Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/69311
Title: Occlusion removal from face image based on the image reconstruction learnt from database
Authors: Huang, Wen
Keywords: DRNTU::Engineering
Issue Date: 2016
Abstract: The human face is one of the most commonly seen and more and more biometric traits are used and researched in our daily life. With the development of the technology, the face images are more easily collected by cameras or other digital electronic devices. Face images are becoming more and more important in human social activities such as security, surveillance, identification, criminal and so on. However, these activities can be interrupted by occluded faces. The occlusion may be from different objects such as sunglasses, scarves, mask or hair. Sometimes, this occlusion is used for criminal to hide the identities of criminal person from the surroundings. Therefore, the occlusion removal in face images is an important task to the society. Unfortunately, facial occlusion removal is difficult and challenging. Although human faces generally have similar appearances including eyes, nose and mouth, the feature details may different from races, genders and ages. It is a difficult task to reconstruct face images with high similarity. In this project, PCA (Principle Component Analysis) is applying for faces image occlusion removal and image reconstruction. A database of different persons’ image is collected and organized which are used in the process of image occlusion removal and reconstruction. The entire face is reconstructed using the non-occluded parts of the face from the database.
URI: http://hdl.handle.net/10356/69311
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 (5).pdf
  Restricted Access
1.6 MBAdobe PDFView/Open

Page view(s)

99
Updated on May 13, 2021

Download(s)

4
Updated on May 13, 2021

Google ScholarTM

Check

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