Using Kinect for face recognition under varying poses, expressions, illumination and disguise

We present an algorithm that uses a low resolution 3D sensor for robust face recognition under challenging conditions. A preprocessing algorithm is proposed which exploits the facial symmetry at the 3D point cloud level to obtain a canonical frontal view, shape and texture, of the faces irrespective...

Full description

Bibliographic Details
Main Authors: Li, Billy, Mian, A., Liu, Wan-Quan, Krishna, Aneesh
Other Authors: Not known
Format: Conference Paper
Published: IEEE 2013
Online Access:http://hdl.handle.net/20.500.11937/6810
_version_ 1848745183896666112
author Li, Billy
Mian, A.
Liu, Wan-Quan
Krishna, Aneesh
author2 Not known
author_facet Not known
Li, Billy
Mian, A.
Liu, Wan-Quan
Krishna, Aneesh
author_sort Li, Billy
building Curtin Institutional Repository
collection Online Access
description We present an algorithm that uses a low resolution 3D sensor for robust face recognition under challenging conditions. A preprocessing algorithm is proposed which exploits the facial symmetry at the 3D point cloud level to obtain a canonical frontal view, shape and texture, of the faces irrespective of their initial pose. This algorithm also fills holes and smooths the noisy depth data produced by the low resolution sensor. The canonical depth map and texture of a query face are then sparse approximated from separate dictionaries learned from training data. The texture is transformed from the RGB to Discriminant Color Space before sparse coding and the reconstruction errors from the two sparse coding steps are added for individual identities in the dictionary. The query face is assigned the identity with the smallest reconstruction error. Experiments are performed using a publicly available database containing over 5000 facial images (RGB-D) with varying poses, expressions, illumination and disguise, acquired using the Kinect sensor. Recognition rates are 96.7% for the RGB-D data and 88.7% for the noisy depth data alone. Our results justify the feasibility of low resolution 3D sensors for robust face recognition.
first_indexed 2025-11-14T06:13:19Z
format Conference Paper
id curtin-20.500.11937-6810
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:13:19Z
publishDate 2013
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-68102018-03-29T09:05:40Z Using Kinect for face recognition under varying poses, expressions, illumination and disguise Li, Billy Mian, A. Liu, Wan-Quan Krishna, Aneesh Not known We present an algorithm that uses a low resolution 3D sensor for robust face recognition under challenging conditions. A preprocessing algorithm is proposed which exploits the facial symmetry at the 3D point cloud level to obtain a canonical frontal view, shape and texture, of the faces irrespective of their initial pose. This algorithm also fills holes and smooths the noisy depth data produced by the low resolution sensor. The canonical depth map and texture of a query face are then sparse approximated from separate dictionaries learned from training data. The texture is transformed from the RGB to Discriminant Color Space before sparse coding and the reconstruction errors from the two sparse coding steps are added for individual identities in the dictionary. The query face is assigned the identity with the smallest reconstruction error. Experiments are performed using a publicly available database containing over 5000 facial images (RGB-D) with varying poses, expressions, illumination and disguise, acquired using the Kinect sensor. Recognition rates are 96.7% for the RGB-D data and 88.7% for the noisy depth data alone. Our results justify the feasibility of low resolution 3D sensors for robust face recognition. 2013 Conference Paper http://hdl.handle.net/20.500.11937/6810 10.1109/WACV.2013.6475017 IEEE restricted
spellingShingle Li, Billy
Mian, A.
Liu, Wan-Quan
Krishna, Aneesh
Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title_full Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title_fullStr Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title_full_unstemmed Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title_short Using Kinect for face recognition under varying poses, expressions, illumination and disguise
title_sort using kinect for face recognition under varying poses, expressions, illumination and disguise
url http://hdl.handle.net/20.500.11937/6810