Square patch feature based face detection architecture for high resolution smart camera

Abstract

Recognizing faces in a crowd in real-time is a key feature which would significantly enhance Intelligent Surveillance Systems. Previously we proposed a high resolution smart camera system that can be used for crowd surveillance. The challenge is with the increasing speed and resolution of the image sensors, a fast and robust face detection system is required for real time operation. In this paper, we proposed a face detection architecture that is suitable to be implemented on a smart camera system. The face detection algorithm is based on a new weak classifier type that we called square patch feature. The targeted platform is a low cost Spartan-3 FPGA. From The simulation result shows that the proposed face detection architecture could speed up the equivalent software based face detector up to 12 times. Parallelizing the feature classification modules could improve the performance further.

Development and Implementation of a New Dynamic Face Detection Operator

“…However, the integral image generation (needed by this method) requires important computation tasks and is associated with a long latency delay [7]. A solution to this problem was proposed by Mustaphah in [8]. It consists in reducing the region of interest (ROI) to only the moving skin region by using background subtraction and skin color detection.…”