簡易檢索 / 詳目顯示

研究生: 龔興東
SING-DONG GONG
論文名稱: 自動臉部特徵偵測整容系統
Face-off: Automatic Alteration of Facial Features
指導教授: 楊傳凱
Chuan-Kai Yang
口試委員: 項天端
Tien-Ruey Hsiang
鮑興國
Hsing-Kuo Kenneth Pao
學位類別: 碩士
Master
系所名稱: 管理學院 - 資訊管理系
Department of Information Management
論文出版年: 2008
畢業學年度: 96
語文別: 中文
論文頁數: 50
中文關鍵詞: 無縫貼圖布阿松影像編輯
外文關鍵詞: Scene Analysis, Poisson Image Editing, Facial Feature Detection
相關次數: 點閱:201下載:7
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 愛美是每個人追求及維持的目標,隨著環境的變遷,交通的進步,人與人之間的距離越來越接近,社交應酬也逐漸頻繁,外表給別人的第一印象變得相對的重要,特別是臉部給人的印象更加深刻,但單靠化粧品是不夠的,許多人開始選擇去整容來改變自己的外表。然而,具有侵入性及高成本的整容手術讓人望之卻步,深怕一旦做了手術,結果卻無法達到期望,甚至花上大量的時間與金錢,為了避免這樣的事情發生,最好的方法就是讓使用者在整容前可以預先看到整容後的結果,所見即所得的結果才會讓使用者接受整容手術。
    在這篇論文中,我們提出一個自動偵測臉部特徵的整容系統,使用者可以載入一張自己的照片,經過臉部特徵辨別後,分出不同的特徵,再從特徵資料庫中挑選自己喜歡的特徵,系統便會自動進行整容,並將整容後的結果輸出。為了自動的取出臉部特徵,我們使用了一系列的辨別方式來去判斷特徵的位置。另外,Perez等人提出利用Poisson Equation來處理無縫貼圖的圖像編輯,將輸入影像能夠無縫地貼到目標影像上,在這篇論文中,我們使用Perez等人等提出的方法將特徵無縫地貼至欲整容的人臉上。
    為了讓使用者在選擇特徵時有所差異,在個別特徵放到特徵資料庫時,我們會做特徵點的擷取,並用所取出的特徵點判斷其分類,在這篇論文中,我們簡單地將特徵分成了幾類,讓使用者可以有更多元的選擇


    Pursuing or maintaining beautifulness has nowadays become a trend in modern society, especially among the celebrity community. In some cases, one may choose to adopt drastic procedures to alter his or her facial or body features to achieve the desired beauty, thus the blossom of industry on cosmetic plastic surgeries.
    However, as performing the related surgeries are still considered intrusive and costly, it is better to preview the result before a surgery is actually carried out. As many believe that facial appearance matters most, we have developed a system that not only offers the previewing functionality, but also allows users to interactively fine-tune the desired results, thus making our system a useful companion tool for facial cosmetic surgeries.
    While existing tools generally entail manual effort to locate or align facial features, our system, characterized by a scheme of automatic feature extraction, eliminates the need of user assistance. Furthermore, for convenience, we have constructed a database of facial features to facilitate the facial alteration process.
    In addition to demonstrating the rendered results to justify our claims, we also believe that our framework could also find its use in other applications as well. For example, our system could help to create an avatar of arbitrary facial appearance, and such functionality would be very welcome for today's IM (instant messaging) tools, such as MSN or Skype.

    目錄索引 第一章 緒論..............................................................................................................1 1.1 前言.............................................................................................................1 1.2 研究動機.....................................................................................................1 1.3 研究目的.....................................................................................................2 第二章 文獻探討......................................................................................................4 2.1 無縫貼圖技術.............................................................................................4 2.2 臉部特徵偵測技術.....................................................................................6 2.3 系統界面.....................................................................................................8 2.4 Face-Off.....................................................................................................9 第三章 臉部特徵偵測及整容.................................................................................10 3.1 臉部特徵偵測整容系統流程圖................................................................11 3.2 人臉辨識方法............................................................................................12 3.3 特徵擷取方法............................................................................................13 3.3.1眼睛特徵擷取方法..........................................................................13 3.3.2嘴巴特徵擷取方法..........................................................................16 3.3.3鼻子特徵擷取方法..........................................................................17 3.3.4眉毛特徵擷取方法..........................................................................19 3.4 Face Off with Poisson Image Editing..........................................................21 3.4.1特徵的抹除......................................................................................23 第四章 臉部特徵分類.............................................................................................24 4.1臉部特徵分類....................................... .....................................................24 4.2眼睛特徵分類....................................... .....................................................25 4.2.1眼睛特徵分類方法.................. .......................................................26 4.3鼻子特徵分類....................................... .....................................................28 4.3.1鼻子特徵分類方法.................. .......................................................29 4.4嘴巴特徵分類....................................... .....................................................31 4.4.1嘴巴特徵分類方法.................. .......................................................32 4.5眉毛特徵分類....................................... .....................................................34 4.5.1眉毛特徵分類方法.................. .......................................................35 第五章 實驗結果.....................................................................................................37 5.1實驗環境.....................................................................................................37 5.2特徵資料庫.................................................................................................37 5.3實作語言.....................................................................................................37 5.4系統界面與展示.........................................................................................38 5.5實驗結果.....................................................................................................43 第六章 結論與未來展望.........................................................................................47 參考文獻...................................................................................................................49

    [1]Leyvand, T., Cohen-Or, D., Dror, G., Lischinski, D., Digital Face Beautification. ACM SIGGRAPH 2006, 2006.
    [2]Kjeldsen, R., Kender, J., Finding Skin in Color Images. In FG’ 96(2nd International Conference on Automatic Face and Gesture Recognition), 1996.
    [3]Perez, P., Gangnet, M., Blake, A., Poisson image editing. Proceedings of ACM SIGGRAPH, 313–318, 2003.
    [4]Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A., Graphcut Textures: Image and Video Synthesis Using Graph Cuts, ACM Trans. Graph. (TOG) 22(3):277-286, 2003.
    [5]Levin, A., Zomet, A., Peleg, S., Weiss, Y., Seamless Image Stitching in the Gradient Domain. ECCV 2004:377-389, 2004.
    [6]Jia, J., Sun, J., Tang C., Shum, H., Drag-and-Drop Pasting. ACM Trans. Graph. (TOG) 25(3):631-637, 2006.
    [7]Yang, M., Kriegman, D. J., Ahuja, N., Detecting Faces in Images: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 1 (2002), 34-58, 2002.
    [8]Lin, C.H., Wu, J.L., Automatic facial feature extraction by genetic algorithms. IEEE Transactions on Image Processing (TIP) 8(6):834-845, 1999.
    [9]Gu, H., Su, G., Du, C., Feature Points Extraction from Faces. In Image and Vision Computing NZ, 2003.
    [10]Lalonde, J., Hoiem, D.A., Efros, A., Rother, C., Winn, J., Criminisi, A., Photo Clip Art. In SIGGRAPH '2007, 2007.
    [11]Agarwala, A., Interactive Digital Photomontage. In SIGGRAPH ‘2004, pp.294-302, 2004.
    [12]Blanz , V., Scherbaum, K., Vetter, T., Seidel, H., Exchanging Faces in Images. In Eurographics ‘2004, 2004.
    [13]Eisenthal, Y., Dror,G., Ruppin, E. Facial Attractiveness: Beauty and the Machine. Neural Comput. 18, 1, 2006.
    [14]Leyvand, T., Cohen-Or, D., Dror, G., Lischinski, D., Data-Driven Enhancement of Facial Attractiveness. SIGGRAPH ‘2004, 2004.

    QR CODE