Skip to main content
DORAS
DCU Online Research Access Service
Login (DCU Staff Only)
Single sample face identification utilizing sparse discriminative multi manifold embedding

Shahali, Fatemeh, Nazemi, Azadeh ORCID: 0000-0002-1138-309X and Azimifar, Zohreh (2018) Single sample face identification utilizing sparse discriminative multi manifold embedding. In: Artificial Intelligence and Signal Processing Conference (AISP2017), 25-27 Oct 2017, Shiraz, Iran.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
472kB

Abstract

This paper describes three methods to improve single sample dataset face identification. The recent approaches to address this issue use intensity and do not guarantee for the high accuracy under uncontrolled conditions. This research presents an approach based on Sparse Discriminative Multi Manifold Embedding (SDMME) , which uses feature extraction rather than intensity and normalization for pre–processing to reduce the effects of uncontrolled condition such as illumination. In average this study improves identification accuracy about 17% compare to current methods

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:No
Uncontrolled Keywords:Face Identification; Sparse Discriminative Multi Manifold Embedding (SDMME); Single Sample dataset; Feature extraction; Self Quotient Image ( SQI)
Subjects:UNSPECIFIED
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in: 2017 Artificial Intelligence and Signal Processing Conference (AISP), Proceedings of the. . IEEE.
Publisher:IEEE
Official URL:https://doi.org/10.1109/AISP.2017.8324123
Copyright Information:© 2017 The Authors
ID Code:23057
Deposited On:04 Mar 2019 10:24 by Azadeh Nazemi . Last Modified 03 Sep 2020 15:58

Downloads

Downloads per month over past year

Archive Staff Only: edit this record

Altmetric
- Altmetric
+ Altmetric
  • Student Email
  • Staff Email
  • Student Apps
  • Staff Apps
  • Loop
  • Disclaimer
  • Privacy
  • Contact Us