Home > IJIPVS > Vol. 1 > Iss. 2 (2012)
International Journal of Image Processing and Vision Science
Article Title
FACE RECOGNITION IN EIGEN DOMAIN WITH NEURO-FUZZY CLASSIFIER AND EVOLUTIONARY OPTIMIZATION
Abstract
Face Recognition is a nascent field of research with many challenges. The proposed system focuses on recognizing faces in a faster and more accurate way using eigenface approach and genetic algorithm by considering the entire problem as an optimization problem. It consists of two stages: Eigenface approach is used for feature extraction and genetic algorithm based feed forward Neuro-Fuzzy System is used for face recognition. Classification of face images to a particular class is done using an artificial neural network. The training of neural network is done using genetic algorithm, a machine learning approach which optimizes the weights used in the neural network. This is an efficient optimization technique and an evolutionary classification method. The algorithm has been tested on 200 images (20 classes). A recognition score for test lot is calculated by considering almost all the variants of feature extraction. Test results gave a recognition rate of 97.01%.
Recommended Citation
R. S, PRASANTH. and R, SARITHA.
(2012)
"FACE RECOGNITION IN EIGEN DOMAIN WITH NEURO-FUZZY CLASSIFIER AND EVOLUTIONARY OPTIMIZATION,"
International Journal of Image Processing and Vision Science: Vol. 1
:
Iss.
2
, Article 12.
Available at:
https://www.interscience.in/ijipvs/vol1/iss2/12