IEEE Transactions on Pattern Analysis and Machine Intelligence
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Local Binary Patterns as an Image Preprocessing for Face Authentication
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
An image preprocessing algorithm for illumination invariant face recognition
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Enhanced local texture feature sets for face recognition under difficult lighting conditions
AMFG'07 Proceedings of the 3rd international conference on Analysis and modeling of faces and gestures
Illumination invariant face recognition in logarithm discrete cosine transform domain
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
A comparison of photometric normalisation algorithms for face verification
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Multi-scale local binary pattern histograms for face recognition
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Hi-index | 0.00 |
Face recognition under varying lighting conditions remains an unsolved problem. In this work, a new photometric normalisation method based on local Discrete Cosine Transform in the logarithmic domain is proposed. The method is experimentally evaluated and compared with other algorithms, achieving a very good performance with a total error rate very similar to that produced by the preprocessing sequence, which is the best performing state of the art photometric normalisation algorithm. An in-depth analysis of both methods revealed notable differences in their behaviour. This diversity is exploited in a multiple classifier fusion framework to achieve further performance improvement.