A New Design of Iris Recognition Using Hough Transform with K-Means Clustering and Enhanced Faster R-CNN

Abstract

Iris recognition method is the most significant biometric modality for human identification. Currently, multiple deep structured architectures have been employed in biometric recognition with various features like robust generalization ability, high accuracy, and automatic learning. It is also considered as a more emerging area in biometrics along with machine learning approaches. Deep CNN is a conventional approach of image processing broadly utilized in several fields, however, it is simply influenced by slight disturbances and also includes bad anti-noise capacity in image classification. The major scope of this work is to implement adaptive deep learning-aided iris recognition. The key contribution of this paper relies on enhancing iris segmentation and iris recognition. Initially, the iris images are pre-processed, which are subjected to segmentation. The segmentation approach focuses on a Hough transform with K-Means Clustering (HT-KMC). Once the segmentation of the iris is done, the “Enhanced Faster Region-Convolutional Neural Network (E-Faster-RCNN)” is developed for the recognition purpose. The number of suitably hidden neurons of the conventional Faster-RCNN is optimized by the Adaptive-Sail Fish Optimization (ASFO) algorithm to obtain the highest efficiency. The simulation findings of the recommended approach proved that the method is effective in iris recognition by experimenting on a benchmark dataset.