摳像(Image Matting)是一個從輸入的影像或是影片中，擷取出前景的過程。摳像在電影工業以及影像處理中都是一項重要的技術，可以用於製作電影特效以及影像合成。所以，如何分離出完整的前景，就成為了一個重要的研究項目。在處理複雜背景的影像時，大部分的方法都會需要使用者提供額外的資訊，來標示何處是前景，何處是背景，有些地方則是混雜了前景與背景的區域，這時，使用者標示的資料，通稱為三原圖(Trimap)，就顯的相當重要。
本研究旨在將整個摳像的過程，包含產生三原圖，計算前景區域的部份，全部使用深度學習方法，成為全自動的過程，使用者只需輸入一張圖像，程式即可自動判斷前景的區域，並將前景計算出來。本研究也提出了一個新的深度學習摳像方法。研究結果顯示，在背景不單一的情況下，本研究仍能夠自動產生三原圖，且本研究提出的摳像方法也勝過其他的摳像方法。

Alpha matting is a method to extract the foreground from an input image or a video. It is an important technology in the film industry and image processing, which can be used to make movie effects and image synthesis. Therefore, how to separate the complete foreground has become an important research project. When input image has complex background, most of previous methods require users to provide additional information to indicate which part of the image is foreground region, which is the background region, and the other is uncertain region. The additional information, commonly known as the trimap, is quite important to the input image has complex background.
The purpose of this study is to make the whole alpha matting process, including generating trimap and calculating the alpha matte, become a fully automatic process by deep learning method. The user can only input the image and our system can automatically calculate. the area of the foreground. This study also proposes a new DL-based image matting method. The research results show that when there are multiple background regions, the research can still automatically generate the trimap, and the image matting method proposed in this study is better than other methods.

[Ako17] Y. Aksoy, T. O. Aydın, and M. Pollefeys, “Designing Effective Inter-Pixel Information Flow for Natural Image Matting,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, pp. 228-236, 2017.
[Bad17] V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 12, pp. 2481-2495, 2017.
[Che13] Q. Chen, D. Li, and C. K. Tang, “KNN Matting,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 35, no. 9, pp. 2175-2188, 2013.
[Cho16] D. Cho, Y. W. Tai, and I. Kweon, “Natural Image Matting using Deep Convolutional Neural Networks,” Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, pp. 626-643, 2016.
[Chu01] Y. Y. Chuang, B. Curless, D. Salesin, and R. Szeliski, “A Bayesian Approach to Digital Matting,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, USA, pp. 264-271, 2001.
[Don16] C. Dong, C. C. Loy, K. He, and X. Tang, “Image Super-Resolution Using Deep Convolutional Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 2, pp. 295-307, 2016.
[Gas10] E. S. L. Gastal and M. M. Oliveira, “Shared Sampling for Real-Time Alpha Matting,” Computer Graphics Forum, vol. 29, no. 2, pp. 575-584, 2010.
[Gra05] L. Grady, T. Schiwietz, and S. Aharon, “Random Walks for Interactive Alpha-Matting,” Proceedings of Conference on Visualization, Imaging, and Image Processing, 2005.
[Gup16] V. Gupta and S. Raman, “Automatic Trimap Generation for Image Matting,” Proceedings of International Conference on Signal and Information Processing (IConSIP), Vishnupuri, Nanded, 2016.
[He17] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, pp. 2980-2988, 2017.
[Hsi13] C. L. Hsieh and M. S. Lee, “Automatic Trimap Generation for Digital Image Matting,” Proceedings of 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Kaohsiung, 2013.
[Lev07] A. Levin, D. Lischinski, and Y. Weiss, “A Closed-Form Solution to Natural Image Matting,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 30, no. 2, pp. 228-242, 2007.
[Lev08] A. Levin, A. Rav-Acha, and D. Lischinski, “Spectral Matting,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 30, no. 10, pp. 1699 - 1712, 2008.
[Lut18] S. Lutz, K. Amplianitis, and A. Smolic, “AlphaGAN: Generative Adversarial Networks for Natural Image Matting,” Accepted by 29th British Machine Vision Conference (BMVC), British, arXiv:1807.10088, 2018.
[Sin13] S. Singh, A.S. Jalal, and C. Bhatanagar, “Automatic Trimap and Alpha-matte Generation for Digital Image Matting,” Proceedings of 2013 Sixth International Conference on Contemporary Computing (IC3), Noida, India, pp. 202-208, 2013.
[Smi96] A. R. Smith and J. F. BLINN, “Blue Screen Matting,” Proceedings of ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), New Orleans, USA, pp. 259-268, 1996.
[Sun04] J. Sun, J. Jia, C. K. Tang, and H. Y. Shum, “Possion Matting,” Proceedings of ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), Los Angeles, USA, pp. 315-321, 2004.
[Wan05] J. Wang, M. Cohen, J. Wang, and M. F. Cohen, “An Iterative Optimization Approach for Unified Image Segmentation and Matting,” Proceedings of IEEE International Conference on Computer Vision (ICCV), Beijing, China, pp. 936-943, 2005.
[Wan07] J. Wang and M. Cohen, “Optimized Color Sampling for Robust Matting,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolos, USA, pp. 1-8, 2007.
[Xu17] N. Xu, B. Price, S. Cohen, and T. Huang, “Deep Image Matting,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, pp. 311-320, 2017.
[Yan16] J. Yang, B. Price, S Cohen, H Lee, and M.H. Yang, “Object Contour Detection with a Fully Convolutional Encoder-Decoder Network,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, pp. 193-202, 2016.
[Zha15] R. Zhao, W. Ouyang, H. Li, and X. Wang, “Saliency Detection by Multi-Context Deep Learning,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, USA, pp. 1265-1274, 2015.
[Zhe09] Y. Zheng and C. Kambhamettu, “Learning Based Digital Matting,” Proceedings of IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan, pp. 889 - 896, 2009.