Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Reasoning Models for Face Recognition
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
The CMU Pose, Illumination, and Expression Database
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian face recognition using Gabor features
WBMA '03 Proceedings of the 2003 ACM SIGMM workshop on Biometrics methods and applications
Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Machine Learning (Adaptive Computation and Machine Learning)
Introduction to Machine Learning (Adaptive Computation and Machine Learning)
Journal of Cognitive Neuroscience
Rough neural fault classification of power system signals
Transactions on rough sets VIII
Face recognition under varying lighting conditions using self quotient image
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
| Hi-index | 0.00 |
In this paper we are presenting an illumination invariant face recognition system that will be able to identify the facial images under varying range of illumination of (azimuth, elevation) (+120-65 and -120+65). The main focus of this work is to address the problem of variations in illumination through the strength of the rough sets to recognize the faces under varying illumination. The proposed approach consists of three major parts, namely, illumination normalization, feature extraction and recognition procedure. Illumination normalization part utilizes the existing approaches for illumination normalization based on a mathematical model called rough membership function (rmf) illumination classifier. After normalizing the illumination, geometrical features are extracted and feature vector is formed using the geometrical relations between facial fiducial points. Finally, in recognition part feature vectors of training images are given as input to approximation-decider neuron network (ADNN). The efficiency and robustness of the proposed system are demonstrated on data set of significant size and are compared with state of the art classifier techniques. Our recognizer has achieved 93.56% accuracy for Yale database and 85% accuracy for CMU-PIE database in recognizing the facial images with different types of illumination.