Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/45785
Title: Enhancement of face recognition using modified linear binary patterns
Authors: Wang, Roger Zhiming.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2011
Abstract: Automatic face analysis which includes, e.g., face detection, face recognition and facial expression recognition has become a very active topic in computer vision research [1], due to its various wide potential applications in public security, financial security, entertainment, intelligent human-computer interaction, etc. A key issue in face analysis is finding efficient descriptors for face appearance. Different holistic methods such as Principal Component Analysis (PCA) [2], Linear Discriminant Analysis (LDA) [3] and 2-D PCA [4] have been studied widely but lately local descriptors have gained popularity due to their robustness to challenges such as pose and illumination changes. The main focus of this project is to develop a system using modified Local Binary Pattern (LBP) to improve on face recognition. Firstly, pre-processing of database is to ensure that images are consistence throughout training and testing process. Pre-processing procedures include, decompressing of database, extracting of eye coordinates automatically or manually for accurate cropping of faces and normalisation. Precise cropping of face will ensure important information of faces is all included in the desired image.
URI: http://hdl.handle.net/10356/45785
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 
e4113.pdf
  Restricted Access
3.16 MBAdobe PDFView/Open

Page view(s) 50

217
checked on Oct 26, 2020

Download(s) 50

14
checked on Oct 26, 2020

Google ScholarTM

Check

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