Fractal Model Based Face Recognition for Ubiquitous Environments

Authors:
Shuenn-Shyang Wang;Su-Wei Lin;Cheng-Ming Cho
Affiliations:
Department of Electrical Engineering, Tatung University, Taipei, Taiwan, R.O.C.;Department of Electrical Engineering, Tatung University, Taipei, Taiwan, R.O.C.;Department of Electrical Engineering, Tatung University, Taipei, Taiwan, R.O.C.
Venue:
UIC '08 Proceedings of the 5th international conference on Ubiquitous Intelligence and Computing
Year:
2008

Citing 8
Cited 0

Fundamentals of digital image processing

Fundamentals of digital image processing
An Analytic-to-Holistic Approach for Face Recognition Based on a Single Frontal View

IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards invariant face recognition

Information Sciences: an International Journal - methods and systems for intelligent human—computer interaction
Fractal Imaging

Fractal Imaging
A Real-life Test of Face Recognition System for Dialogue Interface Robot in Ubiquitous Environments

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Face recognition by fractal transformations

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Combination of projectional and locational decompositions for robust face recognition

AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures

Quantified Score

Hi-index	0.00

Visualization

Abstract

In Ubiquitous environments, it is required to identify the user in order to utilize the knowledge of the user's behavior and situation. In this paper, we propose a novel method of face recognition using dominant facial region extraction and fractal model. In order to improve the performance of the face recognition system, we propose an algorithm to extract the dominant facial region from the face images that includes the most discriminated part of the face, and for each dominant facial region it was presented by its fractal model and stored in database. The fractal model of the dominant facial region is then utilized as fractal facial features for face recognition. To further improve the performance of the face recognition system , we also propose the techniques of weighting mask and DC_Free MSE. Finally, some experimental results are presented and demonstrate the excellent performance of our face recognition approach.