Face Detection Based on Central Geometrical Moments of Face Components

Abstract

This paper presents a face detection framework based on up to the third-order two-dimensional central geometrical moments (CGMs) of face components and their horizontal and vertical gradients. To detect faces in an image an exhaustive search over space and scale is carried out by using a multistage classifier which quickly discards background regions and spends more computation on promising face-like regions. A new method for fast computation of up to the third-order local geometrical moments, suitable for sliding window applications is presented whose computational complexity is invariant to scale and is much faster compared to previous methods for PC-based applications. The presented results show that the proposed system yields good performance in terms of detection and false positive rates.