Face alignment based on the multi-scale local features
Many face recognition algorithms depend on careful positioning of face images into the same canonical pose. Currently, this positioning is usually done by detecting the locations of eyes. And the face images are transformed to the same positions according to the eye coordinates detected. In this pap...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Conference Paper |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/98794 http://hdl.handle.net/10220/13413 |
_version_ | 1811685065515597824 |
---|---|
author | Geng, Cong Jiang, Xudong |
author2 | School of Electrical and Electronic Engineering |
author_facet | School of Electrical and Electronic Engineering Geng, Cong Jiang, Xudong |
author_sort | Geng, Cong |
collection | NTU |
description | Many face recognition algorithms depend on careful positioning of face images into the same canonical pose. Currently, this positioning is usually done by detecting the locations of eyes. And the face images are transformed to the same positions according to the eye coordinates detected. In this paper, we describe a method based on multi-scale local features to achieve face alignment automatically not just dependent on the localizations of two eyes. Given an unaligned face image resulting from a face detector and a set of aligned face images in the data set, we build an automatic transformation mechanism, under which the unaligned face image can be precisely aligned for the following recognition process. Our alignment method improves performance on face recognition tasks, over images aligned by many other algorithms. |
first_indexed | 2024-10-01T04:38:36Z |
format | Conference Paper |
id | ntu-10356/98794 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T04:38:36Z |
publishDate | 2013 |
record_format | dspace |
spelling | ntu-10356/987942020-03-07T13:24:48Z Face alignment based on the multi-scale local features Geng, Cong Jiang, Xudong School of Electrical and Electronic Engineering IEEE International Conference on Acoustics, Speech and Signal Processing (2012 : Kyoto, Japan) DRNTU::Engineering::Electrical and electronic engineering Many face recognition algorithms depend on careful positioning of face images into the same canonical pose. Currently, this positioning is usually done by detecting the locations of eyes. And the face images are transformed to the same positions according to the eye coordinates detected. In this paper, we describe a method based on multi-scale local features to achieve face alignment automatically not just dependent on the localizations of two eyes. Given an unaligned face image resulting from a face detector and a set of aligned face images in the data set, we build an automatic transformation mechanism, under which the unaligned face image can be precisely aligned for the following recognition process. Our alignment method improves performance on face recognition tasks, over images aligned by many other algorithms. 2013-09-09T07:31:39Z 2019-12-06T19:59:44Z 2013-09-09T07:31:39Z 2019-12-06T19:59:44Z 2012 2012 Conference Paper Geng, C., & Jiang, X. (2012). Face alignment based on the multi-scale local features . 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1517-1520. https://hdl.handle.net/10356/98794 http://hdl.handle.net/10220/13413 10.1109/ICASSP.2012.6288179 en © 2012 IEEE. |
spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Geng, Cong Jiang, Xudong Face alignment based on the multi-scale local features |
title | Face alignment based on the multi-scale local features |
title_full | Face alignment based on the multi-scale local features |
title_fullStr | Face alignment based on the multi-scale local features |
title_full_unstemmed | Face alignment based on the multi-scale local features |
title_short | Face alignment based on the multi-scale local features |
title_sort | face alignment based on the multi scale local features |
topic | DRNTU::Engineering::Electrical and electronic engineering |
url | https://hdl.handle.net/10356/98794 http://hdl.handle.net/10220/13413 |
work_keys_str_mv | AT gengcong facealignmentbasedonthemultiscalelocalfeatures AT jiangxudong facealignmentbasedonthemultiscalelocalfeatures |