成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	吳匡鎮 Wu, Kuang-Zhen
論文名稱：	基於自適性布斯特演算法及膚色資訊的新型人臉偵測法 A Novel Face Detection Method based on Adaboost Algorithm and Skin Color Information
指導教授：	賴源泰 Lai, Yen-Tai
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2010
畢業學年度：	98
語文別：	英文
論文頁數：	84
中文關鍵詞：	人臉偵測、膚色偵測、自適性布斯特演算法
外文關鍵詞：	face detection, skin color detection, Adaboost algorithm
相關次數：	點閱：124 下載：0
分享至:	分享至facebook 分享至twitter

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

在本論文中，除了實現迅速、且高準確度的自適性布斯特人臉偵測演算法外，針對高準確率所伴隨而來的高誤判率，採取了預先對偵測圖片作膚色偵測的處理來對應。藉由這樣的預處理方式，不但過濾掉圖片中大部份不需要被偵測的部份，減少了誤判出現的可能性，還可藉此先行準確掌握可能含有人臉的膚色區塊之位置及大小，使偵測人臉所用的子視窗能僅在恰當區域動作，減少計算量及運算時間。因此在膚色偵測法的選擇中，我們謹慎選定數種近年常被採用的膚色偵測法，以結果加以比較，最後採用YCgCr色域來制定膚色範圍。對於其過濾後的圖像，再施行自適性布斯特演算法來偵測人臉，可以得到相當滿意的實驗結果。與原本的自適性布斯特人臉偵測法相比，誤判率降低了幾近20%。

In this thesis, we implement the rapid and high correct rate face detection method based on Adaboost algorithm. Unfortunately, high correct rate always follows high false detection r-ate. Therefore, we find out the skin color pixels of entire image. By this way, we can remo-ve the most parts of the image which don’t need to be detected in order to reduce the false detection rate. We also can get the location and size of skin regions which may include the faces to make the detect sub-window working in suitable area to achieve the lower comput-ation and time consumption. For purpose of finding the best skin color detection manner, we chose several methods which have been used these years and observing their results. In the end, we choose the YCgCr space to formulate the range of skin color. Applying Adaboost detection method on the image that has been pre-detected the skin color in the next step and brings out the satisfying low false detection rate. Compare to the original Adaboost detection method, our false detection rate decreases approximately 20% .

ABSTRACT
CONTENTS
LIST OF FIGURES
LIST OF TABLES
Chapter 1  Introdution...................................1
1	Background.......................................1
2	The Motivation...................................2
3	Organization of The Thesis.......................3

Chapter 2  Background Knowledge..........................4
1	Evolution of Face Detection Research.............4
2	Knowledge-Based Methods..........................4
3	Template Matching Methods........................6
3.1	Predefined Templates.............................6
3.2    Deformable Templates............................8
4	Feature-Based Methods............................8
4.1	Facial Features..................................8
4.2    Texture.........................................9
4.3	Skin Color.......................................9
4.4	Multiple Features...............................10
5	Appearance-Based Methods........................10
5.1	Bayesian Classification.........................11
5.2	Eigenfaces......................................12
5.3	Principal Component Analysis....................12
5.4	Neural Networks.................................13
5.5	Support Vector Machines.........................14
5.6	Hidden Markov Model.............................15

Chapter 3  Adaboost Algorithm...........................17
1	Summary of Adaboost Algorithm...................17
2	Haar-type Features..............................18
3	Integral Image..................................19
4	Adaboost Learning Algorithm.....................21
5	The Cascaded Classifier.........................24

Chapter 4  Skin Color Detection.........................28
1	Review of Skin Color Detection..................28
2	Color Spaces....................................29
2.1	Basic Color Spaces..............................30
2.2	Perceptual Color Spaces.........................31
2.3	Orthogonal Color Spaces.........................32
2.4	Perceptually Uniform Color Spaces...............32
3	Skin-Color Classiﬁcation........................32
3.1	Explicitly Deﬁned Skin Region...................33
3.2	Normalized Lookup Table.........................33
3.3	Bayes Classiﬁer.................................34
3.4	Self Organizing Map.............................35
3.5	Single Gaussian.................................35
3.6	Mixture of Gaussians............................36
3.7	Elliptic Boundary Model.........................36
4	Illumination Adaptation Approaches..............37
4.1	Gray World Algorithm............................38
4.2	White Patch Approach............................39

Chapter 5  Face Detection Algorithm Implementation and Results.................................................40
1	The Process of Face Detection Algorithm.........40
2	Compensation for Varying Illumination Colors....41
3	Skin Color Regions Detection....................44
3.1	Using Combination Color Spaces..................44
3.2	Eliminating Over-dark Pixels Method.............47
3.3	YCgCr Color Space...............................50
3.4	Gaussian Model..................................54
3.5	Elliptic Boundary Model.........................56
4	Face Candidate Regions Segmentation.............60
4.1	Morphological Operation.........................60
4.2	Remain Suitable Regions.........................61
4.3	Reduce Face Detection Scope.....................62
5	Adaboost Training...............................64
6	Experiment Results..............................71

Chapter 6  Conclusion...................................81

References..............................................82

                                    

[1] T. Sakai, M. Nagao, and T. Kanade,“Computer analysis and classiﬁcation of photographs of human faces”, First USA—Japan Computer Conference, pp.27, 1972

[2] R. Chellappa, C. L. Wilson, and S. Sirohey.“Human and machine recognition of faces : A survey”, Proc. IEEE, vol. (83), pp.705-741, 1995.

[3] Erik Hjelmås and Boon Kee Low, “Face Detection: A survey”, Computer Vision and Image Understanding, vol. 83(3), pp. 236-274, 2001.

[4] M.-H. Yang, D. J. Kriegman and N. Ahuja, “Detecting Faces in Images: A Survey”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24(I), pp. 34-58, 2002.

[5] G. Yang and T. S. Huang, “Human Face Detection in Complex Background”, Pattern Recognition, vol.27, no.1, pp.53-63, 1994.

[6] B. Scassellati, “Eye Finding via Face Detection for a Foevated, Active Vision System”, Proc. 15th Nat’l Conf. Artificial Intelligence, 1998.

[7] A. Yuille, P. Hallinan, and D. Cohen, “Feature Extraction from Faces Using Deformable Templates”, Int’l J. Computer Vision, vol. 8, no. 2, pp. 99-111, 1992.

[8] M.F. Augusteijn and T.L. Skujca, “Identification of Human Faces through Texture Based Feature Recognition and Neural Network Technology”, Proc. IEEE Conf. Neural Networks, pp. 392-398, 1993.

[9] Wei Sun; Weigong Zhang; Xiaorui Zhang; Gang Chen; Chengxu Lv, “Multi-feature Fusion Method of Driver Face Location Based on Area Coincidence Degree and Prior Knowledge ”, PACCS '09, pp.431-434, 2009.

[10] Ikeda O., “Segmentation of faces in video footage using HSV color for face detection and image retrieval”, International Conference on Image Processing, vol. 2, pp. III-913-6, 2003.

[11] R. L. Hsu, M. Abdel-Mottaleb, AK Jain., “Face detection in color images”, IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 696-706, 2002.

[12] Aziz K., A. A.; Ramlee R.A.; Abdullah S.S.; Jahari A.N., “Face Detection Using Radial Basis Function Neural Networks with Variance Spread Value ”, International Conference of Soft Computing and Pattern Recognition, Page(s): 399 – 403, 2009

[13] Nefian A.V., Hayes M.H., “Maximum likelihood training of the embedded HMM for face detection and recognition ”, Proc. IEEE Conf. Image Processing, vol.1, pp. 33-36, 2000.

[14] P. Viola, M. Jones, “Robust real-time face detection”, International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.

[15] Lienhart R., Liang L. and Kuranov A., “A Detector Tree of Boosted Classifiers for Real-time Object Detection and Tracking”, Microcomputer Research Labs, Intel Corperation, Santa Clara, CA., vol. 2, pp.II-277-80, 2003.

[16] P. Kakumanu, S. Makrogiannis, N. Bourbakis,"A Survey of Skin-Color Modeling and Detection Methods", Pattern Recognition 40, pp.1106-1122, 2007.

[17] V. Vezhnevets and V. Sazonov and A. Andreeva,“A survey on pixel-based skin color detection techniques”, 13th International Conference on the Computer Graphics and Vision, 2003.

[18] J. J. de Dios, N. Garcia, “Face detection based on a new color space YCgCr”, ICIP03, vol.2, pp. III-909-12, 2003.

[19] Chai D. and Bouzerdoum A., “A bayesian approach to skin color classiﬁcation in ycbcr color space”, In Proceedings IEEE Region Ten Conference (TENCON’2000), vol. 2, pp. 421–424, 2000.

[20] LEE J. Y., and YOO S. I. , “An elliptical boundary model for skin color detection”, In Proc. of International Conference on Imaging Science, Systems, and Technology, 2002.

[21] J. Kovac, P. Peer, F. Solina, “Human skin color clustering for face detection”, EUROCON2003, vol.2, pp. 144-148, 2003.

[22] B. Wang, X. Chang, C. Liu, “A Robust Method for Skin Detection and Segmentation of Human Face”, Second International Conference on Intelligent Networks and Intelligent Systems, pp. 290-293, 2009

[23] Jati H., and Dominic D., “Human skin detection using defined skin region”, International Symposium on Information Technology, vol. 1, pp. 1-4, 2008.

[24] Zhang Z. and Shi Y., “Skin color detecting unite YCgCb color space with YCgCr color space”, International Conference on Image Analysis and Signal Processing, pp. 221-225, 2009.

[25] W.-H. Lai and C.-T. Li, “Skin Colour-Based Face Detection in Colour Images”, IEEE International Conference on Video and Signal Based Surveillance, pp. 56, 2006

[26] Jensen, O. H., “Implementing the Viola-Jones face detection algorithm”, MSc thesis, Technical University of Denmark, 2008.

[27] H. Sajedi, M. Jamzad, “A contourlet-based face detection method in color images”, Proceedings – International Conference on Signal Image Technologies and Internet Based Systems, pp. 727–732, 2007.

校內：2020-01-01公開
校外：不公開電子論文尚未授權公開，紙本請查館藏目錄

簡易檢索 / 詳目顯示

相關論文