Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/128392
Title: FACE IMAGE DE-OCCLUSION WITH VARIABLE-THRESHOLD ROBUST PCA
Authors: LI GUODONG
Keywords: face, deocclusion, RPCA, low-rank, variable-threshold
Issue Date: 24-Jun-2016
Citation: LI GUODONG (2016-06-24). FACE IMAGE DE-OCCLUSION WITH VARIABLE-THRESHOLD ROBUST PCA. ScholarBank@NUS Repository.
Abstract: The human face is one of the most important biometric traits in human social activities such as security, surveillance, identification, criminal and forensic investigation. This thesis aims to overcome the difficulties of existing methods for face occlusion removal by the proposed variable-threshold RPCA (VRPCA) method. Given prior knowledge of the occluded area, VRPCA separates the error matrix into three different parts: the training part, the testing unoccluded part and the testing occluded part. By applying different thresholds to these three parts, VRPCA ensures that the errors are mostly from the occluded part and that unintended corruptions is minimized in the reconstruction of the unoccluded parts. Various test results show that VRPCA is consistently more accurate than existing methods across various test conditions for recovering occluded parts. Moreover, VRPCA is able to preserve the unoccluded parts of the target image with practically zero error.
URI: http://scholarbank.nus.edu.sg/handle/10635/128392
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LiGD.pdf4.01 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

122
checked on Oct 5, 2018

Download(s)

80
checked on Oct 5, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.