Face recognition in unconstrained images and videos

In recent years, face recognition remains as one of the most attractive research topic in the computer vision field. Many methods have been proposed to deal with the large appearance changes of human face, yet it is still debatable which method works best on the unconstrained environment in ordinary...

Full description

Saved in:
Bibliographic Details
Main Author: Nguyen, Bich Hoang Anh
Other Authors: Xu Dong
Format: Theses and Dissertations
Language:English
Published: 2014
Subjects:
Online Access:https://hdl.handle.net/10356/55286
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-55286
record_format dspace
spelling sg-ntu-dr.10356-552862023-03-04T00:48:44Z Face recognition in unconstrained images and videos Nguyen, Bich Hoang Anh Xu Dong School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition In recent years, face recognition remains as one of the most attractive research topic in the computer vision field. Many methods have been proposed to deal with the large appearance changes of human face, yet it is still debatable which method works best on the unconstrained environment in ordinary photograph and video. This thesis thoroughly reviews and implements some state-of-the-art methods for image-based face recognition as well as completely studies their performance on various large scale dataset. Motivated from the results on image datasets, a novel framework is proposed for face verification in unconstrained videos. By leveraging the pose angle information, we employ a divide and conquer approach through the following steps (a) divide the keyframes of the original video into several pose categories from extreme left to right profile face and synthesize the appearance at all missing poses (b) propose the ensemble cross-pose classifiers to recognize human faces despite pose differences by cross reference the subset of the original training data with the same pose categories. Extensive experiments on the large-scale YouTube video dataset clearly demonstrate the effectiveness and robustness to pose variation of our proposed framework. MASTER OF ENGINEERING (SCE) 2014-01-10T04:36:02Z 2014-01-10T04:36:02Z 2013 2013 Thesis Nguyen, B. H. A. (2013). Face recognition in unconstrained images and videos. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/55286 10.32657/10356/55286 en 69 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Nguyen, Bich Hoang Anh
Face recognition in unconstrained images and videos
description In recent years, face recognition remains as one of the most attractive research topic in the computer vision field. Many methods have been proposed to deal with the large appearance changes of human face, yet it is still debatable which method works best on the unconstrained environment in ordinary photograph and video. This thesis thoroughly reviews and implements some state-of-the-art methods for image-based face recognition as well as completely studies their performance on various large scale dataset. Motivated from the results on image datasets, a novel framework is proposed for face verification in unconstrained videos. By leveraging the pose angle information, we employ a divide and conquer approach through the following steps (a) divide the keyframes of the original video into several pose categories from extreme left to right profile face and synthesize the appearance at all missing poses (b) propose the ensemble cross-pose classifiers to recognize human faces despite pose differences by cross reference the subset of the original training data with the same pose categories. Extensive experiments on the large-scale YouTube video dataset clearly demonstrate the effectiveness and robustness to pose variation of our proposed framework.
author2 Xu Dong
author_facet Xu Dong
Nguyen, Bich Hoang Anh
format Theses and Dissertations
author Nguyen, Bich Hoang Anh
author_sort Nguyen, Bich Hoang Anh
title Face recognition in unconstrained images and videos
title_short Face recognition in unconstrained images and videos
title_full Face recognition in unconstrained images and videos
title_fullStr Face recognition in unconstrained images and videos
title_full_unstemmed Face recognition in unconstrained images and videos
title_sort face recognition in unconstrained images and videos
publishDate 2014
url https://hdl.handle.net/10356/55286
_version_ 1759858305542389760