(3.80.6.131) 您好!臺灣時間:2021/05/14 03:08
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:葉蕙綺
研究生(外文):Hui-Chi,Yeh
論文名稱:基於輪廓與幾何性質以定位人臉側面特徵
論文名稱(外文):Identifying Facial Profile Features Based on Contours and Geometric Properties
指導教授:楊士萱楊士萱引用關係
指導教授(外文):Shih-Hsuan Yang
口試委員:張寶基郭天穎
口試日期:2016-07-21
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:資訊工程系研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
畢業學年度:104
語文別:中文
中文關鍵詞:主動形狀模型側面人臉輪廓擷取臉部特徵擷取
外文關鍵詞:Active Shape Model (ASM)Facial ProfileContour ExtractionFacial Feature Extraction
相關次數:
  • 被引用被引用:0
  • 點閱點閱:173
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:14
  • 收藏至我的研究室書目清單書目收藏:0
人臉特徵點在生活中有著廣泛的應用,如人臉辨識、人臉追蹤、醫學美容、和建構人臉3D模型等;而這些應用的實現,都依賴精確的人臉特徵點位置。雖然現今已經有一些自動人臉特徵點定位技術,如主動形狀模型(Active Shape Model)與主動外觀模型(Active Appearance Model)等,但是這些技術都需要預先定義並訓練特徵模型,而且多數僅用於正臉,對於側臉特徵點定位的效果不佳。本論文的目標,在於免去事前訓練特徵模型的繁雜手續,而又能正確有效的定位出側面人臉特徵點;我們也開發出一套醫美應用軟體,提供醫師診療的參考資訊。
本研究依據自適性膚色擷取出人臉側面輪廓,再依照人臉側面輪廓的幾何特性,如斜率、曲率、或局部最凸(凹)點等,定位出目標特徵點,包括眉心、鼻根、鼻尖、鼻翼下緣、上唇、嘴唇中心、下唇、下巴尖點、頦下線點、與頦頸點等;我們也將人臉正面與側面的特徵點相互對應,以輔助定位在視覺上比較不明顯的正臉特徵點。實驗結果顯示,本論文提出的方法能夠快速而準確的定位出側面輪廓上的特徵點。如果特徵點位置的容錯門檻值設定為6像素,平均準確度可達90.2%,而且執行的時間少於1秒。
In daily life facial landmarks have found wide and increasing applications inclusing face recognition, face tracking, aesthetic medicine, and 3D facial model construction. Realization of these application relies on accurate facial landmark locations. Although automatic feature point extraction techniques such as the Active Shape Model (ASM) and Active Appearance Model (AAM) have been developed, these techniques require training on a pre-defined landmark model and they are mostly applied only to frontal faces. Few and poor results have been reported for automatic locating landmarks in profile faces. This thesis aims to accurately and efficiently locate the landmarks of profile faces without the complicated training process. We also hope to develop an aesthetic medicine software package to help doctors diagnose.
The proposed method extracts the outline of a face image in the sagital view based on the adaptive skin color. Geometric characteristics of the outline contour such as the slope, curvature, or local maximum (minimum), are used to locate the target landmarks including the glabella, nasion, nose tip, subnasale, labrale superius, stomion, labrale inferius, pogonion, menton, and cervical point. By matching the corresponding landmarks in the frontal and profile faces, deviated landmarks positions in the frontal face are corrected. Experimental results show that the proposed method can fast and accurately locate the landmarks of a profile face. The average accuracy of feature point locations is 90.2% under a 6-pixel error tolerance with processing time less than one second.
摘 要 i
ABSTRACT ii
誌 謝 iv
目 錄 v
表目錄 viii
圖目錄 ix
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 論文架構 3
第二章 相關背景知識 4
2.1 人臉特徵點在醫學美容之應用 4
2.2 偵測人臉常用之影像特徵 8
2.2.1 Haar-like特徵 8
2.2.2 LBP特徵 9
2.3 色彩空間 9
2.3.1 RGB色彩空間 10
2.3.2 HSV色彩空間 10
2.3.3 YCbCr色彩空間 11
2.3.4 色彩空間比較與選定 12
2.4 正臉特徵點定位相關文獻 13
2.5 主動形狀模型(Active Shape Model) 14
2.5.1 樣本訓練 15
2.5.2 特徵點正規化 16
2.5.3 主成分分析(Principle Component Analysis) 17
2.5.4 局部灰階模型 18
2.5.5 預估初始形狀模型位置 19
2.5.6 形狀模型匹配 20
2.6 側面特徵點定位相關文獻 21
第三章 研究方法 24
3.1 演算法流程 24
3.2 擷取側面人臉區域 25
3.2.1 側臉偵測 25
3.2.2 修正人臉區域 26
3.3 背景移除 29
3.3.1 邊緣偵測 29
3.3.2 形態學處理與區域合併 30
3.3.3 背景遮罩 32
3.4 自適性膚色偵測 33
3.4.1 建立橢圓模型 35
3.4.2 橢圓形膚色偵測 37
3.5 側面人臉邊緣輪廓 38
3.6 側面特徵點定位 39
3.6.1 鼻尖點 40
3.6.2 下巴尖點 41
3.6.3 頦下線點與頦頸點 42
3.6.4 鼻翼下緣點 44
3.6.5 鼻根點與眉心點 45
3.6.6 嘴唇點 46
3.7 正面與側面臉部特徵點對應 48
3.7.1 正面特徵點定位 49
3.7.2 特徵點對應 50
第四章 實驗結果與分析 51
4.1 實驗環境 51
4.1.1 軟硬體設備 51
4.1.2 測試影像資料庫 51
4.2 實驗測試方法 54
4.2.1 特徵點誤差計算方法 54
4.2.2 手動標記正確特徵點 54
4.3 特徵點定位結果 57
4.4 正面與側面特徵點對應結果 58
4.5 特徵點準確度分析 59
4.5.1 受測者誤差統計 61
4.5.2 特徵點誤差統計 66
4.5.3 特徵點誤差佔臉長比例統計 67
4.6 實驗數據分析 70
第五章 結論與未來工作 70
5.1 結論 70
5.2 未來工作 71
參考文獻 72
[1]“Wikipedia 人臉識別,” https://zh.wikipedia.org/wiki/人臉識別
[2]Marc S. Zimbler and Jongwook Ham, “AESTHETIC FACIAL ANALYSIS,” Cummings Otolaryngology: Head and Neck Surgery, CHAPTER 21, 2004.
[3]“Digital Image Fundamentals - Introduction to Signal and Image Processing,” https://miac.unibas.ch/SIP/02-Fundamentals.html
[4]“Wikipedia talk:YCbCr,” http://en.wikipedia.org/wiki/Talk%3AYCbCr.
[5]“Wikipedia HSL and HSV,” http://en.wikipedia.org/wiki/HSL_and_HSV
[6]Paul Viola, and Michael Jones, “Rapid object detection using a boosted cascade of simple features”. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.1, pp.I-511-I-518, 2001.
[7]Rainer Lienhart, and Jochen Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection”. Image Processing. 2002. Proceedings. 2002 International Conference on vol.1, pp.I-900-I-903, 2002.
[8]T. Ojala and M. Pietikainen.” Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Trans on Pattern Analysis and Machine Intelligence, Vol. 24. No.7, July, 2002
[9]甘家澤,基於彩色及深度影像之台灣手語互動學習系統,碩士論文,國立中台北科技大學資訊工程研究所,2014。
[10]Cootes Timothy, and Christopher Taylor,“Active shape models—‘smart snakes’.” BMVC92. Springer London, pp. 266-275, 1992.
[11]T. F. Cootes; G. J. Edwards; C. J. Taylor., “Active Appearance Models.” In European Conference on Computer Vision, volume 2, pages 484–498, 1998.
[12]D. Cristinacce and T. Cootes. “Feature detection and tracking with constrained local models.” In British Machine Vision Conference, volume 3, pages 929–938, 2006.
[13]“The MUCT landmarked face database,” http://www.milbo.org/muct
[14]“Wikipedia Procrustes_analysis,” https://en.wikipedia.org/wiki/Procrustes_analysis
[15]Stasm. http://www.milbo.users.sonic.net/stasm/
[16]余幸娟,適用於唇形辨識之改良式主動形狀模型匹配演算法,碩士論文,國立中央大學資訊工程研究所,2010。
[17]Andera Bottino and Sandro Cumani, “Robust identification of face landmarks in profile images,” in Proceedings of the 12th WSEAS international conference on Computers, pp. 107-114, 2008.
[18]Ricardo Teles Freitas, Kelson Rômulo Teixeira Aires and Victor Eulálio Sousa Campelo “Locating Facial Landmarks towards Plastic Surgery”. 28th SIBGRAPI Conference on Graphics, Patterns and Images, pp. 219 – 225, 2015.
[19]X. Zhu and D. Ramanan, “Face detection, pose estimation, and landmark localization in the wild,” in IEEE Conference on Computer Vision and Pattern Recognition, pp. 2879 – 2886, 2012.
[20]Shengcai Liao, Xiangxin Zhu, Zhen Lei, Lun Zhang, Stan Z. Li, “Learning Multi-scale Block Local Binary Patterns for Face Recognition,” ICB07 Proceedings of the 2007 international conference on Advances in Biometrics, pp. 828-837, 2007.
[21]John Canny, “A computational approach to edge detection,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.679-698,1986
[22]“Canny Edge Detector”
http://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector.html
[23]“Wikipedia Flood fill,”https://en.wikipedia.org/wiki/Flood_fill
[24]H. Tang and Z. Feng, “Hand’s Skin Detection Based on Ellipse Clustering,” in Computer Science and Computational Technology, ISCSCT 08. International Symposium on Volume:2, pp. 758 – 761,2008.
[25]Rein-Lien Hsu, M. Abdel-Mottaleb, A. K. Jain, “Face detection in color images”. IEEE Transactions on Pattern Analysis and Machine Intelligence. vol.24 ,pp.696-706, 2002.
[26]劉怡廷,使用膚色與深度資訊改良主動形狀模型以擷取人臉特徵,碩士論文,國立中台北科技大學資訊工程研究所,2015。
[27]“OpenCV 2.4.10 Structural Analysis and Shape Descriptors” http://www.swarthmore.edu/NatSci/mzucker1/opencv-2.4.10-docs/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html
[28]“Dr. James Pearson Facial Plastic Surgery Blog,”
http://www.southbayfacialplasticsurgery.com/2013/02/chin-enhancement/
[29]“Wikipedia Ramer–Douglas–Peucker algorithm,”
https://en.wikipedia.org/wiki/Ramer%E2%80%93Douglas%E2%80%93Peucker_algorithm
[30]“Peter Peer, CVL Face Database,” http://www.lrv.fri.uni-lj.si/facedb.html
[31]“Psychological Image Collection at Stirling (PICS),” http://pics.psych.stir.ac.uk/2D_face_sets.htm
[32]“Stirling/ESRC 3D Face Database,” http://pics.stir.ac.uk/ESRC/2d_images.htm
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔