Robust hand detection

Abstract

Vision-based hand gesture interfaces require fast and extremely robust hand detection. Here, we study view-specific hand posture detection with an object recognition method proposed by Viola and Jones. Training with this method is computationally very expensive, prohibiting the evaluation of many hand appearances for their suitability to detection. In this paper, we present a frequency analysis-based method for instantaneous estimation of class separability, without the need for any training. We built detectors for the most promising candidates, their receiver operating characteristics confirming the estimates. Next, we found that classification accuracy increases with a more expressive feature type. Lastly, we show that further optimization of training parameters yields additional detection rate improvements. In summary, we present a systematic approach to building an extremely robust hand appearance detector, providing an important step towards easily deployable and reliable vision-based hand gesture interfaces.