Iris Codes Classification Using Discriminant and Witness Directions

TL;DR

This paper proposes a neural network approach to improve iris recognition accuracy by better separating intra- and inter-class score distributions, enhancing biometric decision-making.

Contribution

It introduces a neural training model that effectively addresses natural fuzzification in iris code classification, improving score separation.

Findings

Neural support enhances separation of score distributions.

Improved biometric decision accuracy.

Neural model outperforms traditional methods.

Abstract

The main topic discussed in this paper is how to use intelligence for biometric decision defuzzification. A neural training model is proposed and tested here as a possible solution for dealing with natural fuzzification that appears between the intra- and inter-class distribution of scores computed during iris recognition tests. It is shown here that the use of proposed neural network support leads to an improvement in the artificial perception of the separation between the intra- and inter-class score distributions by moving them away from each other.