受惠於網路商場提供的便利性與多樣性，在網路上購買服飾配件對於許多消費者來說已經成為常態。為了使商品更貼近使用者，許多虛擬試穿系統因應而生。本篇論文提供一個結合自動配件切割的互動式虛擬配件試戴系統。使用者只需將喜歡的配件圖與實戴圖兩種類型的影像輸入系統中，系統會自動將實戴圖上的配件擷取下來，載入試戴系統提供使用者做後續選取。當使用者從試戴系統中選取欲試戴的配件時，系統根據配件原始的資訊將擷取下來的配件放在使用者身上合適的位置完成試戴功能。
本篇論文在配件切割的階段，不透過任何人工標記的方式，僅依照配件本身的物理特性對實戴圖做區域擷取。將擷取下來的區域做超像素分割，對每個超像素上的色彩資訊做統計。利用色彩直方圖統計結果產生的特徵向量做為篩選配件區域的標準，找出和配件具有相似顏色的超像素集合做為配件切割的結果。
本篇論文在試戴系統階段，利用kinect快速追蹤到使用者的骨架資訊，對使用者做人臉追蹤與手勢偵測。當使用者選取配件後，系統會讀入相對應的配件資訊並根據人臉追蹤的結果確定配件放置的位置。
在實驗中，配件切割的準確率皆能達到90%以上且試戴系統在個人電腦上也能達到30 fps的實時運作。

The convenience and diversity of online shopping makes many consumers willing to buy apparel or accessories on the web. In order to make products more attractive to users, many virtual try-on systems are developed for e-commerce applications. This paper proposes an interactive virtual try-on system combined with automatic accessory segmentation. Our system automatically retrieves the accessory from images and store them in the try-on system to provide users with subsequent selection. When a user selects the hat that he or she wants to try on, the accessory is placed on the proper position of the user in the image.

In the stage of accessories segmentation, we perform background elimination and super-pixel segmentation. According to the color information on the accessory image, the feature vector generated by the color histogram is used to select super-pixels that belong to the accessories. In the stage of try-on system, we use Kinect, which provides skeleton information, to track the user’s face and gestures. When a user selects the accessory, the proposed system reads the corresponding accessory information and places the accessory in the appropriate location based on the results of the face tracking. In the experiment, the segmentation part of our system can reach an accuracy of more than 90%. The proposed try-on system can reach 30 fps real-time speed in a personal computer.

[1] R. C. Gonzalez and R. E. Woods, “Digital imaging processing,” Massachusetts: Addison-Wesley, 1992
[2] I. Karoui, R. Fablet, J.-M. Boucher, and J. Augustin, “Variational region-based segmentation using multiple texture statistics,” Proc. IEEE Transactions on Image Processing, vol. 19, no. 12, pp. 3146–3156, 2010.
[3] C. Rambabu, I. Chakrabarti, and A. Mahanta, “Floodingbased watershed algorithm and its prototype hardware architecture,” Proc. IEEE Proceedings-Vision, Image and Signal Processing, vol. 151, no. 3, pp. 224–234,2004
[4] J. Shi and J. Malik, “Normalized cuts and image segmentation,” Proc. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888–905, 2000
[5] P. F. Felzenszwalb and D. P. Huttenlocher, “Efficient graphbased image segmentation,” Proc. International Journal of Computer Vision, vol. 59, no. 2, pp. 167–181, 2004
[6] C. Rother, V. Kolmogorov, and A. Blake, “Grabcut: Interactive foreground extraction using iterated graph cuts,” Proc. ACM Transactions on Graphics (TOG), vol. 23, no. 3, 2004, pp. 309–314
[7] D. Freire-Obregon, M. Castrill ´ on-Santana, E. Ram ´ on-Balmaseda and J. Lorenzo-Navarro “Automatic clothes segmentation for soft biometrics” Proc. IEEE International Conference on Image Processing (ICIP), 2014, pp. 4972–4976
[8] B. Zhao, X. Wu, Q. Peng, S Yan “Clothing Cosegmentation for Shopping Images With Cluttered Background",Proc. IEEE Transactions on multimedia , vol. 18, no. 6, JUNE 2016
[9] Y. I. Yang, C. K. Yang, and C. H. Chu, “A virtual try-on system in augmented reality using RGB-D cameras for footwear personalization,” J. Manuf. Syst., vol. 33, no. 4, pp. 690–698, 2014
[10] P. Azevedo, T. Oliveira dos Santos, E. de Aguiar “An Augmented Reality Virtual Glasses Try-On System”, Proc. IEEE pp.21-24 June 2016
[11] Z. Xianhui,D. Yongsheng, S.Shihuang “Applying Image Warping Technique to Implement Real-Time Virtual Try-on”, Proc. IEEE pp.26-28 Dec. 2009
[12] V. Kazemi , J. Sullivan "One millisecond face alignment with an ensemble of regression trees ", Proc. IEEE Intell. Veh. Symp., pp. 926-932, 2014
[13] A. Aziz , Karara "Direct Linear Transformation from Comparator Coordinates into Object Space Coordinates in Close Range Photogrammmetry. " Proc. ASP/UI Symposiumon Close-Range Photogrammetry, Urbana, Illionis, pp. 1-18.,1971
[14] S. Roweis, “Levenberg-Marquardt Optimization” (University of Toronto, 1996) http://www.cs.toronto.edu/∼roweis/notes.html
[15] Y. Boykov and G. Funka-Lea, “Graph cuts and efficient n-d image segmentation,” Proc International Journal of Computer Vision, vol. 70, no. 2, pp. 109–131, 2006
[16] M. Van den Bergh, X. Boix, G. Roig, and L. Van Gool. SEEDS: “Superpixels Extracted via Energy-Driven Sampling”. Proc. IJCV, 111(3):298–314, 2015
[17] K. He, C. Rhemann, C. Rother, X. Tang, and J. Sun. “A global sampling method for alpha matting”. Proc. CVPR, pages 2049–2056, 2011.
[18] C. Rhemann, C. Rother, and M. Gelautz. “Improving color modeling for alpha matting”.Proc. BMVC, 2008.
[19] K. He, J. Sun, and X. Tang. “Guided image filtering” Proc. Pattern Analysis and Machine Intelligence, IEEE Trans., 2012
[20] Viola, P., Jones, M. “Rapid object detection using a boosted cascade of simplefeatures.” Proc. CVPR pp.511 – 518, 2001
[21] Dlib C++ library , http://dlib.net/