GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms
Abstract
Boosted cascade of simple features, by Viola and Jones, is one of the most famous object detection frameworks. However, it suffers from a lengthy training process. This is due to the vast features space and the exhaustive search nature of Adaboost. In this paper we propose GAdaboost: a Genetic Algorithm to accelerate the training procedure through natural feature selection. Specifically, we propose to limit Adaboost search within a subset of the huge feature space, while evolving this subset following a Genetic Algorithm. Experiments demonstrate that our proposed GAdaboost is up to 3.7 times faster than Adaboost. We also demonstrate that the price of this speedup is a mere decrease (3%, 4%) in detection accuracy when tested on FDDB benchmark face detection set, and Caltech Web Faces respectively.
Keywords
Cite
@article{arxiv.1609.06260,
title = {GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms},
author = {Mai Tolba and Mohamed Moustafa},
journal= {arXiv preprint arXiv:1609.06260},
year = {2016}
}
Comments
8th International Conference on Evolutionary Computation Theory and Applications (ECTA 2016). Final paper will appear at the SCITEPRESS Digital Library