A Real-time Model for Multiple Human Face Tracking from Low-resolution Surveillance Videos

Abstract

This article discusses a novel approach of multiple-face tracking from low-resolution surveillance videos. There has been significant research in the field of face detection using neural-network based training. Neural network based face detection methods are highly accurate, albeit computationally intensive. Hence neural network based approaches are not suitable for real-time applications. The proposed approach approximately detects faces in an image solely using the color information. It detects skin region in an image and finds existence of eye and mouth region in the skin region. If it finds so, it marks the skin region as a face and fits an oriented rectangle to the face. The approach requires low computation and hence can be applied on subsequent frames from a video. The proposed approach is tested on FERET face database images, on different images containing multiple faces captured in unconstrained environments, and on frames extracted from IP surveillance camera.