A novel iris weight map method for less constrained iris recognition based on bit stability and discriminability
- Submitting institution
-
The University of Kent
- Unit of assessment
- 12 - Engineering
- Output identifier
- 6307
- Type
- D - Journal article
- DOI
-
10.1016/j.imavis.2016.05.003
- Title of journal
- Image and Vision Computing
- Article number
- -
- First page
- 168
- Volume
- 58
- Issue
- -
- ISSN
- 0262-8856
- Open access status
- Not compliant
- Month of publication
- May
- Year of publication
- 2016
- URL
-
https://kar.kent.ac.uk/53325/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to introduce a method for iris matching which improves recognition in less constrained environments by introducing noise and quality deterioration in the images. The method considers both intra-class stability and inter-class discriminability of the resulting iris codes. Extensive experimental evidence from publicly available datasets in varying conditions demonstrate that our method achieves significant improvements compared to state-of-the-art methods enabling realistic expectations for industrial adoption.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
