A New Unsupervised Approach to Face Recognition

Authors:
Zizhu Fan;Ergen Liu
Affiliations:
School of Natural Science, East China Jiaotong University, Nanchang, China 330013;School of Natural Science, East China Jiaotong University, Nanchang, China 330013
Venue:
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Year:
2008

Citing 9
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Support Vector Machines to Enhance the Performance of Elastic Graph Matching for Frontal Face Authentication

IEEE Transactions on Pattern Analysis and Machine Intelligence
Principal Manifolds and Probabilistic Subspaces for Visual Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Alignment by maximization of mutual information

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
2D and 3D face recognition: A survey

Pattern Recognition Letters
A comparative study of Minimax Probability Machine-based approaches for face recognition

Pattern Recognition Letters
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Face recognition using a fuzzy fisherface classifier

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new unsupervised approach to face recognition is proposed in this paper. Shape and color entropy is presented to descript face features. Firstly, images are pre-processed including face normalization and image segmentation and so on. Secondly, by using the information entropy theory, the method defines the color and shape entropy of the face images, respectively. Finally, an integrated similarity measurement framework is presented by computing mutual information between images according to these entropies. Compared with other methods of feature description, experiments indicate that this approach is more effective and efficient.