Gender and ethnicity identification from silhouetted face profiles

This paper demonstrates, to our best knowledge, the first attempt on gender and ethnicity identification from silhouetted face profiles using a computer vision technique. The results achieved, after testing on 441 images, show that silhouetted face profiles have a lot of information, in particular, for ethnicity identification. Shape context based matching [1] was employed for classification. The test samples were multi-ethnic. Average accuracy for gender was 71.20% and for ethnicity 71.66%. However, the accuracy was significantly higher for some classes, such as 83.41% for females (in case of gender identification) and 80.37% for East and South East Asians (in case of ethnicity identification).

[1]  Paul A. Viola,et al.  A unified learning framework for real time face detection and classification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[2]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[3]  Kenneth Steiglitz,et al.  Combinatorial Optimization: Algorithms and Complexity , 1981 .

[4]  A. J. O'toole,et al.  Classifying faces by face and sex using an autoassociative memory trained for recognition , 1991 .

[5]  Ming-Hsuan Yang,et al.  Learning Gender with Support Faces , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Xun Xu,et al.  Building Large Scale 3D Face Database for Face Analysis , 2007, MCAM.

[7]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[9]  Nicolas Davidenko.  Silhouetted face profiles: a new methodology for face perception research. , 2007, Journal of vision.

[10]  Sushil J. Louis,et al.  Genetic feature subset selection for gender classification: a comparison study , 2002, Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings..

[11]  J. Meinguet.  Multivariate interpolation at arbitrary points made simple , 1979 .

[12]  Gender aftereffects in face silhouettes reveal face-specific mechanisms , 2008 .

[13]  Terrence J. Sejnowski,et al.  SEXNET: A Neural Network Identifies Sex From Human Faces , 1990, NIPS.

[14]  Felix A. Wichmann,et al.  Gender Classification of Human Faces , 2002, Biologically Motivated Computer Vision.

[15]  V Bruce,et al.  Perceiving the sex and race of faces: the role of shape and colour , 1995, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[16]  Brunelli Poggio,et al.  HyberBF Networks for Gender Classification , 1992 .

[17]  Laurenz Wiskott,et al.  Phantom faces for face analysis , 1997, Proceedings of International Conference on Image Processing.

[18]  A. M. Burton,et al.  Sex Discrimination: How Do We Tell the Difference between Male and Female Faces? , 1993, Perception.

[19]  Xun Xu,et al.  SODA-Boosting and Its Application to Gender Recognition , 2007, AMFG.

[20]  Amit Jain,et al.  Integrating independent components and linear discriminant analysis for gender classification , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[21]  D. Perrett,et al.  What Gives a Face its Gender? , 1993, Perception.

[22]  Anil K. Jain,et al.  Multimodal Facial Gender and Ethnicity Identification , 2006, ICB.

[23]  Shaogang Gong,et al.  Fusing gait and face cues for human gender recognition , 2008, Neurocomputing.

[24]  Harry Wechsler,et al.  Mixture of experts for classification of gender, ethnic origin, and pose of human faces , 2000, IEEE Trans. Neural Networks Learn. Syst..

[25]  Mohammed Yeasin,et al.  Support Vector Learning for Gender Classification Using Audio and Visual Cues , 2003, Int. J. Pattern Recognit. Artif. Intell..

[26]  Anil K. Jain,et al.  Ethnicity identification from face images , 2004, SPIE Defense + Commercial Sensing.