An efficient novel approach for iris recognition based on stylometric features and machine learning techniques

This paper presents a novel iris recognition system based on machine learning methods. The motivation behind this research resides in the interrelatedness of biometric systems and stylometry, as shown in our previous research. The main goal of the proposed model is to reach virtually perfect classification accuracy, eliminate false acceptance rates, and cancel the possibility of recreating an iris image from a generated template. To achieve this, we omit Gabor wavelets and other filter banks typically employed in iris recognition systems based on the pioneering work of John Daugman. Instead, we employ machine learning methods that classify biometric templates as numeric features. The biometric templates are generated by converting a normalized iris image into a one-dimensional set of fixed-length codes, which then undergoes stylometric feature extraction. The extracted features are further used for classification. A new recognition method is developed using the CASIA iris database, and its generalizability is demonstrated on the MMU and IITD iris databases separately, and also on their unification with the CASIA database, by applying oversampling before and during the cross-validation procedure. The experimental evaluation shows that the system performs as intended. In addition, the computational costs are significantly decreased with respect to traditional systems, which in turn reduces the overall complexity of the recognition system, making it suitable for use in practical applications.