A new feature extraction based on advanced PCA for real time face recognition

Author

Mahdi, Samira ; Menhaj, M.B. ; Hormat, A.M.

Author_Institution

Dept. of Electr., Comput. & Biomed. Eng., Islamic Azad Univ., Qazvin, Iran

fYear

2013

fDate

27-29 Aug. 2013

Firstpage

1

Lastpage

7

Abstract

Face recognition is an important and challenging task in machine vision. In this paper, we present a new method for feature extraction in the face recognition field. Firstly, each image in the training set is divided into a finite number of small parts. After that all parts of images merged together in one set, the K-means method is then applied over the set to obtain K clusters based on which a proper dictionary is constructed. High level features for face images are obtained by employing PCA on this dictionary. A robust face recognition system is developed based on multilayer perceptron neural networks (MLPs) and support vector machine (SVM) by imposing these features as the inputs. Experimental results easily show high accuracy of the system in terms of the correct recognition rate of 91% with low error rate and low computational complexity as well.

Keywords

computational complexity; face recognition; feature extraction; multilayer perceptrons; pattern clustering; principal component analysis; support vector machines; K clusters; K-means method; MLP; PCA; SVM; computational complexity; dictionary; error rate; face images; feature extraction; high level features; machine vision; multilayer perceptron neural networks; real time face recognition; recognition rate; robust face recognition system; support vector machine; Face Recognition; Multilayer perceptron neural network (MLPs); Support Vector Machine (SVM); principal component analysis (PCA);

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems (IFSC), 2013 13th Iranian Conference on

Conference_Location

Qazvin

Print_ISBN

978-1-4799-1227-8

Type

conf

DOI

10.1109/IFSC.2013.6675690

Filename

6675690