Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/46951
Title: Sclera recognition using dense-SIFT
Authors: Das, Abhijit
Pal, Umapada
Ballester, Miguel Angel Ferrer 
Blumenstein, Michael
UNESCO Clasification: Investigación
Keywords: Biometric
Sclera Vessel Patterns
D-Sift
Svm
Bag Of Features
K-Means
Bank Of 2D Decomposition Haar Multi-Resolution Filters Wavelet
Issue Date: 2014
Journal: International Conference on Intelligent Systems Design and Applications 
Conference: 2013 13th International Conference on Intellient Systems Design and Applications, ISDA 2013 
Abstract: In this paper we propose a biometric sclera recognition and validation system. Here the sclera segmentation is performed bya time-adaptive active contour-based region growing technique. The sclera vessels are not prominent so image enhancement is required and hence a bank of 2D decomposition. A Haar wavelet multi-resolution filter is used to enhance the vessels pattern for better accuracy. For feature extraction, Dense Scale Invariant Feature Transform (D-SIFT) is used. D-SIFT patch descriptors of each training image are used to form bag of features by using k-means clustering and a spatial pyramid model, which is used to produce the training model. Support Vector Machines (SVMs) are used for classification. The UBIRIS version 1 dataset is used here for experimentation. Anencouraging Equal Error Rate (EER) of 0.66% is attained in the experiments presented.
URI: http://hdl.handle.net/10553/46951
ISBN: 978-1-4799-3516-1
ISSN: 2164-7143
DOI: 10.1109/ISDA.2013.6920711
Source: International Conference on Intelligent Systems Design and Applications, ISDA [ISSN 2164-7143] (6920711), p. 74-79, (2013)
Appears in Collections:Actas de congresos
Thumbnail
Adobe PDF (904,65 kB)
Show full item record

SCOPUSTM   
Citations

29
checked on Feb 28, 2021

WEB OF SCIENCETM
Citations

19
checked on Feb 28, 2021

Page view(s)

25
checked on Feb 28, 2021

Download(s)

25
checked on Feb 28, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.