臺灣博碩士論文加值系統

隨著現在科技的進步，交友軟體也越來越多，所以照片給人的第一印象是非常重要的，大部分的交友軟體，如果想要吸引人的注目，往往照片的呈現就決定了成敗。目前市面上販售的數位相機或是智慧型手機上的APP軟體都具有美肌的功能，但普遍的做法都是直接淡化整張照片讓顯眼的痘疤消失，而這樣的做法只能針對較小的痘疤有效，並無法移除較大面積的痘疤或是傷疤。因此，我們這篇論文主要的貢獻就是使用者可以自行的更換膚色，再更換膚色的同時就可以達到除疤的效果。

為了要讓膚色多元化，於是我們利用網路搜尋各種明星的膚色來建立我們的膚色資料庫。除了使用者可以自行更換喜愛的膚色外，我們也有自動配對膚色的功能，可以從我們的資料庫中選出一組與使用者輸入的照片最相近的膚色套用上去。讓使用者能保有原本的膚色樣貌，而不會有太大的差異，從我們的實驗結果中，我們成功的將臉上的疤痕完全去掉，並且提供使用者能夠自由的更換膚色，讓原本的樣貌有了各種不同的效果。

This paper presents a novel system to remove facial scars and pores for a portrait. The facial skin complexion and colors are important attractive factors, and most people consider that a good portrait should be scar free and have smooth facial colors.

Currently, most available commercial digital cameras or smart phones all provide facial-skin-beatification functions, but most of them only use simple image processing functions to smooth the taken image for the removal of small-scale unwanted facial scars and pores and these functions cannot remove large and obvious scars or pores from the face.

Therefore, the main contribution of this system allows the user to replace the facial skin of a portrait with a beautiful and scar-less skin of another portrait chosen from a collected database which consists of scar-less and beautiful faces from webs.

中文摘要 i
Abstract ii
誌謝 iii
Table of Contents iv
表目錄 vi
圖目錄 vii
Chapter1 Introduction 1
1.1 研究背景與動機 1
1.2 相關研究 2
1.3 論文架構 5
1.4 系統架構 6
Chapter2 人臉辨識介紹 7
2.1 ASM(Active Shape Model) 7
2.2 局部切割偵測 9
2.2.1 輪廓偵測 11
2.2.2 五官偵測 14
2.3 人臉切割分類 16
Chapter3 資料庫建置 17
3.1 SLIC(Simple linear iterative clustering) Feature Extraction 17
3.2 Bicubic Patch Construction 20
3.3 建立膚色資料庫 22
Chapter4 膚色重建 24
4.1 臉部膚色對應 24
4.2 TPS(Thin Plate Spline) 24
4.3 Poisson Image Editing 26
4.4 Color Transfer Between Images 30
4.5 人臉膚色偵測 31
4.6 五官變形 33
Chapter5 實驗結果與討論 36
Chapter6 Conclusion 43
參考文獻 44

[1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal
Fua, and S Sabine. SLIC Superpixels. ep
technical report 149300, (June),
2010.
[2] K. Arakawa and K. Nomoto. A system for beautifying face images using
interactive evolutionary computing. 2005 International Symposium on
Intelligent Signal Processing and Communication Systems, pages 9{12, 2005.
[3] TF Cootes and CJ Taylor. Active shape models-their training and
application. Computer vision and . . . , 61, 1995.
[4] Yael Eisenthal, Gideon Dror, and Eytan Ruppin. Facial attractiveness:
beauty and the machine. Neural computation, 18(1):119{42, January 2006.
[5] Xavier Hilaire and Karl Tombre. Robust and accurate vectorization of line
drawings. IEEE transactions on pattern analysis and machine intelligence,
28(6):890{904, June 2006.
[6] Takeo Igarashi and John F Hughes. As-Rigid-As-Possible Shape
Manipulation. 2005.
[7] Takuya Okada Kaoru Arakawa. -Separating Nonlinear Filter Bank and Its
Application to Face Image Beautification.pdf, 2006.
[8] P. Soille L. Vincent. Watersheds in digital spaces-An efficient algorithm based
on immersion simulations.pdf. IEEE Transactions on Pattern Analysis and
Machine Intelligence, 1991.
[9] Gregory Lecot and Bruno Levy. Ardeco : Automatic Region DEtection and
COnversion. Eurographics Symposium on Rendering, 2006.
[10] Tommer Leyvand, Daniel Cohen-Or, Gideon Dror, and Dani Lischinski.
Digital face beautification. ACM SIGGRAPH 2006 Sketches on - SIGGRAPH
'06, page 169, 2006.
[11] Tommer Leyvand, Daniel Cohen-Or, Gideon Dror, and Dani Lischinski.
Data-driven enhancement of facial attractiveness. ACM Transactions on
Graphics, 27(3):1, August 2008.
[12] Takashi Matsui, Kaoru Arakawa, and Kohei Nomoto. A Nonlinear Filter
System for Beautifying Face Images with Enhancement Using Interactive
Evolutionary Computing. 2006 International Symposium on Intelligent Signal
Processing and Communications, pages 534{537, December 2006.
[13] Patrick Perez, Michel Gangnet, and Andrew Blake. Poisson image editing.
ACM SIGGRAPH 2003 Papers on - SIGGRAPH '03, page 313, 2003.
[14] Erik Reinhard, Michael Ashikhmin, Bruce Gooch, Peter Shirley, and Simon
Pre. Color Transfer between Images. Computer Graphics and Applications,
IEEE, 21(October):34{41, 2001.
[15] Carsten Rother, V Kolmogorov, and Andrew Blake. Grabcut: Interactive
foreground extraction using iterated graph cuts. ACM Transactions on
Graphics (TOG), 1(212):309{314, 2004.
[16] Tian Xia, Binbin Liao, and Yizhou Yu. Patch-based image vectorization with
automatic curvilinear feature alignment. ACM Transactions on Graphics,
28(5):1, December 2009.
[17] Jian Yang, David Zhang, Yong Xu, and Jing-yu Yang. Recognize Color Face
Images Using Complex Eigenfaces. Springer Berlin Heidelberg, pages 64{68,
2005.
[18] Ju Jia Zout and Hong Yant. Cartoon Image Vectorization Based on Shape
Subdivision. Proceeding CGI '01 Computer Graphics International 2001,
pages 225{231, 2006.