Iris Feature Extraction and Matching Method for Mobile Biometric Applications

Abstract

Biometric methods are increasingly penetrating the field of mobile applications, confronting researchers with a huge number of problems that have not been considered before. Many different interaction scenarios in conjunction with the mobile device performance limitations challenge the capabilities of on-board biometrics. Saturated with complex textural features the iris image is used as a source for the extraction of unique features of the individual that are used for recognition. The mentioned features inherent to the interaction with the mobile device affect not only the source image quality but natural deformations of the iris leading to high intra-class variations and hence reducing the recognition performance. A novel method for iris feature extraction and matching is represented in this work. It is based on a lightweight CNN model combining the advantages of a classic approach and advanced deep learning techniques. The model utilizes shallow and deep feature representations in combination with characteristics describing the environment that helps to reduce intra-class variations and as a consequence the recognition errors. It showed high efficiency on the mobile and a few more datasets outperforming state-of-the-art methods by far.