Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/55220
Title: Techniques for face recognition in surveillance applications
Authors: Htun, Naw Olive.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2013
Abstract: This is a final year report aiming to provide the knowledge and achievements acquired upon completion of the final year project. It covers the motivations for the project and project objectives, scope and background knowledge required carrying out the project. In this project, the main focus is to study still-image face recognition system and thus theoretical backgrounds for the two essential algorithms in recognizing the different faces and the neural network used to implement the face recognition are briefly presented in this report. The main algorithms used in this project are the two appearance-based face recognition algorithms: Eigenface and Fisherface. The face databases used with the programs are also briefly described. The backpropagation neural network is utilized as a classifier and the face images from the databases are presented into the network to perform face recognition. Also a user friendly graphical user interface (GUI) acting as a platform for face recognition is also introduced. Finally, the correct classification rates based on the conditions that images were taken are then analyzed. After the evaluating the results, it is observed that Fisherface method has better performance under varying lighting condition. It is also observed that the performance of Eigenface improved after removing the first three components of the Eigenfaces.
URI: http://hdl.handle.net/10356/55220
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_Report_P3002-111.pdf
  Restricted Access
Final Year Report1.28 MBAdobe PDFView/Open

Page view(s) 50

160
checked on Oct 26, 2020

Download(s) 50

10
checked on Oct 26, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.