A Novel NSCT based Illuminant Invariant Extraction with Optimized Edge Detection Technique for Face Recognition

A novel integrated approach for resolving the effect of illumination changes on face recognition is proposed. This face recognition system comprises feature extraction, feature selection and recognition. For feature extraction, a normal shrink filter in NSCT domain denoising technique is applied which produces illuminant invariant for the given image. In the second phase, to capture the important geometrical structures and to reduce the feature dimensionality Ant colony Optimization algorithm is performed. This combined approach fairly detects the edges with improved quality. Finally for recognition, a graph matching algorithm is employed. This algorithm utilizes a group of feature points to explore their geometrical relationship in a graph arrangement. While applying the entire method to the yaleB database, experimental results shows that the proposed work yields the best subset of features and provides a better solution for complex illumination problems.