A Comparative Analysis of Feed-Forward and Elman Neural Networks for Face Recognition Using Principal Component Analysis
Journal Title: International Journal of Advanced Research in Computer Engineering & Technology(IJARCET) - Year 2012, Vol 1, Issue 4
Abstract
Abstract—In this paper we give a comparative analysis of performance of feed forward neural network and elman neural network based face recognition. We use different inner epoch for different input pattern according to their difficulty of recognition. We run our system for different number of training patterns and test the system’s performance in terms of recognition rate and training time. We run our algorithm for face recognition application using Principal Component Analysis and both neural network. PCA is used for feature extraction and the neural network is used as a classifier to identify the faces. We use the ORL database for all the experiments. Here 150 face images from the database are taken and some performance metrics such as recognition rate and total training time are calculated. We use two way cross validation approach while calculating recognition rate and total training time . In two way cross validation, we interchange training set into test set and test set into training set. Feed forward neural network has better performance in terms of recognition rate and total training time as compare to elman neural network.Abstract—In this paper we give a comparative analysis of performance of feed forward neural network and elman neural network based face recognition. We use different inner epoch for different input pattern according to their difficulty of recognition. We run our system for different number of training patterns and test the system’s performance in terms of recognition rate and training time. We run our algorithm for face recognition application using Principal Component Analysis and both neural network. PCA is used for feature extraction and the neural network is used as a classifier to identify the faces. We use the ORL database for all the experiments. Here 150 face images from the database are taken and some performance metrics such as recognition rate and total training time are calculated. We use two way cross validation approach while calculating recognition rate and total training time . In two way cross validation, we interchange training set into test set and test set into training set. Feed forward neural network has better performance in terms of recognition rate and total training time as compare to elman neural network.Abstract—In this paper we give a comparative analysis of performance of feed forward neural network and elman neural network based face recognition. We use different inner epoch for different input pattern according to their difficulty of recognition. We run our system for different number of training patterns and test the system’s performance in terms of recognition rate and training time. We run our algorithm for face recognition application using Principal Component Analysis and both neural network. PCA is used for feature extraction and the neural network is used as a classifier to identify the faces. We use the ORL database for all the experiments. Here 150 face images from the database are taken and some performance metrics such as recognition rate and total training time are calculated. We use two way cross validation approach while calculating recognition rate and total training time . In two way cross validation, we interchange training set into test set and test set into training set. Feed forward neural network has better performance in terms of recognition rate and total training time as compare to elman neural network.Abstract—In this paper we give a comparative analysis of performance of feed forward neural network and elman neural network based face recognition. We use different inner epoch for different input pattern according to their difficulty of recognition. We run our system for different number of training patterns and test the system’s performance in terms of recognition rate and training time. We run our algorithm for face recognition application using Principal Component Analysis and both neural network. PCA is used for feature extraction and the neural network is used as a classifier to identify the faces. We use the ORL database for all the experiments. Here 150 face images from the database are taken and some performance metrics such as recognition rate and total training time are calculated. We use two way cross validation approach while calculating recognition rate and total training time . In two way cross validation, we interchange training set into test set and test set into training set. Feed forward neural network has better performance in terms of recognition rate and total training time as compare to elman neural network.
Authors and Affiliations
Amit Kumar1 , Mahesh Singh
Keywords
Related Articles
- EP ID EP87829
- DOI -
- Views 152
- Downloads 0
Simulation and evaluation of convolution encoder for different noisy channel over wireless communication network in CDMA environment
In this paper we simulate and evaluate the performance of physical layer of wireless communication system of CDMA-2000 specification using radio configuration-3 under forward fundamental channel 1x in terms of bit...
A Survey on Access Control of Cloud Data
t-Among the emerging technologies, cloud computing provides a flexible, on-demand computing infrastructure for a number of applications. Cloud computing is about moving computing from the single desktop pc/data c...
Secure Policy Based Data Sharing for Dynamic Groups in the Cloud
Major problem in public clouds is how to share documents based on fine-grained attribute based access control policies, sharing data in a dynamic groups while preserving data and identity privacy from an un trusted...
Study of User Experience (UX) and UX Evaluation methods.
The goal of user experience analysis and evaluation methods in the software industry is to improve customer satisfaction through the utility, ease of use, and quality of interaction with applications, services and...
A Hybrid Local Broadcast Algorithm in Wireless Ad Hoc Networks using Dynamic Approach
Broadcasting is a commonly used feature in wireless ad hoc networks. It is a common operation for route establishment and for sending control and emergency messages. The primary goal of broadcasting is to successfully re...