Efficient high‐speed framework for sparse representation‐based iris recognition
Abstract While various frameworks for iris recognition have been proposed, most lack efficiency and high speed. A new framework for iris recognition is presented that is both efficient and fast. Feature extraction is performed by extracting Gabor features and then applying supervised locality‐preser...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-IET
2021-05-01
|
Series: | IET Biometrics |
Subjects: | |
Online Access: | https://doi.org/10.1049/bme2.12022 |
_version_ | 1797421621655371776 |
---|---|
author | Michael Melek Mohamed F. Abu‐Elyazeed Ahmed Khattab |
author_facet | Michael Melek Mohamed F. Abu‐Elyazeed Ahmed Khattab |
author_sort | Michael Melek |
collection | DOAJ |
description | Abstract While various frameworks for iris recognition have been proposed, most lack efficiency and high speed. A new framework for iris recognition is presented that is both efficient and fast. Feature extraction is performed by extracting Gabor features and then applying supervised locality‐preserving projections with heat kernel weights, which improves the recognition rate in comparison with the results from unsupervised dimensionality reduction techniques such as principal component analysis, locality‐preserving projections, and random projections. Afterwards, a classification is performed using the recently proposed sparse representation‐based classification (SRC). To considerably improve classification performance, SRC is proposed, using a greedy compressed‐sensing recovery algorithm, as opposed to employing the traditional computationally expensive ℓ1 minimisation. The proposed framework achieves a recognition rate of about 99.5% using two iris databases, with a significant improvement in speed over related frameworks. |
first_indexed | 2024-03-09T07:20:09Z |
format | Article |
id | doaj.art-9dcd53ebb3184f9797beb967aeb4aa0a |
institution | Directory Open Access Journal |
issn | 2047-4938 2047-4946 |
language | English |
last_indexed | 2024-03-09T07:20:09Z |
publishDate | 2021-05-01 |
publisher | Hindawi-IET |
record_format | Article |
series | IET Biometrics |
spelling | doaj.art-9dcd53ebb3184f9797beb967aeb4aa0a2023-12-03T07:43:41ZengHindawi-IETIET Biometrics2047-49382047-49462021-05-0110330431410.1049/bme2.12022Efficient high‐speed framework for sparse representation‐based iris recognitionMichael Melek0Mohamed F. Abu‐Elyazeed1Ahmed Khattab2Electronics and Electrical Communications Engineering Department Cairo University Giza EgyptElectronics and Electrical Communications Engineering Department Cairo University Giza EgyptElectronics and Electrical Communications Engineering Department Cairo University Giza EgyptAbstract While various frameworks for iris recognition have been proposed, most lack efficiency and high speed. A new framework for iris recognition is presented that is both efficient and fast. Feature extraction is performed by extracting Gabor features and then applying supervised locality‐preserving projections with heat kernel weights, which improves the recognition rate in comparison with the results from unsupervised dimensionality reduction techniques such as principal component analysis, locality‐preserving projections, and random projections. Afterwards, a classification is performed using the recently proposed sparse representation‐based classification (SRC). To considerably improve classification performance, SRC is proposed, using a greedy compressed‐sensing recovery algorithm, as opposed to employing the traditional computationally expensive ℓ1 minimisation. The proposed framework achieves a recognition rate of about 99.5% using two iris databases, with a significant improvement in speed over related frameworks.https://doi.org/10.1049/bme2.12022feature extractionimage classificationimage representationiris recognitionprincipal component analysissupervised learning |
spellingShingle | Michael Melek Mohamed F. Abu‐Elyazeed Ahmed Khattab Efficient high‐speed framework for sparse representation‐based iris recognition IET Biometrics feature extraction image classification image representation iris recognition principal component analysis supervised learning |
title | Efficient high‐speed framework for sparse representation‐based iris recognition |
title_full | Efficient high‐speed framework for sparse representation‐based iris recognition |
title_fullStr | Efficient high‐speed framework for sparse representation‐based iris recognition |
title_full_unstemmed | Efficient high‐speed framework for sparse representation‐based iris recognition |
title_short | Efficient high‐speed framework for sparse representation‐based iris recognition |
title_sort | efficient high speed framework for sparse representation based iris recognition |
topic | feature extraction image classification image representation iris recognition principal component analysis supervised learning |
url | https://doi.org/10.1049/bme2.12022 |
work_keys_str_mv | AT michaelmelek efficienthighspeedframeworkforsparserepresentationbasedirisrecognition AT mohamedfabuelyazeed efficienthighspeedframeworkforsparserepresentationbasedirisrecognition AT ahmedkhattab efficienthighspeedframeworkforsparserepresentationbasedirisrecognition |