Please use this identifier to cite or link to this item:
Title: Real-time face recognition
Authors: Liu, Liyao
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2015
Abstract: Face recognition has been one of the most popular and important research topics in computer vision, and was applied to many other fields such as security and law enforcement. Over the past two decades, face recognition are still challenging, due to the technology limit, wide range of input, and complexity of the algorithms. Researchers and engineers have devoted in a lot of efforts trying to improve the algorithms so that faster, better or more reliable performance can be achieved. There are different types of face recognition algorithms. Each has its pros and cons and there is no robust method for all kinds of situations. Modern embedded system is a computer system that based on microcontrollers which often come with integrated memory. Embedded system is normally applied in portable devices such as digital watches, music players, smart devices etc. Due to its hardware resource limitations, the software system that built in such devices needs to pay special attention to the efficiency measure and hardware costs. This report will introduce and implement one of the idea based on ARENA and Nearest Neighbour (NN) to build a real-time based face recognition system, which aims to find out whether the captured face is within the current face database. With the consideration of hardware limit, the performance and time cost will be evaluated. The input query image can be taken from either video or static image, and used to compare with the predefined face database through the application. Also, the flows, functionalities, and testing results of the application will be presented in order to show the full picture of the whole process.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.3 MBAdobe PDFView/Open

Page view(s)

checked on Sep 22, 2020


checked on Sep 22, 2020

Google ScholarTM


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