Welcome to the InfoSci Platform
Reference Hub2
On the Generalization Power of Face and Gait in Gender Recognition

On the Generalization Power of Face and Gait in Gender Recognition

Yu Guan, Xingjie Wei, Chang-Tsun Li
Copyright: © 2014 |Volume: 6 |Issue: 1 |Pages: 8
ISSN: 1941-6210|EISSN: 1941-6229|EISBN13: 9781466653474|DOI: 10.4018/ijdcf.2014010101
Cite Article Cite Article

MLA

Guan, Yu, et al. "On the Generalization Power of Face and Gait in Gender Recognition." IJDCF vol.6, no.1 2014: pp.1-8. http://doi.org/10.4018/ijdcf.2014010101

APA

Guan, Y., Wei, X., & Li, C. (2014). On the Generalization Power of Face and Gait in Gender Recognition. International Journal of Digital Crime and Forensics (IJDCF), 6(1), 1-8. http://doi.org/10.4018/ijdcf.2014010101

Chicago

Guan, Yu, Xingjie Wei, and Chang-Tsun Li. "On the Generalization Power of Face and Gait in Gender Recognition," International Journal of Digital Crime and Forensics (IJDCF) 6, no.1: 1-8. http://doi.org/10.4018/ijdcf.2014010101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.