2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS) 2016
DOI: 10.1109/btas.2016.7791208
|View full text |Cite
|
Sign up to set email alerts
|

Very low-resolution iris recognition via Eigen-patch super-resolution and matcher fusion

Abstract: Current research in iris recognition is moving towards enabling more relaxed acquisition conditions. This has effects on the quality of acquired images, with low resolution being a predominant issue. Here, we evaluate a superresolution algorithm used to reconstruct iris images based on Eigen-transformation of local image patches. Each patch is reconstructed separately, allowing better quality of enhanced images by preserving local information. Contrast enhancement is used to improve the reconstruction quality,… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
5
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 8 publications
(7 citation statements)
references
References 24 publications
2
5
0
Order By: Relevance
“…The present paper extends previous studies [11], [12] with additional experiments. A related method was proposed and studied for face super-resolution by Chen and Chien [13], which was the initial source that motivated the method studied here.…”
Section: Introductionsupporting
confidence: 89%
See 3 more Smart Citations
“…The present paper extends previous studies [11], [12] with additional experiments. A related method was proposed and studied for face super-resolution by Chen and Chien [13], which was the initial source that motivated the method studied here.…”
Section: Introductionsupporting
confidence: 89%
“…• Multi-algorithmic evaluation. In our previous works [11], [12], we used only two iris comparators for the experimental study. Here, we use six different publicly available iris feature extraction methods from popular and state-of-the-art schemes [52] based on 1D log-Gabor filters [19], the SIFT operator [20], [50], local intensity variations in iris textures [15], the Discrete-Cosine Transform [16], cumulative-sum-based grey change analysis [17], and Gabor spatial filters [18].…”
Section: A Contributionsmentioning
confidence: 99%
See 2 more Smart Citations
“…Here, the size of the patches is the precious parameter. After calculating the PSNR, MSE, and SSIM values, we obtain that the FLDA/PCA method performs better than bilinear or bicubic interpolation even at very low resolution [51]. We can therefore conclude that it is more resilient than reducing the resolution of the image.…”
Section: Intraclass and Interclassmentioning
confidence: 76%