Paper Info
Title
Improving Very Low-Resolution Iris Identification via Super-Resolution Reconstruction of Local Patches
Abstract
Relaxed acquisition conditions in iris recognition systems have significant effects on the quality and resolution of acquired images, which can severely affect performance if not addressed properly. Here, we evaluate two trained superresolution algorithms in the context of iris identification. They are based on reconstruction of local image patches, where each patch is reconstructed separately using its own optimal reconstruction function. We employ a database of 1,872 near-infrared iris images (with 163 different identities for identification experiments) and three iris comparators. The trained approaches are substantially superior to bilinear or bicubic interpolations, with one of the comparators providing a Rank-1 performance of ~88% with images of only 15×15 pixels, and an identification rate of 95% with a hit list size of only 8 identities.
Year
DOI
Venue
2017
10.23919/BIOSIG.2017.8053512
2017 International Conference of the Biometrics Special Interest Group (BIOSIG)
Keywords
Field
DocType
low-resolution iris identification,super-resolution reconstruction,iris recognition systems,optimal reconstruction function,near-infrared iris images,iris comparators,image quality,image resolution,image patches reconstruction,bilinear interpolations,bicubic interpolations
Iterative reconstruction,Iris recognition,Computer vision,Signal processing,Pattern recognition,Computer science,Interpolation,Bicubic interpolation,Pixel,Artificial intelligence,Image resolution,Bilinear interpolation
Conference
ISBN
Citations 
PageRank 
978-1-5386-0396-3
0
0.34
References 
Authors
7
3
Name
Order
Citations
PageRank
Fernando Alonso-Fernandez153137.65
Reuben A. Farrugia211118.26
Josef Bigun342641.34