Pose Normalization based on Kernel ELM Regression for Face Recognition

Pose variation is the one of the main difficulty faced by present automatic face recognition system. Due to the pose variations, feature vectors of the same person may vary more than inter person identity. This paper aims to generate virtual frontal view from its corresponding non frontal face image...

Full description

Saved in:
Bibliographic Details
Published in:International journal of image, graphics and signal processing graphics and signal processing, 2017-05, Vol.9 (5), p.68-75
Main Authors: Goel, Tripti, Nehra, Vijay, P. Vishwakarma, Virendra
Format: Article
Language:English
Subjects:
Face recognition
Facial recognition technology
Mapping
Neural networks
Regression
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Pose variation is the one of the main difficulty faced by present automatic face recognition system. Due to the pose variations, feature vectors of the same person may vary more than inter person identity. This paper aims to generate virtual frontal view from its corresponding non frontal face image. The approach presented in this paper is based on the assumption of existence of an approximate mapping between the non frontal posed image and its corresponding frontal view. By calculating the mapping between frontal and posed image, the problem of estimating the frontal view will become the regression problem. In the present approach, non linear mapping, kernel extreme learning machine (KELM) regression is used to generate virtual frontal face image from its non frontal counterpart. Kernel ELM regression is used to compensate for the non linear shape of the face. The studies are performed on GTAV database with 5 posed images and compared with linear regression approach.
ISSN:2074-9074
2074-9082
DOI:10.5815/ijigsp.2017.05.07