影像擷取是將圖片中的前景裁出的技術。本論文提出一個線上前景裁出工具NIM 3.0。NIM 1.0是第一個可以在瀏覽器上使用的影像擷取工具。使用者利用筆刷概略地刷過並涵蓋前景與背景之邊界。在畫的過程中，NIM就會開始分析筆刷涵蓋的範圍；它會從已知的前景區及背景區分別選取恰當的前景樣本及背景樣本，再根據這些樣本的灰階值，判斷涵蓋的區域為前景還是背景，並即時呈現處理的結果。NIM 2.0改進前一版的演算法加快處理速度。NIM 3.0增加的功能為：(1)可利用色調改善前景及背景灰階值相近時結果不佳的問題；(2)在分析筆刷涵蓋的區域時，能較快速地搜尋到前景及背景樣本；(3)避免筆刷移動太快時，所產生的擷取錯誤；(4)所能辨認的筆刷移動方向由四個增為八個，使之能更精確判斷前景及背景。NIM 3.0的處理速度比Photoshop及其它擁有前景裁出功能的線上工具快，且裁出的前景品質也較佳。

Image matting is a technique to extract the foreground from an image. NIM is the first Web-based image matting tool. The user only needs to roughly paint the boundary of the foreground to complete image matting. The computation begins when painting begins, and a partial result can be shown immediately. This paper presents NIM 3.0, which uses several new techniques to perform better than its earlier versions. NIM 3.0 produces better foreground quality and is faster than two other online foreground extraction tools and non-online Photoshop.

[1] Y.-Y. Chuang, B. Curless, D. H. Salesin, and R. Szeliski, "A Bayesian Approach to Digital Matting," Proceedings of IEEE Computer Vision and Pattern Recognition, vol. 2, pp. 264-271, 2001.
[2] J. Sun, J. Jia, C.-K. Tang, and H.-Y. Shum, "Poisson matting," ACM Transactions on Graphics, vol. 23, pp. 315-321, 2004.
[3] L. Grady, T. Schiwietz, S. Aharon, and R. Westermann, "Random walks for interactive alpha-matting," Proceedings of Visualization, Imaging and Image Processing, pp. 423-429, 2005.
[4] A. Levin, D. Lischinski, and Y. Weiss, "A Closed-Form Solution to Natural Image Matting," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
[5] J. Wang and M. F. Cohen, "Optimized color sampling for robust matting," IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp. 1-8.
[6] J. Sun, Y. Li, S. B. Kang, and H.-Y. Shum, "Flash matting," ACM Transactions on Graphics vol. 25, pp. 772-778, 2006.
[7] A. R. Smith and J. F. Blinn, "Blue screen matting," Proceedings of ACM SIGGRAPH, 1996, pp. 259–268.
[8] J. Wang and M. F. Cohen, "Image and video matting: a survey," Foundations and Trends in Computer Graphics and Vision, vol. 3, pp. 97-175, 2007
[9] E. S. L. Gastal and M. M. Oliveira, "Shared Sampling for Real-Time Alpha Matting," Proceedings of Eurographics 2010, 2010.
[10] Christoph Rhemann, Carsten Rother, Jue Wang, Margrit Gelautz, Pushmeet Kohli, and P. Rott, "A Perceptually Motivated Online Benchmark for Image Matting," Computer Vision and Pattern Recognition, 2009.
[11] Aviary. Phoenix image editor. Available: http://www.aviary.com/online/image-editor
[12] FotoFlexer. The world's most advanced online photo editor. Available: http://fotoflexer.com/
[13] 謝怡芳, "OPEN線上影像編輯器," 資訊工程系, 國立臺灣科技大學, 台北, 2009.
[14] Y.-C. Lin, H.-A. Wang, and Y.-F. Hsieh, "Image matting through a Web browser," Multimedia Tools and Applications, 2010. Available: http://www.springerlink.com/content/t3q0370w4312r70n/
[15] R. Barrett, M. Berry, T. F. Chan, J. Demmel, J. Donato, J. Dongarra, V. Eijkhout, R. Pozo, C. Romine, and H. v. d. Vorst, Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd ed. Philadephia, PA: SIAM, 1994.