A study on face detection and gender recognition 趙翊傑、林國祥
E-mail: [email protected]
ABSTRACT
In this paper, we proposed a system to simultaneously achieve face detection and gender recognition based on color and geometrical features. The proposed face detection algorithm is composed of face candidate localization and face region verification. We first use a color feature, skin color, to coarsely localize these face candidate regions. Moreover, we detect eyes and calculate the geometrical properties among them to select the possible eye pairs. Therefore, we can detect face regions by combing the face regions and eye pairs. As for gender recognition, we extract useful features from the result of face detection. These features contain skin and lip color information. Based on the extracted features and a trained classifier, we can identify the gender information of each testee in an image. Experimental results show that our proposed system can achieve not only face detection but also gender recognition.
Keywords : Face detection、Eye pair detection、Skin color detection、Gender recognition Table of Contents
封面內頁 簽名頁 中文摘要iv ABSTRACTv 誌謝vi 目錄vii 圖目錄ix 表目錄xiii 第一章緒論1 1.1 研究動機1 1.2 系統概要1 1.3 人臉偵測相關技術3 1.3.1 人臉偵測困難之處4 1.4 性別辨識相關技術4 1.4.1 性別辨識困難之處5 第二章人臉偵測6 2.1 人臉偵 測之系統架構6 2.2 相關技術討論7 2.2.1 色彩空間7 2.2.2 標記連通成分10 2.2.3 數學形態學之Dilation與 Erosion運算11 2.2.4 區域填充11 2.3 膚色偵測12 2.4 眼睛配對偵測13 2.4.1 人眼區域偵測14 2.4.2 眼睛配對篩選17 2.5 人臉區域驗證19 第三章性 別辨識22 3.1 性別辨識之系統架構22 3.2 SVM簡介與原理23 3.3 人臉方位校正24 3.4 嘴唇偵測26 3.5 特徵擷取30 第四章實驗 結果與分析33 4.1 系統執行環境與定義評估標準33 4.2 人臉偵測35 4.3 性別辨識49 第五章結論與未來研究方向52 5.1 結論52 5.2 未來研究方向52 參考文獻54 附錄57
REFERENCES
[1]J.-S. Jang and J.-H. Kim, “Fast and robust face detection using evolutionary pruning, ” IEEE Transactions on Evolutionary Computation, Vol. 12, No. 5, pp. 562–571, 2008.
[2]P. S. Hiremath and A. Danti, “Detection of Multiple Faces in an Image Using Skin Color Information and Lines-of-Separability Face Model,
” International Journal of Pattern Recognition and Artificial Intelligence, Vol. 20, No. 1, pp. 39–61, 2006.
[3]Chin-Chung Han, Hong-Yuan Mark Liao, Kuo-Chung Yu, and Liang-Hua Chen, “Fast Face Detection Via Morphology-based Pre-processing,” Pattern Recognition, Vol. 33, pp.1701–1712, 2000.
[4]L. Goldmann, U. J. Monich, and T. Sikora, “Components and Their Topology for Detection in the Presence of Partial Occlusions,” IEEE Transactions on Information Forensics and Security, Vol.2, No.3, Sep, pp. 559–569, 2007.
[5]M. Turkan, M. Pardes, and A.E. Cetin, “Edge Projections for eye localization,” Optical Engineering, Vol. 47, pp. 047007-1–047007-6, 2008.
[6]Olugbenga Ayinde, and Yee-Hong Yang, “Region-Based Face Detection,” Pattern Recognition, Vol. 35, pp. 2095–2107, 2002.
[7]S. Hayashi and O. Hasegawa, “A Detection Technique for Degraded Face Images,” Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Vol. 2, pp. 1506–1512, 2006.
[8]L. Zhao, X. Sun, and X. Xu, “Face detection based on facial features,” Proceedings of the International Conference on Signal Processing, Vol.3, Nov, pp. 16–20, 2006.
[9]M. Hassaballah and Shun Ido, “Eye Detection Using Intensity and Appearance Information,” IAPR Conference on Machine Vision Applications, pp. 20–22, May, 2009.
[10]Huynh Nguyen Duy Nhan, Pham The Bao, “A New Approach to Mouth Detection Using Neural Network,” International Conference on Computer Analysis of Images and Petterns, pp.616–619, 2009.
[11]J. G. Wang and T. N. Tan, “A new face detection method based on shape information,” Pattern Recognition Letters, Vol. 21, pp. 463 –471, 2000.
[12]S. Buchala, T. M. Gale, N. Davey, R. J. Frank, and K. Foley, “Global and Feature Based Gender Classification of Faces: A comparison of human performance and computational models,” Progress in Neural Processing, Vol. 16, pp. 349–360, 2005.
[13]Zheng Ji, Xiao-Chen Lian, and Bao-Liang Lu, “Gender Classification by Information Fusion of Hair and Face,” State of the Art in Face Recognition [14]Md. Geaur Rahman, Md. Aotab Hossain, Dipankar Das, and Md. Khademul Islam Molla, “Gender Identification System from Facial Image Using Artificial Neural Network,” Proceeding of the International Conference On Computer and Information Technology, pp. 19 –21, 2003.
[15]S. Campanella, A. Chrysochoos, and R. Bruyer, “Categorical Perception of Facial Gender Information :Behavioural Evidence and The Face-Space Metaphor,” Visual Cognition, Vol. 8, pp. 237–262, 2001.
[16]T. Kawano, K. Kato and K. Yamamoto, “An Analysis of the Gender and Age Differentiation Using Facial Parts,” IEEE International Conference on Systems, Vol. 4, pp. 3432–3436, 2005.
[17]Prinshul Jain, Automatic Gender Identification System, Department of Computer Science and Engineering Indian Institute of Technology Kanpur, 2008.
[18]K. Ramesha, K. B. Raja, K. R. Venugopal, and L. M. Patnaik, “Feature Extraction based Face Recognition, Gender and Age,”
International Journal on Computer Science and Engineering, Vol. 2, No.01S, pp. 14–23, 2010.
[19]R. C. Gonzalez and R. E.Wood, Digital Image Processing, Second edition, Addison Wesley.
[20]C. C. Chang and C. J. Lin, “LIBSVM: A library for support vector machine,” http://www.csie.ntu.edu.tw/~cjlin/libsvm/, 2003.
