Illumination compensation algorithm based on quadratic polynomial model

Authors:
Wang Jian;Zhao Honglian;Liu Bing;Wang Dezhuang
Affiliations:
Northeastern University, Computer Architecture Institute, Shenyang;Northeastern University, Computer Architecture Institute, Shenyang; ;
Venue:
CCDC'09 Proceedings of the 21st annual international conference on Chinese Control and Decision Conference
Year:
2009

Citing 8
Cited 0

Adaptive histogram equalization and its variations

Computer Vision, Graphics, and Image Processing
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Interpretation and Coding of Face Images Using Flexible Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust image based 3d face recognition

Robust image based 3d face recognition
Illumination Normalization for Robust Face Recognition Against Varying Lighting Conditions

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
The CMU Pose, Illumination, and Expression Database

IEEE Transactions on Pattern Analysis and Machine Intelligence
Total Variation Models for Variable Lighting Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces for recognition

Journal of Cognitive Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

Face detection and recognition technologies have a wide range of applications, while varying illumination typically make these technologies perform poorly. The illumination variations heavily affect the effectiveness of face visualization and face recognition. The novelty in this paper is that quadratic polynomial model is applied to illumination compensation. Experimental results demonstrate that the proposed algorithm performs well not only in weakening illumination effect but also in improving the face recognition rates. From the experiments, we can find that face recognition rate can reach 99.17%, and the visualization effectiveness of images is greatly improved.