4 March 2015 Gender classification in low-resolution surveillance video: in-depth comparison of random forests and SVMs
Author Affiliations +
Abstract
This research considers gender classification in surveillance environments, typically involving low-resolution images and a large amount of viewpoint variations and occlusions. Gender classification is inherently difficult due to the large intra-class variation and interclass correlation. We have developed a gender classification system, which is successfully evaluated on two novel datasets, which realistically consider the above conditions, typical for surveillance. The system reaches a mean accuracy of up to 90% and approaches our human baseline of 92.6%, proving a high-quality gender classification system. We also present an in-depth discussion of the fundamental differences between SVM and RF classifiers. We conclude that balancing the degree of randomization in any classifier is required for the highest classification accuracy. For our problem, an RF-SVM hybrid classifier exploiting the combination of HSV and LBP features results in the highest classification accuracy of 89.9 0.2%, while classification computation time is negligible compared to the detection time of pedestrians.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Christopher D. Geelen, Rob G. J. Wijnhoven, Gijs Dubbelman, Peter H. N. de With, "Gender classification in low-resolution surveillance video: in-depth comparison of random forests and SVMs", Proc. SPIE 9407, Video Surveillance and Transportation Imaging Applications 2015, 94070M (4 March 2015); doi: 10.1117/12.2077079; https://doi.org/10.1117/12.2077079
PROCEEDINGS
14 PAGES


SHARE
Back to Top