Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Overview of the Face Recognition Grand Challenge
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Preliminary Face Recognition Grand Challenge Results
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple Face Model of Hybrid Fourier Feature for Large Face Image Set
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Journal of Cognitive Neuroscience
Score normalization in multimodal biometric systems
Pattern Recognition
Robust coding schemes for indexing and retrieval from large face databases
IEEE Transactions on Image Processing
Comparison of tensor unfolding variants for 2DPCA-based color facial portraits recognition
ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
Hi-index | 0.00 |
This paper presents a horizontal and vertical 2D principal component analysis (2DPCA) based discriminant analysis (HVDA) method for face verification. The HVDA method, which derives features by applying 2DPCA horizontally and vertically on the image matrices (2D arrays), achieves high computational efficiency compared with the traditional PCA and/or LDA based methods that operate on high dimensional image vectors (1D arrays). The HVDA method further performs discriminant analysis to enhance the discriminating power of the horizontal and vertical 2DPCA features. Finally, the HVDA method takes advantage of the color information across two color spaces, namely, the YIQ and the YCbCr color spaces, to further improve its performance. Experiments using the Face Recognition Grand Challenge (FRGC) version 2 database, which contains 12,776 training images, 16,028 controlled target images, and 8,014 uncontrolled query images, show the effectiveness of the proposed method. In particular, the HVDA method achieves 78.24% face verification rate at 0.1% false accept rate on the most challenging FRGC experiment, i.e., the FRGC Experiment 4 (based on the ROC III curve).