Face Recognition of Enhanced Contrast Limited Adaptive Histogram Equalization using Feature Extraction Method
Thamizharasi A1, Jayasudha J.S2

1Thamizharasi A M.E., M.B.A., Research Scholar, Manonmaniam Sundaranar University, Abhishekapatti, Tirunelveli (Tamil Nadu), India.
2Dr Jayasudha J.S., Professor, Department of Computer Science & Engineering, SCT College of Engineering, Pappanamcode, Trivandrum (Kerala), India.

Manuscript received on 10 October 2016 | Revised Manuscript received on 18 October 2016 | Manuscript Published on 30 October 2016 | PP: 29-34 | Volume-6 Issue-1, October 2016 | Retrieval Number: A4737106116/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Face recognition is most widely useful for social networks and surveillance applications. Face recognition is complex if there are variations in light. The proposed work is to develop an illumination invariant face recognition system by enhancing Contrast Limited Adaptive Histogram Equalization (CLAHE). The face recognition of Enhanced CLAHE is done using feature extraction method. The features extracted are DWT statistical features, moments, texture, regional features, shape ratios, Fourier descriptors and facial features from Enhanced CLAHE images. These features are combined to create a feature vector. The feature vector is classified using Support Vector Machine (SVM) classifier and Multilayer Perceptron (MLP) neural network. The efficiency of feature vector is tested with three public face databases AR, Yale and ORL. The testing result proves that feature vector has high recognition accuracy rate.
Keywords: Face Recognition, CLAHE, Enhanced CLAHE, Feature Vector, Illumination Invariant, SVM And MLP Classifier.

Scope of the Article: Pattern Recognition