Face detection in color images

TLDR

Human face detection plays an important role in applications such as video surveillance, human‑computer interface, face recognition, and face image database management. The study proposes a face detection algorithm for color images that works under varying lighting and complex backgrounds. The method uses a novel lighting compensation and nonlinear color transformation to detect skin regions, generates face candidates from their spatial arrangement, and verifies them with eye, mouth, and boundary maps. Experiments show the algorithm successfully detects faces across diverse color, position, scale, orientation, 3D pose, and expression variations in indoor and outdoor images.

Abstract

Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors).