Are Gabor Kernels Optimal for Iris Recognition?

  title={Are Gabor Kernels Optimal for Iris Recognition?},
  author={Aidan Boyd and Adam Czajka and K. Bowyer},
  journal={2020 IEEE International Joint Conference on Biometrics (IJCB)},
Gabor kernels are widely accepted as dominant filters for iris recognition. In this work we investigate, given the current interest in neural networks, if Gabor kernels are the only family of functions performing best in iris recognition, or if better filters can be learned directly from iris data. We use (on purpose) a single-layer convolutional neural network as it mimics an iris code-based algorithm. We learn two sets of data-driven kernels; one starting from randomly initialized weights and… Expand


Toward More Accurate Iris Recognition Using Dilated Residual Features
This paper investigates a new deep learning-based approach for iris recognition and attempts to improve the accuracy using a more simplified framework to more accurately recover the representative features. Expand
DeepIrisNet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition
Experimental analysis reveal that proposed DeepIrisNet can model the micro-structures of iris very effectively and provides robust, discriminative, compact, and very easy-to-implement iris representation that obtains state-of-the-art accuracy. Expand
Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features
This paper proposes an accurate and generalizable deep learning framework for iris recognition based on a fully convolutional network (FCN), which generates spatially corresponding iris feature descriptors and exhibits superior generalization capability. Expand
ThirdEye: Triplet Based Iris Recognition without Normalization
  • Sohaib Ahmad, Benjamin Fuller
  • Computer Science
  • 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS)
  • 2019
A new iris recognition system called ThirdEye is developed based on triplet convolutional neural networks that directly uses segmented images without normalization, suggesting that normalization is more important for less constrained environments. Expand
Information Theory and the IrisCode
  • J. Daugman
  • Computer Science
  • IEEE Transactions on Information Forensics and Security
  • 2016
A simple two-state hidden Markov model is shown to emulate exactly the statistics of bit sequences generated both from natural and white noise iris images, including their imposter distributions, and may be useful for generating large synthetic IrisCode databases. Expand
An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex.
It seems that an optimal strategy has evolved for sampling images simultaneously in the 2D spatial and spatial frequency domains and the Gabor function provides a useful and reasonably accurate description of most spatial aspects of simple receptive fields. Expand
High Confidence Visual Recognition of Persons by a Test of Statistical Independence
  • J. Daugman
  • Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1993
A method for rapid visual recognition of personal identity is described, based on the failure of a statistical test of independence, which implies a theoretical "cross-over" error rate of one in 131000 when a decision criterion is adopted that would equalize the false accept and false reject error rates. Expand
OSIRIS: An open source iris recognition software
A novel approach for iris normalization, based on a non geometric parameterization of contours is proposed in the latest version: OSIRISV4.1 and is detailed in particular here. Expand
LivDet iris 2017 — Iris liveness detection competition 2017
Results of the third LivDet-Iris 2017 show that even with advances, printed iris attacks as well as patterned contacts lenses are still difficult for software-based systems to detect. Expand
In Defense of the Triplet Loss for Person Re-Identification
It is shown that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin. Expand