Face location in non-uniform illumination conditions using dynamic thresholds, lighting normalization and weighting mask function

Authors:
Chiunhsiun Lin;Ching-Hung Su
Affiliations:
National Taipei University, Taipei, Taiwan;The Department of Electronic Engineering, Lunghwa University of Science and Technology, Taoyuan County, Taiwan
Venue:
CEA'07 Proceedings of the 2007 annual Conference on International Conference on Computer Engineering and Applications
Year:
2007

Citing 3
Cited 0

Digital Image Processing

Digital Image Processing
A probabilistic hit-and-miss transform for face localization

Pattern Analysis & Applications
A hierarchical neural network for human face detection

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a robust and efficient human face location system that uses dynamic thresholds, lighting normalization and a weighting mask function to locate the human face embedded in photographs with non-uniform illumination conditions is presented. The designed system is composed of two principal parts: The first part is to use dynamic thresholds to obtain a satisfied binary image, and then to search the potential face regions based on the rules of "the combination of two eyes and one mouth". The second part of the proposed system is to perform the face verification task by a lighting normalization function and a weighting mask function. The experimental results reveal that the proposed method is better than previous methods in non-uniform illumination conditions.