Exploring Deep Learning Image Super-Resolution for Iris Recognition

Ribeiro, EduardoUniversity of Salzburg, Department of Computer Sciences, Salzburg, Austria & Federal University of Tocantins, Department of Computer Sciences, Tocantins, Brazil (author)

Funder: National Council for Scientific and Technological Development (CNPq) under grant No. 00736/2014-0
Funding: CNPq-Brazil
In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms. © EURASIP 2017.

NATURVETENSKAP Data- och informationsvetenskap Datorseende och robotik hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Vision and Robotics hsv//eng
TEKNIK OCH TEKNOLOGIER Elektroteknik och elektronik Signalbehandling hsv//swe
ENGINEERING AND TECHNOLOGY Electrical Engineering, Electronic Engineering, Information Engineering Signal Processing hsv//eng
Biometrics
Infrared devices
Learning systems
Neural networks
Optical resolving power
Quality of service
Signal processing
Convolutional neural network
High resolution image
Image super resolutions
Iris recognition
Learning approach
Learning methods
Local information
Quality assessment
Deep learning

Uhl, AndreasUniversity of Salzburg, Department of Computer Sciences, Salzburg, Austria (author)
Alonso-Fernandez, Fernando,1978-Högskolan i Halmstad,Halmstad Embedded and Intelligent Systems Research (EIS),CAISR Centrum för tillämpade intelligenta system (IS-lab)(Swepub:hh)feralo (author)
Farrugia, Reuben A.University of Malta, Department of CCE, Msida, Malta (author)
University of Salzburg, Department of Computer Sciences, Salzburg, Austria & Federal University of Tocantins, Department of Computer Sciences, Tocantins, BrazilUniversity of Salzburg, Department of Computer Sciences, Salzburg, Austria (creator_code:org_t)

In:25th European Signal Processing Conference (EUSIPCO 2017): Institute of Electrical and Electronics Engineers (IEEE), s. 2176-2180978099286267197809928626889781538607510

By the author/editor: Ribeiro, Eduardo; Uhl, Andreas; Alonso-Fernandez ...; Farrugia, Reuben ...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Signal Processin ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.