Please use this identifier to cite or link to this item:
Title: Theory and practice of Arena face detection and recognition system
Authors: Zhao, Zixiao
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2016
Abstract: Face is one of the most unique biometrics for identification verification. Nowadays many projects are undertaken to realize an effective way for quickly identifying human faces through studies of manifold techniques and machine learning. Unlike these newly innovated complex algorithms target at mass-scale system of enterprise level, most of which have not been published to open source platform, This project aims to use a rather state-of-art system, ARENA, to handle a classical real time webcam face verification task in reality, as a feasible and open source solution for face verification in daily individual use under an acceptable budget, while helping readers build fundamental notions of classical face recognition utilization. The implementation of this system will be based on C++ language as primary programming language( to maintain data structure ), Qt user interface to build GUI, and OpenCV for all image processing tasks under a basis of the MVC principle (Model, View, Controller) as shown in the figure 1 below. Figure 1[1] After we finish combining these components, The ARENA system is capable of detecting and recognizing faces through web cam and analyzing if this face is ‘known’ as someone inside our face database or ‘unknown’ as a stranger excluded from database. We are also capable of making further modifications to the database by viewing existing faces and adding/removing faces.
Schools: School of Computer Engineering 
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 
FYP report - ZHAO ZIXIAO.pdf
  Restricted Access
4.53 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 17, 2024


Updated on Jun 17, 2024

Google ScholarTM


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