學術產出-學位論文

題名 彩色影像中的人臉偵測
Face detection in Color Image
作者 李俊達
貢獻者 何瑁鎧
李俊達
關鍵詞 色彩空間
人臉偵測
特徵
color space
face detection
haar-like feature
日期 2006
上傳時間 17-九月-2009 14:07:04 (UTC+8)
摘要 本論文的目的是利用人臉在彩色影像中所提供的多色彩空間資訊,來達成在變異度較大的光源中即時偵測人臉的任務。彩色影像所擁有的原始RGB色彩資訊,經過轉化到正規RGB以及HSV (色調、飽合、明度)等色彩空間後,擁有對光源變化反應減緩的特性。以此特性為基礎,在4個選定的色彩空間中定義8種不同的類赫爾特徵(Haar-like feature),再利用推進演算法(Boosting algorithm)選出重要性最高的幾組特徵來進行對人臉的特徵。實驗結果顯示依此方法所產生的辨識器可在2點多秒內處理近百萬個次窗口(sub-window),並對光源變化有相當程度的抵抗力。
The main goal of this thesis is to detect human face under varying lighting condition by utilizing multiple color space information in real-time. Images of RGB color space can be converted into normalized RGB and HSV color spaces and thus reduce the interference of lighting condition. Base on this mechanism, we define 8 Haar-like features inside 4 selected color spaces, and then select the important features with boosting algorithm. Experimental results show that detectors constructed with our approach are able to process nearly one million sub-windows within 2.4 seconds, being robust to the changes of lighting conditions.
參考文獻 [1] Yoav Freund, Robert E. Schapire, “Experiments with a New Boosting Algorithm”, Machine Learning: Proceedings of the Thirteenth International Conference, 1996.
[2] Michael Oren , Constantine Papageorgiou, Pawan Sinha, Edgar Osuna, and Tomosa Poggio, “Pedestrian Detection Using Wavelet Templates”, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997.
[3] Paul Viola, Michael Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features”, 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001.
[4] Jie Yang, Weier Lu, and Alex Waibel, “Skin-Color Modeling and Adaptation”, Proceedings of the Third Asian Conference on Computer Vision-Volume II, 1998.
[5] Richard O. Duda, Peter E.Hart and David G.Stork, Pattern Classification Second Edition, Wiley – Interscience, 2001.
[6] Rein-Lien Hsu, Mohamed Abdel-Mottaleb, and Anil K. Jain, “Face Detection in Color Images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, May 2002.
[7] HD. Cheng, XH. Jiang Y. Sun, and Jing-Li Wang, “Color Image Segmentation: Advance & Prospects”, Pattern Recognition, Vol. 34: p. 2259-2281, 2001.
[8] Helman Stern, Boris Efros, "Adaptive Color Space Switching for Face Tracking in Multi-Colored Lighting Environments", Fifth IEEE International Conference on Automatic Face and Gesture Recognition, p. 0249, 2002.
[9] Vladimir Vezhnevets Vassili Sazonov Alla Andreeva, “A Survey on Pixel-Based Skin Color Detection Techniques”, Proceedings of Graphicon-2003, pp. 85-92 , 2003.
[10] W. Skarberk and A.Koschan, “Color Images Segmentation – a survey – “, Tech.rep., Institute for Technical Informatics, Technical University of Berlin, October 1994.
[11] Constantine P. Papageorgiou, Michael Oren, Tomaso Poggio, “A General Framework for Object Detection”, Proceedings of International Conference on Computer Vision, 1998.
[12] Rainer Lienhard and Jochen Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection”, Proceedings of the IEEE Conference on Image Processing (ICIP`02), September 2002.
[13] Rema Chellappa, Charles L. Wilson, Saad Sirohey, “Human and Machine Recognition of Faces: A Survey,” Proceedings of the IEEE, Vol.83, NO.5, May 1995.
[14] W. Zhao, R. Chellappa and A. Rosenfeld, P.J. Phillips, “Face Recognition: A Literature Survey,” Technical Report CAR-TR948, University of Maryland, 2000.
[15] Erik Hjelmas and Boon K. Low, “Face Detection, a Survey”, Computer Vision and Image Understanding 83, 236–274, 2001.
[16] Paul Viola and Michael J. Jones, “Robust Real-Time Face Detection”, International Journal of Computer Vision 57(2), p137-154, 2004.
[17] K. Sobottka and I.Pitas, “Looking for Faces and Facial Features in Color Image”, Pattern Recognition and Image Analysis: Advanced in Mathematical Theory and Applications, vol. 7, no. 1, 1996
[18] J. Barreto, P. Menezes, and J. Dias, “Human-robot Interaction Based on Haar-like Features and Eigenfaces,” in International Conference on Robotics and Automation, New Orleans, 2004
[19] M. Wimmer, B. Radig, “Adaptive Skin Color Classificator,” in Proc. of the first ICGST International Conference on Graphics, Vision and Image Processing GVIP-05, 2005
[20] Tilo Burghardt, Janko Ćalić, Barry T. Thomas, “Tracking Animals in Wildlife Videos Using Face Detection,” in European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology, October 2004
[21] Rafael C. Gonzalez, and Richard E. Woods, “Digital Image Processing”, 2nd Edition, Prentice Hall, 2001
[22] M.-H. Yang and N. Ahuja, "Detecting Human Faces in Color Images," in Proceedings of the International Conference on Image Processing, vol. 1, pp. 127--130, 1998.
描述 碩士
國立政治大學
資訊科學學系
91753036
95
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0917530363
資料類型 thesis
dc.contributor.advisor 何瑁鎧zh_TW
dc.contributor.author (作者) 李俊達zh_TW
dc.creator (作者) 李俊達zh_TW
dc.date (日期) 2006en_US
dc.date.accessioned 17-九月-2009 14:07:04 (UTC+8)-
dc.date.available 17-九月-2009 14:07:04 (UTC+8)-
dc.date.issued (上傳時間) 17-九月-2009 14:07:04 (UTC+8)-
dc.identifier (其他 識別碼) G0917530363en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/32714-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 91753036zh_TW
dc.description (描述) 95zh_TW
dc.description.abstract (摘要) 本論文的目的是利用人臉在彩色影像中所提供的多色彩空間資訊,來達成在變異度較大的光源中即時偵測人臉的任務。彩色影像所擁有的原始RGB色彩資訊,經過轉化到正規RGB以及HSV (色調、飽合、明度)等色彩空間後,擁有對光源變化反應減緩的特性。以此特性為基礎,在4個選定的色彩空間中定義8種不同的類赫爾特徵(Haar-like feature),再利用推進演算法(Boosting algorithm)選出重要性最高的幾組特徵來進行對人臉的特徵。實驗結果顯示依此方法所產生的辨識器可在2點多秒內處理近百萬個次窗口(sub-window),並對光源變化有相當程度的抵抗力。zh_TW
dc.description.abstract (摘要) The main goal of this thesis is to detect human face under varying lighting condition by utilizing multiple color space information in real-time. Images of RGB color space can be converted into normalized RGB and HSV color spaces and thus reduce the interference of lighting condition. Base on this mechanism, we define 8 Haar-like features inside 4 selected color spaces, and then select the important features with boosting algorithm. Experimental results show that detectors constructed with our approach are able to process nearly one million sub-windows within 2.4 seconds, being robust to the changes of lighting conditions.en_US
dc.description.tableofcontents CHAPTER 1 Introduction 1
1.1 Previous Detection Approaches 2
1.2 Proposed Approach 3
1.3 Organization of the Thesis 4
CHAPTER 2 Related Work 6
2.1 Haar-like Feature 6
2.2 Skin-Color Based Detection 6
2.3 Color Space 8
2.3.1 RGB 8
2.3.2 CMY and CMYK Color Space 9
2.3.3 HSV Color Space 11
2.3.4 Device-Independent Color Spaces 11
2.3.5 YUV YCrCb and YIQ Color Space 12
CHAPTER 3 Rectangle Feature 14
3.1 Feature Type 15
3.1.1 Haar-like Feature 15
3.1.2 DC Color Feature 16
3.2 Color Space 17
3.2.1 Normalized RGB Color Space 17
3.2.2 HSV Color Space 18
3.3 Proposed Feature 20
3.3.1 Rectangle Feature Set 20
3.3.2 Color Conversion 21
CHAPTER 4 Detection Framework 25
4.1 Weak Classification Function 25
4.2 AdaBoost Algorithm 27
4.3 Cascade Classifier 30
CHAPTER 5 System Framework 33
5.1 Rectangle Feature 34
5.2 Training Data 35
5.3 Weak Learner 36
5.4 Weak Classifier 36
5.5 Learning Algorithm 37
5.6 Strong Classifier 37
5.7 Cascade Classifier 38
CHAPTER 6 Experiment 40
6.1 Feature Definition 40
6.2 Implementation 41
6.2.1 Preprocessing 41
6.2.2 Cascade Construction 44
6.3 Detection Result 46
CHAPTER 7 Discussion And Conclusion 52
Reference 54
zh_TW
dc.format.extent 13362 bytes-
dc.format.extent 64348 bytes-
dc.format.extent 14177 bytes-
dc.format.extent 27796 bytes-
dc.format.extent 24014 bytes-
dc.format.extent 46488 bytes-
dc.format.extent 78653 bytes-
dc.format.extent 89633 bytes-
dc.format.extent 47504 bytes-
dc.format.extent 134849 bytes-
dc.format.extent 16497 bytes-
dc.format.extent 69478 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0917530363en_US
dc.subject (關鍵詞) 色彩空間zh_TW
dc.subject (關鍵詞) 人臉偵測zh_TW
dc.subject (關鍵詞) 特徵zh_TW
dc.subject (關鍵詞) color spaceen_US
dc.subject (關鍵詞) face detectionen_US
dc.subject (關鍵詞) haar-like featureen_US
dc.title (題名) 彩色影像中的人臉偵測zh_TW
dc.title (題名) Face detection in Color Imageen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] Yoav Freund, Robert E. Schapire, “Experiments with a New Boosting Algorithm”, Machine Learning: Proceedings of the Thirteenth International Conference, 1996.zh_TW
dc.relation.reference (參考文獻) [2] Michael Oren , Constantine Papageorgiou, Pawan Sinha, Edgar Osuna, and Tomosa Poggio, “Pedestrian Detection Using Wavelet Templates”, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997.zh_TW
dc.relation.reference (參考文獻) [3] Paul Viola, Michael Jones, “Rapid Object Detection using a Boosted Cascade of Simple Features”, 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001.zh_TW
dc.relation.reference (參考文獻) [4] Jie Yang, Weier Lu, and Alex Waibel, “Skin-Color Modeling and Adaptation”, Proceedings of the Third Asian Conference on Computer Vision-Volume II, 1998.zh_TW
dc.relation.reference (參考文獻) [5] Richard O. Duda, Peter E.Hart and David G.Stork, Pattern Classification Second Edition, Wiley – Interscience, 2001.zh_TW
dc.relation.reference (參考文獻) [6] Rein-Lien Hsu, Mohamed Abdel-Mottaleb, and Anil K. Jain, “Face Detection in Color Images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, May 2002.zh_TW
dc.relation.reference (參考文獻) [7] HD. Cheng, XH. Jiang Y. Sun, and Jing-Li Wang, “Color Image Segmentation: Advance & Prospects”, Pattern Recognition, Vol. 34: p. 2259-2281, 2001.zh_TW
dc.relation.reference (參考文獻) [8] Helman Stern, Boris Efros, "Adaptive Color Space Switching for Face Tracking in Multi-Colored Lighting Environments", Fifth IEEE International Conference on Automatic Face and Gesture Recognition, p. 0249, 2002.zh_TW
dc.relation.reference (參考文獻) [9] Vladimir Vezhnevets Vassili Sazonov Alla Andreeva, “A Survey on Pixel-Based Skin Color Detection Techniques”, Proceedings of Graphicon-2003, pp. 85-92 , 2003.zh_TW
dc.relation.reference (參考文獻) [10] W. Skarberk and A.Koschan, “Color Images Segmentation – a survey – “, Tech.rep., Institute for Technical Informatics, Technical University of Berlin, October 1994.zh_TW
dc.relation.reference (參考文獻) [11] Constantine P. Papageorgiou, Michael Oren, Tomaso Poggio, “A General Framework for Object Detection”, Proceedings of International Conference on Computer Vision, 1998.zh_TW
dc.relation.reference (參考文獻) [12] Rainer Lienhard and Jochen Maydt, “An Extended Set of Haar-like Features for Rapid Object Detection”, Proceedings of the IEEE Conference on Image Processing (ICIP`02), September 2002.zh_TW
dc.relation.reference (參考文獻) [13] Rema Chellappa, Charles L. Wilson, Saad Sirohey, “Human and Machine Recognition of Faces: A Survey,” Proceedings of the IEEE, Vol.83, NO.5, May 1995.zh_TW
dc.relation.reference (參考文獻) [14] W. Zhao, R. Chellappa and A. Rosenfeld, P.J. Phillips, “Face Recognition: A Literature Survey,” Technical Report CAR-TR948, University of Maryland, 2000.zh_TW
dc.relation.reference (參考文獻) [15] Erik Hjelmas and Boon K. Low, “Face Detection, a Survey”, Computer Vision and Image Understanding 83, 236–274, 2001.zh_TW
dc.relation.reference (參考文獻) [16] Paul Viola and Michael J. Jones, “Robust Real-Time Face Detection”, International Journal of Computer Vision 57(2), p137-154, 2004.zh_TW
dc.relation.reference (參考文獻) [17] K. Sobottka and I.Pitas, “Looking for Faces and Facial Features in Color Image”, Pattern Recognition and Image Analysis: Advanced in Mathematical Theory and Applications, vol. 7, no. 1, 1996zh_TW
dc.relation.reference (參考文獻) [18] J. Barreto, P. Menezes, and J. Dias, “Human-robot Interaction Based on Haar-like Features and Eigenfaces,” in International Conference on Robotics and Automation, New Orleans, 2004zh_TW
dc.relation.reference (參考文獻) [19] M. Wimmer, B. Radig, “Adaptive Skin Color Classificator,” in Proc. of the first ICGST International Conference on Graphics, Vision and Image Processing GVIP-05, 2005zh_TW
dc.relation.reference (參考文獻) [20] Tilo Burghardt, Janko Ćalić, Barry T. Thomas, “Tracking Animals in Wildlife Videos Using Face Detection,” in European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology, October 2004zh_TW
dc.relation.reference (參考文獻) [21] Rafael C. Gonzalez, and Richard E. Woods, “Digital Image Processing”, 2nd Edition, Prentice Hall, 2001zh_TW
dc.relation.reference (參考文獻) [22] M.-H. Yang and N. Ahuja, "Detecting Human Faces in Color Images," in Proceedings of the International Conference on Image Processing, vol. 1, pp. 127--130, 1998.zh_TW