On the Generalization Power of Face and Gait in Gender Recognition

Human face/gait-based gender recognition has been intensively studied in the previous literatures, yet most of them are based on the same database. Although nearly perfect gender recognition rates can be achieved in the same face/gait dataset, they assume a closed-world and neglect the problems caused by dataset bias. Real-world human gender recognition system should be dataset-independent, i.e., it can be trained on one face/gait dataset and tested on another. In this paper, the authors test several popular face/gait-based gender recognition algorithms in a cross-dataset manner. The recognition rates decrease significantly and some of them are only slightly better than random guess. These observations suggest that the generalization power of conventional algorithms is less satisfied, and highlight the need for further research on face/gait-based gender recognition for real-world applications.

[1]  Mark S. Nixon,et al.  On a Large Sequence-Based Human Gait Database , 2004 .

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[5]  Tieniu Tan,et al.  Robust view transformation model for gait recognition , 2011, 2011 18th IEEE International Conference on Image Processing.

[6]  Ja-Ling Wu,et al.  Real-time Gender Classification from Human Gait for Arbitrary View Angles , 2009, 2009 11th IEEE International Symposium on Multimedia.

[7]  Tieniu Tan,et al.  A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

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

[9]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[10]  Jun Li,et al.  Dense SIFT and Gabor descriptors-based face representation with applications to gender recognition , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[11]  Melike Akkaraca Köse.  Telecommunications Interception in Turkey: Rights to Privacy vs. Discourses of Security , 2011 .

[12]  Sudeep Sarkar,et al.  The humanID gait challenge problem: data sets, performance, and analysis , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Michael A. Caloyannides.  Digital "Evidence" is Often Evidence of Nothing , 2006 .

[14]  Bir Bhanu,et al.  Individual recognition using gait energy image , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Manimurugan Shanmuganathan,et al.  Secure and Efficient Medical Image Transmission by New Tailored Visual Cryptography Scheme with LS Compressions , 2015, Int. J. Digit. Crime Forensics.

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

[17]  Wei Qi Yan,et al.  Attack Graph Analysis for Network Anti-Forensics , 2014, Int. J. Digit. Crime Forensics.

[18]  Tieniu Tan,et al.  A Study on Gait-Based Gender Classification , 2009, IEEE Transactions on Image Processing.

[19]  A. Martínez,et al.  The AR face databasae , 1998 .

[20]  Panagiotis Kanellis,et al.  Digital Crime And Forensic Science in Cyberspace (N/A) , 2006 .

[21]  Bok-Min Goi,et al.  Vision-based Human Gender Recognition: A Survey , 2012, ArXiv.

[22]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[23]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  Xuelong Li,et al.  Gait Components and Their Application to Gender Recognition , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[25]  Shumeet Baluja,et al.  Boosting Sex Identification Performance , 2005, International Journal of Computer Vision.