Super-resolution for iris feature extraction

Deshpande, Anand; Patavardhan, Prashant P.; Rao, D. H.

doi:10.1109/iccic.2014.7238401

Cited by 7 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, learning-based methods model the relationship between LR and HR images with a training dictionary, using the learned model to up-sample unseen LR images Learning-based methods only need one LR image as input, and generally outperform reconstruction-based methods, achieving higher magnification factors [20]. The few works available on iris learning-based approaches employ Multi-Layer Perceptrons [23], or frequency analysis [9]. One major limitation is that they try to develop a prototype iris using combination of complete images.…”

Section: Introductionmentioning

confidence: 99%

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

Alonso‐Fernandez

Farrugia

Bigün

2016

2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

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, while matcher fusion has been adopted to improve iris recognition performance. We validate the system using a database of 1,872 near-infrared iris images. The presented approach is superior to bilinear or bicubic interpolation, especially at lower resolutions, and the fusion of the two systems pushes the EER to below 5% for down-sampling factors up to a image size of only 13×13.

show abstract

Section: Introductionmentioning

confidence: 99%