A Benchmark for Iris Location and a Deep Learning Detector Evaluation

TL;DR

This paper introduces a benchmark dataset for iris location, compares classical and deep learning methods, and demonstrates that a YOLO-based detector outperforms traditional approaches in accuracy and speed.

Contribution

The work provides a publicly available annotated iris dataset and evaluates multiple iris location methods, highlighting the superiority of deep learning approaches.

Findings

Deep learning detector outperforms classical methods in accuracy.

Deep learning detector is faster with GPU implementation.

Benchmark datasets enable standardized evaluation of iris location methods.

Abstract

The iris is considered as the biometric trait with the highest unique probability. The iris location is an important task for biometrics systems, affecting directly the results obtained in specific applications such as iris recognition, spoofing and contact lenses detection, among others. This work defines the iris location problem as the delimitation of the smallest squared window that encompasses the iris region. In order to build a benchmark for iris location we annotate (iris squared bounding boxes) four databases from different biometric applications and make them publicly available to the community. Besides these 4 annotated databases, we include 2 others from the literature. We perform experiments on these six databases, five obtained with near infra-red sensors and one with visible light sensor. We compare the classical and outstanding Daugman iris location approach with two window based detectors: 1) a sliding window detector based on features from Histogram of Oriented Gradients (HOG) and a linear Support Vector Machines (SVM) classifier; 2) a deep learning based detector fine-tuned from YOLO object detector. Experimental results showed that the deep learning based detector outperforms the other ones in terms of accuracy and runtime (GPUs version) and should be chosen whenever possible.