Matching Cross-Domain Iris Images

Development of accurate cross-domain iris matching capability requires advanced and adapted learning capability to achieve accurate matching. A new approach to effectively and accuratevely match such images is described in reference [1]. The implementation codes to reproduce the results in this paper can be downloaded from this webpage.

Implementation Codes

This implementation codes to reproduce the matching results on three publicly available iris database can be downloaded here. The parameters for the algoriithm is also available in the same zip file.

This implementation code is provided for academic usage and is available on as-it-is basis. The commercial use/distribution of these codes is strictly prohibited. All the technical reports and papers that report experimental results from these implementation codes should provide due acknowledgement and reference to [1].

References

[1] N. Pattabhi Ramaiah and Ajay Kumar, "Towards more accurate iris recognition using bi-spectral imaging and cross-spectral matching capability,” Under Review, Dec. 2015.