A Performance Analysis of Face Recognition Based on Artificial Neural Network
Journal Title: International Journal of Science Engineering and Advance Technology - Year 2013, Vol 1, Issue 5
Abstract
Face recognition is bearing in mind and recognizing a face of individual, like a visual pattern recognition that enables the system to verify or identify individual faces that is taken from imaging system. In this paper we tried to show that a face recognition that uses a tanh activation function would have a better or lower mean squared error instead of using the Logistic Sigmoid activation function. The network was trained several times on different ideal input and noisy images that are taken from imaging devices like camera. In this case training a network on different sets of noisy images forced the network to learn how to deal with noise image by using a tanh activation function.
Authors and Affiliations
Abrham Debasu Mengistu| M.Sc. (Computer Science) School of Computing and Electrical Engineering IOT, Bahir Dar University Ethiopia, Dr. Vuda Sreenivasarao| Professor School of Computing and Electrical Engineering IOT, Bahir Dar University Ethiopia, INDIA
Keywords
Related Articles
- EP ID EP16227
- DOI -
- Views 394
- Downloads 19
A Novel Strategy for Static Compensator Based Control of Grid Interfaced OWF and MCF for Dynamic Stability Enhancement
This paper presents a novel strategy for static compensator based control of grid interfaced OWF and MCF for dynamic stability enhancement. The performance of the studied OWF is simulated by an equivalent doubly-fed...
Efficient Data Access in Disruption Tolerant Networks Using Cooperative Caching with DRAMA
Disruption Tolerant Networks (DTNs) is characterized by low node density and unpredictable node mobility. The current research efforts in DTN focus on data forward in gand reduce absence of end-toend path between sour...
A New Clustering Technique On Text In Sentence For Text Mining
Clustering is a commonly considered data mining problem in the text domains. The problem finds numerous applications in customer segmentation, classification, collaborative filtering, visualization, document organizat...
A Grid Level High Power Back To Back System Using Modular Multilevel Cascade Converter Without Dc Link Capacitor
In this paper a fuzzy logic controller have been designed for back-to back (BTB) system unifying two modular multilevel cascade converters (MMCCs). Based on double-star chopper cells BTB system designed. The two DSCC...
Performance Analysis of Ship Tracking using PID/Predictive Controller
Accurate ship navigation is very essential for saving fuel as well time. In order to achieve accurate tracking in unmanned ship navigation various controllers like PID, Predictive and Adaptive controllers are used. Ea...