Gabor-Based kernel fisher discriminant analysis for pose discrimination

Authors:
Jiada Chen;Jianhuang Lai;Guocan Feng
Affiliations:
Center of Computer Vision, Sun Yat-sen University;Center of Computer Vision, Sun Yat-sen University;Center of Computer Vision, Sun Yat-sen University
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 5
Cited 0

3-D Facial Pose and Gaze Point Estimation Using a Robust Real-Time Tracking Paradigm

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
3D Deformable Face Model for Pose Determination and Face Synthesis

ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Face recognition by elastic bunch graph matching

ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Face Recognition Based on Fitting a 3D Morphable Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Gabor-Based Kernel PCA with Fractional Power Polynomial Models for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel Gabor-based Kernel Fisher Discriminant Analysis (KFDA) method to determine human pose under depth rotation (out of the image plane) Specially, the capability of different orientation and size of Gabor Filter is discussed and the optimal one is selected for feature representation Then KFDA with fractional power polynomial models leads to a non-linear projection to meet the non-linear depth rotation of human face In the experiment section, we can see that, the correct classification rate of 93.5% is achieved in MIT database.