20, 2007
[6] B. F. Klare, M. J. Burge, J. C. Klontz, W. Richard, V. Bruegge, “Face Recognition Performance: Role of Demographic Information”, IEEE Signal Processing Society, Vol. 7, No 6, pp. 1789-1801, 2012
[7] V. Conti, C. Militello, F. Sorbello, S. Vitabile “Introducing Pseudo-Singularity Points for Efficient Fingerprints Classification and Recognition”, International Conference on Complex, Intelligent and Software Intensive Systems, Feb 2010, pp.368-375
[8] D. Zhang, K. H. Yap, S. Subbhuraam, “Mobile Product Recognition with Efferent Bag-of-Phrase Visual Search,” Communications, Control and Signal Processing (ISCCSP), pp. 65-68, 2014
[9] W. Zhang, K. H. Yap, D. J. Zhang, Z. W. Miao, “Feature Weighting in Visual Product Recognition”, IEEE International Symposium on Circuits and Systems (ISCAS), pp.734-737, 2015
[10] L. Y. Duan, F. Gao, J, Chen, J. Lin, T, Huang, “Compact Descriptor for Mobile Visual Search and MPEG CDVS Standardization”, on IEEE international Symposium on Circuits and Systems (ISCAS), pp. 885-888, 2013
[11] H. Bay, A. Ess, T. Tuytelaars, L. V. Gool, “Speed-Up Robust Features”, in Computer Vision and Image Understanding (CYIU), Vol. 110, No. 3, pp. 349-359, 2008
[12] A. Hakim, E. Alaa, A. A. Farag, “CSIFT: A SIFT Descriptor with Color Invariant Characteristics”, IEEE Computer Society Conference, Vol.2, pp. 1978-1983, 2006
[13] L, Bo, T. Whangbo, “A SIFT-Color Moments Descriptor for Object Recognition”, IT Convergence and Security(ICITCS), International Conference, pp. 1-3, 2014
[14] J. Matas, O. Chum, M. Urban, T. Pajdla, “Robust Wide Baseline Stereo from Maximally Stable Extremal Regions”, Proc. of British Machine Vision Conference, pp. 384-396, 2002
[15] N. Dalal, B. Triggs, “Histogram of Oriented Gradients for Human Detection”, IEEE computer Society Conference on Computer Vision and pattern Recognition (CVPR’05), Vol 1, pp. 886-893, 2005
[16] C. Harris, M. Stephens, “A Combined Corner and Edge Detector”, Proceedings of the 4-th Alvey Vision Conference, pp. 147-151, 1988
[17] R. O. Duda, P. E. Hart, “Use of the Hough Transform Translation to Detect Lines and Curves in Pictures,” Comm. ACM, Vol. 15, pp. 11-15, 1972
[18] J. Shi, C. Tomasi, “Good Feature to Track”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR94), pp. 593-600, 1994
[19] P. M. Panchal, S. R. Panchal, S. K. Shah, “A Comparison of SIFT and SURF”, in international Journal of Innovative Research in computer and Communication Engineering Vol. 1, No. 2, pp. 323-327, 2013
[20] K. Milolajczyk, C. Schmid, “A Performance Evaluation of Local Descriptors", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, No. 27, pp 1615-1630, 2005
[21] E. Nowak, F. Jurie, and B. Triggs, “Sampling Strategies for Bag-of-features Image Classification,” in Proc. Eur. Conf. Comput. Vis. (ECCV), pp. 490–503, 2006
[22] C. C. Chung, C. J. Lin, “LibSVM” http://www.csie.ntu.edu.tw/~cjlin/libsvm/
[23]C. Sharat. “Introduction to kd-trees”, University of Maryland Department of Computer Science.
[24] D. Elena, D. M. Marie “Encyclopedia of Distances”. 2009
[25] E.F. Krause. Taxicab Geometry. Dover. 1987
[26] L. Kabbai, A. Azaza, M. Abdellaoui, A, Douik “Image Matching Based on LBP and SIFT Descriptor”, IEEE Conference on Systems, Signals & Devices (SSD), pp.1-6, 2015