本研究旨在提出結合雲端運算及影像辨識之行動商品比價系統，因應現今物價與人民平均所得之比例逐漸失衡，商品比價成為民眾重視的一項需求，本系統提供使用者便捷的操作模式，使用者僅需利用行動裝置之照相功能，以任意角度拍下商品照片後上傳至雲端，系統即會透過雲端上部署之影像辨識比對技術取得符合之商品，並在合理時間內將比價資訊回傳給使用者。
辨識技術在本研究可分為三階段，在進行各階段辨識前，系統會先透過前處理模組去除商品影像背景雜訊並取得商品外觀輪廓，在第一階段辨識採用傅立葉描述子 (Fourier Descriptor，FD) 進行商品之輪廓外觀辨識以篩選出外觀符合之商品，第二階段為本研究所提出之以色調為基礎之圖像分割法 (Hue-Based Image Segmentation，HBIS)，將針對篩選出之商品內部顏色進行辨識比對，且為了更進一步提升辨識之準確度，本研究加入第三階段加速穩健特徵（Speeded Up Robust Features，SURF），以比對更細部之商品內部區域特徵，系統透過上述三階段之辨識模式，並加入雲端平行與分散式運算之特性，可讓使用者快速取得符合之商品資訊。
本研究透過實際商品樣本蒐集與測量，根據實驗結果，在辨識後商品排名第一名即為正確商品之條件下，採用FD+HBIS兩階段辨識模式之商品辨識準確率可達86.85%，加入第三階段SURF之影像區域比對特性，最佳辨識率可達100%，且透過雲端系統可在0.953秒內完成商品辨識，快速將最符合之商品資訊回傳給使用者，如此可滿足使用者以實惠之價格購得所需商品。

Due to the rising price of merchandise, parity between merchandise has become an important demand. This study provides a convenient operation of the mobile parity system for users to compare price of merchandise. Users only use mobile device function such as camera and upload photo to the parity system after taking merchandise photo at any angle. Users will get the parity information of merchandise immediately through image recognition technology and cloud computing.
The image recognition technology can be divided into three phases. The first phase uses “Fourier Descriptors” (FD) to filter out the contour of the merchandise. The second phase uses “Hue-Based Image Segmentation” (HBIS) approach for matching merchandise color. The third phase uses “Speeded Up Robust Features” (SURF) to match the characteristics of the merchandise region in detail.
The findings are the following: In the condition of the correct merchandise that will ranked first after three phases recognition, the recognition rate can be up to 90% with a 1-second by cloud computing. Finally, the findings will proved this study’s mobile parity system is feasible in the real world.

[1] Qureshi, S. S., Ahmad, T., & Rafique, K., “Mobile cloud computing as future for mobile applications-Implementation methods and challenging issues,” In 2011 IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), pp. 467-471, 2011
[2] Nkosi, M., & Mekuria, F., “Improving the capacity, reliability & life of mobile devices with Cloud Computing,” In IST-Africa Conference Proceedings, pp. 1-9, 2011
[3] Jain, A. K., Klare, B., & Park, U., “Face matching and retrieval in forensics applications,” IEEE MultiMedia, Vol.19, No.1, pp. 20. 2012
[4] Du, S., Ibrahim, M., Shehata, M., & Badawy, W., “Automatic License Plate Recognition (ALPR): A State-of-the-Art Review,” IEEE Transactions on Circuits and Systems for Video Technology, Vol.23, No.2, pp. 311-325, 2013
[5] Pirlo, G., & Impedovo, D., “Adaptive membership functions for handwritten character recognition by Voronoi-based image zoning,” IEEE Transactions on Image Processing, Vol.21, No.9, pp. 3827-3837, 2012
[6] Munoz-Mejias, D., González-Díaz, I., & Diaz-de-Maria, F., “A low-complexity pre-processing system for restoring low-quality QR code images,” IEEE Transactions on Consumer Electronics, Vol.57, No.3, pp. 1320-1328, 2011
[7] Venkatesh, V., Morris, M. G., Davis, G. B., & Davis, F. D., “User acceptance of information technology: Toward a unified view,” MIS quarterly, pp. 425-478, 2003
[8] Badger, L., Grance, T., Patt-Corner, R., & Voas, J., “Draft cloud computing synopsis and recommendations,” Recommendations of the National Institute of Standards and Technology, 2011
[9] Mell, P., & Grance, T., “The NIST definition of cloud computing (draft),” NIST special publication, 800.145, pp. 7, 2011
[10] Dean, J., & Ghemawat, S., “MapReduce: simplified data processing on large clusters,” Communications of the ACM, Vol.51, No.1, pp. 107-113, 2008
[11] Gonzalez, R. C., Woods, R. E., & Eddins, S. L., “Digital image processing using MATLAB (Vol. 2),” Knoxville: Gatesmark Publishing, 2009
[12] Sonka, M., Hlavac, V., & Boyle, R., “Image processing, analysis, and machine vision,” Brooks/Cole, Pacific Grove, CA, 1999
[13] Maglianesi, M., & Stegmayer, G., “Methodology for the construction of a biometric facial recognition system based on a neural classifier,” Latin America Transactions, IEEE (Revista IEEE America Latina), Vol.10, No.5, pp. 2175-2184, 2012
[14] Tsai, S. S., Chen, D., Chen, H., Hsu, C. H., Kim, K. H., Singh, J. P., & Girod, B, “Combining image and text features: a hybrid approach to mobile book spine recognition,” In Proceedings of the 19th ACM international conference on Multimedia, pp. 1029-1032, 2011
[15] Lo, C. C., Kuo, T. H., Kung, H. Y., Kao, H. T., Chen, C. H., Wu, C. I., & Cheng, D. Y., “Mobile merchandise evaluation service using novel information retrieval and image recognition technology,” Computer Communications, Vol.34, No.2, pp. 120-128, 2011
[16] Youlian, Z., Cheng, H., & Lifang, Z., “A Median Image Filtering Algorithm Based on Statistical Histogram,” In 2013 Fifth International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), pp. 17-20, 2013
[17] Panggabean, M., & Rønningen, L. A., “Character recognition of the Batak Toba alphabet using signatures and simplified chain code,”In 2009 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 215-220, 2009
[18] Reddy, B. S., & Chatterji, B. N., “An FFT-based technique for translation, rotation, and scale-invariant image registration,” IEEE Transactions on Image Processing, Vol.5, No.8, pp. 1266-1271, 1996
[19] Niu, Q., Zhang, H., Liu, J., Wang, Q., Xu, G., & Xue, Y., “A shape contour description method based on chain code and Fast Fourier Transform,”In 2011 Seventh International Conference on Natural Computation (ICNC) , Vol.3, pp. 1809-1812, 2011
[20] White, T., “Hadoop: the definitive guide,”O'Reilly, 2012
[21] Banerjee, A., & Dutta, A., “Fuzzy matching scheme on fourier descriptors for retrieval of 2 dimensional shapes,”In 2012 National Conference on Computing and Communication Systems (NCCCS), pp. 1-5, 2012
[22] Wanli, F., & GaoShangbing, G., “A vehicle license plate recognition algorithm in night based on HSV,” In 2010 3rd International Conference on Advanced Computer Theory and Engineering (ICACTE), Vol. 4, pp. V4_53-56, 2010
[23] Son, J. W., Park, S. B., & Kim, K. J., “A convolution kernel method for color recognition,” In 2007 Sixth International Conference on Advanced Language Processing and Web Information Technology , pp. 242-247, 2007
[24] Lowe, D. G., “Distinctive image features from scale-invariant keypoints,” International journal of computer vision, Vol.60, No.2, pp. 91-110, 2004
[25] Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L., “Speeded-up robust features (SURF),” Computer vision and image understanding, Vol.110, No.3, pp. 346-359, 2008
[26] Juan, L., & Gwun, O., “A comparison of sift, pca-sift and surf,” International Journal of Image Processing (IJIP), Vol.3, No.4, pp. 143-152, 2009
[27] Viola, P., & Jones, M., “Rapid object detection using a boosted cascade of simple features,” In Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol.1, pp. I-511 - I-518, 2001