Component Based Representation Using Probabilistic NeuralNetwork Classifier

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 6

Abstract

 Abstract: The law enforcement agency make use of face recognition system for the identification of criminals.In some cases, the photograph of criminals is not available. In this situation,sketch is drawn by the informationprovided by the eyewitness. In the early stages sketches are drawn by the artist by the information provided bythe eyewitness. Sometimes the witness does not recall the exact apperance of the suspect. In that case,sketchdrawn is not helpfull for investigation. In this networked world, the sketch construction with the help ofcomputer generated software arises. The computer generated composite sketch is constructed by selecting thefacial components provided in the system database. The composite sketch construction gives more faster resultsfor the law enforcement agency. The component based approach for face recognition using probabilistic neuralnetwork classifier gives more accurate result in photo to sketch matching. The proposed approach performsfacial decomposition, some transformations and feature extraction for photo to composite matching. The use ofclassifier is helpfull for comparing the features of face images and gives the degree of match to make a decision. The advantage of using Probabilisitic Neural Network( PNN) classifier is that it requires only short trainingtime

Authors and Affiliations

Anjali G

Keywords

Related Articles

 Influence of Socioeconomic Status and Expectations among Completely Edentulous Patients on Conventional Complete Denture Treatment

Objective: The purpose of this study was to determine the effect of socioeconomic status on patient expectation from the treatment through a Questionnaire based survey. Material and Method: The Present study was conducte...

A Survey on Routing Protocols influencing Mobile Sink in enhancing life time of WSN for Data gathering

Abstract: Wireless Sensor Network is a group of specialized sensors have the ability to sense, monitor, communicate to the neighbors and recording conditions at assorted locations such as temperature, sound, pressure, se...

 The effect of Encryption algorithms Delay on TCP Traffic overdata networks

 Abstract: Security is a big concern for data networks users. Data encryption considered to be one of the bestsolutions for security issues. There are some standard encryption algorithms that used to encrypt transfe...

 Reduce the False Positive and False Negative from Real Trafficwith Intrusion Detection in Zigbee Wireless Networks

 Abstract: Denial-of-Service attack in particular is a threat to zigbee wireless networks. It is an attack in whichthe primary goal is to deny the legitimate users access to the resources. A node is prevented from r...

The Evaluation of (CapEx/OpEx) Cost reduction of IPTV Service delivery using SDN Solution

This paper aims to quantify and evaluate the cost saving of offering IPTV service through the ‘Gold’ Network Solutions implemented in IPTV SMC ISP data center; SDN and NFV.Recently, the demand for Streaming services like...

Download PDF file
  • EP ID EP158133
  • DOI -
  • Views 92
  • Downloads 0

How To Cite

Anjali G (2014).  Component Based Representation Using Probabilistic NeuralNetwork Classifier. IOSR Journals (IOSR Journal of Computer Engineering), 16(6), 35-39. https://europub.co.uk/articles/-A-158133