Selecting optimal orientations of Gabor wavelet filters for facial image analysis

Authors:
Tianqi Zhang;Bao-Liang Lu
Affiliations:
Dept. of Computer Sci. & Eng., Shanghai Jiao Tong University, Shanghai, China;Dept. of Computer Sci. & Eng., Shanghai Jiao Tong University, Shanghai, China and MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems, Shanghai Jiao Tong University, ...
Venue:
ICISP'10 Proceedings of the 4th international conference on Image and signal processing
Year:
2010

Citing 9
Cited 0

Gabor-Based Kernel PCA with Fractional Power Polynomial Models for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
On the Euclidean Distance of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
An adaptive image Euclidean distance

Pattern Recognition
Multi-view gender classification using local binary patterns and support vector machines

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Gabor parameter selection for local feature detection

IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part I
The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Independent component analysis of Gabor features for face recognition

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gabor wavelet-based methods have been widely used to extract representative features for face analysis. However, the existing methods usually suffer from high computational complexity of Gabor wavelet transform (GWT), and the Gabor parameters are fixed to a few conventional values which are assumed to be the best choice. In this paper we show that, for some facial analysis applications, the conventional GWT could be simplified by selecting the most discriminating Gabor orientations. In the selection process, we analyze the histogram of oriented gradient (HOG) of the average face image in a dataset, and eliminate the less significant orientation combinations. Then we traverse the rest combinations and select the best according to classification performance. We find that the selected orientations match the analysis of HOG well, and are therefore consistent with the intrinsic gradient characteristics of human face images. In order to assess the performance of the selected Gabor filters, we apply the proposed method to two tasks: face recognition and gender classification. The experimental results show that our method improves the accuracy of the classifiers and reduces the computation cost.