臺灣博碩士論文加值系統

隨著數位照相技術的發展，越來越多人使用智慧型手機與數位相機於戶外拍攝生活照片，且隨著近年來網路社群的盛行，越來越多人喜歡透過網路社群分享拍攝的照片並將自已美好的一面呈現出來。但是，隨著年齡的增長與日常生活的壓力，皮膚會出現老化與暗沉的問題，造成所拍攝出來的影像不如預期。目前市面上影像軟體常見的處理方式，仍然需要使用者手動的操作定位人臉或者是臉部特徵，雖然可以解決多人臉尋找的問題，但對於非人臉的處理仍有一些瑕疵存在。有鑒於此，本文提出一套基於多人為基礎之人臉美化演算法，首先，採用膚色偵測搭配人臉偵測找出影像中人臉的位置，並透過膚色區塊搜尋與人臉偵測區域整合判斷出影像中人臉的臉部遮罩，同時將原影像進行亮度調整以及雙邊濾波器作平滑運算。最後，利用泊松圖像編輯將平滑後的影像透過臉部遮罩無縫接合至原影像中，使影像中的人臉達到修整與美化的效果，且非人臉部分仍可以維持原有的風貌，此方法可推廣至多人環境的影像中。實驗結果顯示，本文提出人臉美化演算法相較於其他的演算法能有效的改善影像中人臉皮膚上皺紋、暗沉和其他皮膚問題。

With the advance of technology and science, more and more people use smartphones and digital cameras to shoot their outdoor life photos. On the other hand, with the rise in popularity of the internet, more and more people like to share their photos through the online community. Everyone hopes the bright side presented to the others but the photos shoot are often not as expected, because the skin becomes old and dull by the increasing age and stress of life. Currently, the common APP on the market still requires the user to manually locate the facial location or facial features. Although it is possible to solve the problems of the face searching, but it still exists some flaws on the non-face part. For this reason, we propose an algorithm for multi-facial skin beautification design to improve the photo of the human face skin wrinkles, dull and other skin problems. First, the face location in the photo is searched by skin color detection and face detection, and the face mask is determined by the areas of the skin color detection and face detection. On the other hand, the original photo brightness is adjusted and using a bilateral filter for image smoothing. Finally, we use the Poisson image algorithm to seamless the smoothing image to the original image by the face mask. The proposed method can be extended to a multiplayer environment photos and improve the human face skin wrinkles, dull and other skin problems. In addition, the non-face areas can still also maintain the original photo style. Finally, the experimental results show that the proposed algorithm is better than other algorithm and achieve satisfied performance.

摘要 I
ABSTRACT II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 IX
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 論文架構 2
第二章 相關技術研究 3
2.1 色彩空間 3
2.2 膚色偵測 6
2.2.1基於Soriano等人提出之RGB膚色偵測 7
2.2.2基於Kovac等人提出之RGB膚色偵測 8
2.2.3 HSI膚色偵測 9
2.2.4 YCbCr膚色偵測 9
2.3 美化濾波器 11
2.3.1均值濾波器 11
2.3.2高斯濾波器 13
2.3.3雙邊濾波器 15
2.4 連通物件標示演算法 17
2.5 人臉偵測 18
2.5.1 Haar-Like Features 20
2.5.2積分影像法 21
2.5.3 AdaBoots演算法 23
2.5.4弱分類器 23
2.5.5階層分類器 25
2.6 無縫接合技術介紹 26
第三章 研究方法 29
3.1 人臉偵測 30
3.2膚色偵測 32
3.3區域偵測及臉部遮罩 32
3.4亮度調整 36
3.5美化濾波器 37
3.6無縫接合 44
第四章 實驗結果及比較 48
4.1 實驗結果 48
4.2 比較結果 53
第五章 結論及未來展望 57
5.1 結論 57
5.2 未來展望 58
附錄 63

[1]鄭家在，自動化證件照拍攝演算法設計，國立金門大學電子工程學系碩士論文，民國102年。
[2]M. Sonka, V. Hlavac, and R. Boyle, "Image Processing, Analysis, and Machine Vision," Chapman & Hall Computing, London, 1993.
[3]鄔誌仁，膚色偵測器應用於即時臉部擷取系統，國立臺灣師範大學機電科技研究所，民國96年。
[4]M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, "Skin color modeling under varying illumination conditions using the skin locus for selecting training pixels," Proceedings of IEEE Nordic Signal Processing Symposium, Kolmården, Sweden, 2000.
[5]M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, "Skin detection in video under changing illumination conditions," Proceedings of the 15th International Conference on Pattern Recognition, 2000.
[6]陳勇緯，即時人臉特徵擷取技術，玄奘大學資訊管理系碩士論文，民國99年。
[7]陳佳源，結合平移距離與傅立葉特徵之手勢辨識系統，中原大學資訊工程學系碩士論文，民國九十六年。
[8]高建坡、王煜堅、楊浩、吳鎮揚，一種基於KL變換的橢圓模型膚色檢測方法，民國96年。
[9]吳俊霖，使用簡易型雙向濾波器消除影像高斯雜訊，國立中興大學資訊科學與工程學系，民國99年。
[10]莊尚仁，加入高斯濾波器之霍普菲爾類神經網路之辨識研究，國立高雄海洋科技大學電訊工程所，民國100年。
[11]L. G. Shapiro and G. C. Stockman, "Computer Vision", Prentice Hall, 2001.
[12]M. S. Nixon and A. S. Aguado, "Feature Extraction and Image Processing," Academic Press, 2008.
[13]C. Tomasi and R. Manduchi, "Bilateral filtering for gray and color images," IEEE ICASSP, Jan. 1998.
[14]A. Rosenfeld and J. L. Pfaltz, "Sequential Operation in Digital Image Processing," Journal of the ACM, vol. 13, 1996.
[15]許博翔，多像素管線式單回合連通物件標示演算處理器之軟／硬整合設計與實現，國立台灣科技大學電子工程系，民國101年7月。
[16]K. Wu, E. Otoo, and A. Shoshani, "Optimizing Connected Component Labeling Algorithms," Lawrence Berkeley National Laboratory, 2005.
[17]M. Manohar and H. K. Ramapriyan, "Connected Component Labeling of Binary Images on a Mesh Connected Massively Parallel Processor," CVGIP, vol. 45, pp. 133-149, 1989.
[18]A. Rasquinha and N. Ranganathan, "C3L: A Chip for Connected Component Labeling," Tenth International Conference on VLSI Design, VLSI in Multimedia Applications, pp. 446, 1997.
[19]D. G. Bailey and C. T. Johnston, "Single Pass Connected Components Analysis," Image and Vision Computing New Zealand, Hamilton, NZ, 2007.
[20]C. T. Johnston and D. G. Bailey, "FPGA Implementation of a Single Pass Connected Components Algorithm," Electronic Design, Test and Applications, pp. 228-231, 2008.
[21]R. Walczyk, A. Armitage, and T. D. Binnie, "Comparative Study on Connected Component Labeling Algorithms for Embedded Video Processing Systems," IPCV'10, CSREA Press, vol. 2, 2010.
[22]M. H. Yang, D. Kriegman, and N. Ahuja, "Detecting faces in images: a survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, Jan. 2002.
[23]余誌強，結合擴增式合爾材質特徵與AdaBoost演算法應用於人臉偵測之研究，育達商業科技大學資訊管理研究所研士學位論文，民國102年6月。
[24]P. Viola and M. Jones. "Robust Real-Time Face Detection", International Journal of Computer Vision, vol.57, no.2, pp. 137-154, 2004.
[25]T. K. Leung, M. C. Burl, and P. Perona, "Finding faces in cluttered scenes using random labeled graph matching," International Conference on Computer Vision, pp. 637-644, 1995.
[26]M. C. Burl, T. K. Leung, and P. Perona, "Face localizatin via shape statistics," International Conference on Workshop Automatic Face and Gesture Recognition, pp. 154-159, 1995.
[27]T. K. Leung, M. C. Burl, and P. Perona, "Probabilistic affine invariants for recognition," IEEE Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, pp. 678-684, 1998.
[28]D. G. Kendall, "Shape manifolds, procrustean metrics, and complex proxjective shapes," Bulletin of the London Mathematical Society, vol. 16, no. 2, pp. 81-121, 1984.
[29]K. V. Mardia and I. L. Dryden, "Shape distributions for landmark data," Advanced Applied Probability, vol. 21, no. 11, pp. 742-755, 1989.
[30]T. Sakai, M. Nagao, and S. Fujibayashi, "Line extraction and pattern detection in a photograph," Pattern Recognition, vol. 1, pp. 233-248, 1969.
[31]I. Craw, H. Ellis, and J. Lishman, "Automatic extraction of face features," Pattern Recognition Letters, vol. 5, no. 2, pp. 183-187, 1987.
[32] A. Samal and P. A. Iyengar, "Human face detectin using silhouettes," International Journal of Pattern Recognition and Artificial Intelligence, vol. 9, no. 6, pp. 845-867, 1995.
[33]A. Yuille, P. Hallinan, and D. Cohen, "Feature extraction from faces using deformable templates," International Journal of Computer Vision, vol. 8, no. 2, pp. 99-111, 1992.
[34]G. J. Edwards, C. J. Taylor, and T. Cootes, "Learning to identify and track faces in image sequences," International Conference on Computer Vision, Nara, Japan, pp. 260-265, 1998.
[35]T. Kohonen and P. Lehtio, "Storage and Processoing of information in distributed associative memory systems," in Models of Associative Memory, G. E. Hinton and J. A. Anderson, Eds., vol. 4, 1981.
[36]M. Turk and A. Pentland, "Eigenfaces for recognition," Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[37]梁振升，以OpenCV實現即時之人臉偵測與辨識系統，銘傳大學電腦與通訊工程學系碩士論文，民國99年7月。
[38]L. H. Koh, S. Ranganath, Y. V. Venkatesh, "An integrated automatic face detection and recognition system," Pattern Recognition, vo. 35, pp. 1259-1273, 2002.
[39]P. Viola, M. Jones, "Robust Real-time Object Detection," Second International Workshop on Statistical and Computational Theories of Vision - Modeling, Learning, Computing, and Sampling, 2001.
[40]M. Kearns and L. G. Valiant, "Learning boolean formulae or finite automata is as hard as factoring," Harvard University Aiken Computation Laboratory, TR-14-88, 1988.
[41]L. G. Valiant, "A Theory of the Learnable," Communications of the ACM, vol. 27, no.11, pp. 1134-1142, 1984.
[42]M. Kearns, "The computational complexity of machine learning," in Cambridge: MIT Press London, England: Massachusetts, 1990.
[43]V. Kwatra, A. Schödl, I. Essa, G. Turk, A. Bobick, "Graphcut Textures:Image and Video Synthesis Using Graph Cuts," ACM Trans. Graph (TOG), vol. 22(3), pp. 277-286, 2003.
[44]Y. Y. Boykov and M. P. Jolly, "Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images," International Conference on Computer Vision, Vancouver, Canada, vol. 1, pp. 105-112, 2001.
[45]龔興東，自動臉部特徵偵測整容系統，國立臺灣科技大學資訊管理系，民國96年。
[46]A. Levin, A. Zomet, S. Peleg, and Y. Weiss, "Seamless Image Stitching in the Gradient Domain," ECCV 2004, pp. 377-389, 2004.
[47]P. Perez, M. Gangnet, and A. Blake, "Poisson Image Editing," Proceedings of ACM SIGGRAPH, pp. 313-318, 2003.
[48]J. Jia, J. Sun, C. Tang, and H. Shum, "Drag and Drop Pasting," ACM Trans. Graph. (TOG), vol. 25(3), pp. 631-637, 2006.
[49]C. Lee, M. T. Schramm, M. Boutin and J. P. Allebach, "An Algorithm For Automatic Skin Smoothing In Digital Portraits," IEEE International Conference on Image Processing, pp. 3149-3152, 2009.
[50]L. Liang and L. Jin, "Facial Skin Beautification Using Region-Aware Mask," IEEE International Conference on Systems, Man, and Cybernetics, pp. 2922-2926, 2013.
[51]C. W. Chen, D. Y. Huang and C. S. Fuh, "Automatic Skin Color Beautification," Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, 2010.