Face Recognition using Feed Forward Neural Network
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2015, Vol 17, Issue 5
Abstract
Abstract: In this paper, we propose four techniques for extraction of facial features namely 2DPCA, LDA, KPCA and KFA. The purpose of face feature extraction is to capture certain discriminative features that are unique for a person. In the previous works that uses PCA for face feature extraction involves merging the features and reducing the dimensions that results in some information loss. To overcome this problem, in the first method we used 2D-PCA for face feature extraction, LDA for making class labels and FFNN for face recognition. Similarly we used the three more techniques namely LDA, KPCA and KFA for face feature extraction and then FFNN for face recognition.The proposed method is tested on the ORL database. Results involve the comparison of face recognition rate of the different feature extraction techniques with FFNN using 10, 20, 30 and 40 hidden neurons. The results on ORL database shows that FFNN with 30 hidden neurons performs best by extracting features using KPCA.
Authors and Affiliations
Pooja Rani
Keywords
Related Articles
- EP ID EP153548
- DOI -
- Views 82
- Downloads 0
Effective Cancer Detection Using Soft Computing Technique
Abstract: Cancer research is rudimentary research which is done to identify causes and develop strategies forprevention, diagnosis, treatment and cure. An optimized solution for the better treatment of cancer and t...
An innovative scheme for representation of signed numbers employing ternary logic and method of development of semiconductor optical amplifiers based wavelength encoded optical ternary half adder
Abstract: In binary logic, two different logical states are used to represent signed as well as unsigned numbers. In case of signed numbers one bit, usually the Most Significant Bit is solely devoted to represent the sig...
Performance Evaluation of HTTP and DB Traffic Application Using Proactive and Reactive Routing Protocols
Abstract: A group of fixed or mobile communication devices that does not have a stable infrastructure to communicate with each other is known as mobile ad-hoc network. In MANET their is very importent role of nodes...
Application Newton methods in the reduction of the problem of optimal control of a boundary value problem.
The article presents a generalized continuation of the parameter and Newton methods for solving nonlinear equations . It describes and explores one approach to the application of the continuation method for solving...
Breast Cancer Monitoring and Tracking System using Soft Computing and Expert System for Healthcare Support
Abstract:The decision process for selecting the best-suited follow-up treatment for suspected breast cancer cases are strongly dependent upon the correct diagnosis and assessment of the breast cancer risk. This stu...