Performance of Humans in Iris Recognition: The Impact of Iris Condition and Annotation-Driven Verification

@article{Moreira2019PerformanceOH,
  title={Performance of Humans in Iris Recognition: The Impact of Iris Condition and Annotation-Driven Verification},
  author={Daniel Moreira and Mateusz Trokielewicz and Adam Czajka and K. Bowyer and Patrick J. Flynn},
  journal={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2019},
  pages={941-949}
}
This paper advances the state of the art in human examination of iris images by (1) assessing the impact of different iris conditions in identity verification, and (2) introducing an annotation step that improves the accuracy of people's decisions. In a first experimental session, 114 subjects were asked to decide if pairs of iris images depict the same eye (genuine pairs) or two distinct eyes (impostor pairs). The image pairs sampled six conditions: (1) easy for algorithms to classify, (2… Expand
Development of a clustering based fusion framework for locating the most consistent IrisCodes bits
TLDR
This work focuses on locating and subsequently extracting the most consistent bit-locations from these binary iris features, and achieves this objective by initially constructing a Matching-Code vector from some specifically designated training IrisCodes, and subsequently forming a series of 1D clusters in them. Expand
Human-Aided Saliency Maps Improve Generalization of Deep Learning
TLDR
This work compares the accuracy and generalization of a state-of-the-art deep learning algorithm for a difficult problem in biometric presentation attack detection when trained on original images with typical data augmentations, and the same original images transformed to encode human judgement about salient image regions. Expand

References

SHOWING 1-10 OF 20 REFERENCES
Identity verification using iris images: Performance of human examiners
  • Kevin McGinn, S. Tarin, K. Bowyer
  • Computer Science
  • 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2013
TLDR
Results suggest that novice examiners can readily achieve accuracy exceeding 90% and can exceed 96% when they judge their decision as “certain”, and suggest that examiners may be able to improve their accuracy with experience. Expand
Human versus biometric detection of texture similarity in left and right irises
TLDR
There clearly is a similarity in the texture pattern of the left and right iris of the same person that can reliably be detected by novice observers with a brief viewing time. Expand
Iris recognition based on human-interpretable features
TLDR
This work proposes a new approach for detecting and matching iris crypts automatically, which outperforms the known visible feature based iris recognition method on two different datasets, by over 19% higher rank one hit rate in identification and over 46% lower equal error rate in verification. Expand
An assessment of the human performance of iris identification
TLDR
The results suggest that performance using the computer-based system is no better than performance of the human participants, but performance can be improved through incorporation of thehuman as a `second decision maker' and this fusion system yields a false acceptance rate of just 9% when disagreements are resolved in line with strengths of each `decision-maker'. Expand
Human iris recognition in post-mortem subjects: Study and database
TLDR
This study shows that post-mortem iris recognition is possible and occasionally works even 17 days after death, contradict a promulgated rumor that iris is unusable shortly after decease. Expand
How iris recognition works
  • J. Daugman
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2004
Algorithms developed by the author for recognizing persons by their iris patterns have now been tested in many field and laboratory trials, producing no false matches in several million comparisonExpand
Database of iris images acquired in the presence of ocular pathologies and assessment of iris recognition reliability for disease-affected eyes
TLDR
A database of iris images collected from disease affected eyes and an analysis related to the influence of ocular diseases on iris recognition reliability are presented, which obtained significantly worse genuine comparison scores for all iris matchers and all disease-affected eyes when compared to a group of healthy eyes. Expand
Genetically identical irises have texture similarity that is not detected by iris biometrics
TLDR
In experiments with human observers viewing pairs of iris images acquired using an iris biometric system, it is found that there is recognizable similarity in the left and right iris of an individual and in the irises of identical twins. Expand
Similarity of iris texture between identical twins
TLDR
It is found that untrained humans can classify pairs of twins with more than 81% accuracy using the appearance of the iris alone, without any proximal image content such as eyelashes, eyelids, or tear duct visible. Expand
Are iris crypts useful in identity recognition?
  • Feng Shen, P. Flynn
  • Computer Science
  • 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2013
TLDR
Although the inter-participant annotation consistency may be limited by crypts' noticeability, the intra-iris crypt perception is sufficiently consistent for nearly 95% of query images to be correctly identified. Expand
...
1
2
...