No abstract

This paper considers three issues that arise in creating an algorithm for the robust detection of textured contact lenses in iris recognition images. The first issue is whether the accurate segmentation of the iris region is required in order to achieve the accurate detection of textured contact lenses. Our experimental results suggest that accurate iris segmentation is not required. The second issue is whether an algorithm trained on the images acquired from one sensor will well generalize to the images acquired from a different sensor. Our results suggest that using a novel iris sensor can significantly degrade the correct classification rate of a detection algorithm trained with the images from a different sensor. The third issue is how well a detector generalizes to a brand of textured contact lenses, not seen in the training data. This paper shows that a novel textured lens type may have a significant impact on the performance of textured lens detection.INDEX TERMS Biometrics, machine learning, image processing, image classification, image texture analysis.

The use of an artificial replica of a biometric characteristic in an attempt to circumvent a system is an example of a biometric presentation attack. Liveness detection is one of the proposed countermeasures, and has been widely implemented in fingerprint and iris recognition systems in recent years to reduce the consequences of spoof attacks. The goal for the Liveness Detection (LivDet) competitions is to compare software-based iris liveness detection methodologies using a standardized testing protocol and large quantities of spoof and live images. Three submissions were received for the competition Part 1The best results from across all three datasets was from Federico with a rate of falsely rejected live samples of 28.6% and the rate of falsely accepted fake samples of 5.7%.

Automatic detection of textured contact lenses in images acquired for iris recognition has been studied by several researchers. However, to date, the experimental results in this area have all been based on the same manufacturer of contact lenses being represented in both the training data and the test data and only one previous work has considered images from more than one iris sensor. Experimental results in this work show that accuracy of textured lens detection can drop dramatically when tested on a manufacturer of lenses not seen in the training data, or when the iris sensor in use varies between the training and test data. These results suggest that the development of a fully general approach to textured lens detection is a problem that still requires attention.

No abstract