Face Recognition System Based on Different Artificial Neural Networks Models and Training Algorithms
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2013, Vol 4, Issue 6
Abstract
Face recognition is one of the biometric methods that is used to identify any given face image using the main features of this face. In this research, a face recognition system was suggested based on four Artificial Neural Network (ANN) models separately: feed forward backpropagation neural network (FFBPNN), cascade forward backpropagation neural network (CFBPNN), function fitting neural network (FitNet) and pattern recognition neural network (PatternNet). Each model was constructed separately with 7 layers (input layer, 5 hidden layers each with 15 hidden units and output layer). Six ANN training algorithms (TRAINLM, TRAINBFG, TRAINBR, TRAINCGF, TRAINGD, and TRAINGD) were used to train each model separately. Many experiments were conducted for each one of the four models based on 6 different training algorithms. The performance results of these models were compared according to mean square error and recognition rate to identify the best ANN model. The results showed that the PatternNet model was the best model used. Finally, comparisons between the used training algorithms were performed. Comparison results showed that TrainLM was the best training algorithm for the face recognition system.
Authors and Affiliations
Omaima AL-Allaf, Abdelfatah Tamimi, Mohammad Alia
Keywords
Related Articles
- EP ID EP146354
- DOI 10.14569/IJACSA.2013.040606
- Views 110
- Downloads 0
Algorithm to Match Ontologies on the Semantic Web
It has been recognized that semantic data and knowledge extraction will significantly improve the capability of natural language interfaces to the semantic search engine. Semantic Web technology offers a vast scale of sh...
Performance Evaluation of Different Data Mining Techniques for Social Media News Credibility Assessment
Social media has recently become a basic source for news consumption and sharing among millions of users. Social media platforms enable users to publish and share their own generated content with little or no restrictio...
An Extension of the Bisection Theorem to Symmetrical Circuits with Cross-Coupling
This paper demonstrates that the bisection theorem can be applied to the differential and common-mode analysis of balanced symmetrical circuits with cross coupling. This class of circuits is often found in the literature...
An improved Approach for Document Retrieval Using Suffix Trees
Huge collection of documents is available at few mouse clicks. The current World Wide Web is a web of pages. Users have to guess possible keywords that might lead through search engines to the pages that contain informat...
Investigating Clinical Decision Support Systems Success Factors with Usability Testing
Clinical Decision Support Systems (CDSS) have been used widely since 2000s to improve the healthcare quality. CDSS can be utilized to support healthcare services as a tool to diagnose, predict, as well as to provide clin...