Face Detection in the Near-IR Spectrum

摘要

Face detection is an important prerequisite step for successful face recognition. The performance of previous face detection methods reported in the literature is far from perfect and deteriorates ungracefully where lighting conditions cannot be controlled. We propose a method that outperforms state-of-the-art face detection methods in environments with stable lighting. In addition, our method can potentially perform well in environments with variable lighting conditions. The approach capitalizes upon our near-IR skin detection method reported elsewhere [Proceedings IEEE Workshop on Computer Vision beyond the Visible Spectrum: Methods and Applications; 2000, IEEE Trans. Int. Trans. Sys.; vol. 1; 72–85]. It ascertains the existence of a face within the skin region by finding the eyes and eyebrows. The eye–eyebrow pairs are determined by extracting appropriate features from multiple near-IR bands. Very successful feature extraction is achieved by simple algorithmic means like integral projections and template matching. This is because processing is constrained in the skin region and aided by the near-IR phenomenology. The effectiveness of our method is substantiated by comparative experimental results with the Identix face detector [http://www.faceit.com].