Biometric Verification System Using Hyperparameter Tuned Deep Learning Model Mohammad Yamin 1 , Saleh Bajaba 2 , Sarah B. Basahel 3 and E. Laxmi Lydia 4,* 1 Department of Management Information Systems, Faculty of Economics and Administration, King Abdulaziz University, Jeddah, 21589, Saudi Arabia 2 Department of Business Administration, Faculty of Economics and Administration, King Abdulaziz University, Jeddah, 21589, Saudi Arabia 3 Department of Management Information Systems, Faculty of Economics and Administration, King Abdulaziz University, Jeddah, Saudi Arabia 4 Department of Computer Science and Engineering, Vignan’ s Institute of Information Technology, Visakhapatnam, 530049, India *Corresponding Author: E. Laxmi Lydia. Email: elaxmi2002@yahoo.com Received: 29 July 2022; Accepted: 19 October 2022 Abstract: Deep learning (DL) models have been useful in many computer vision, speech recognition, and natural language processing tasks in recent years. These models seem a natural fit to handle the rising number of biometric recognition problems, from cellphone authentication to airport security systems. DL approaches have recently been utilized to improve the efficiency of various bio- metric recognition systems. Iris recognition was considered the more reliable and accurate biometric detection method accessible. Iris recognition has been an active research region in the last few decades due to its extensive applications, from security in airports to homeland security border control. This article presents a new Political Optimizer with Deep Transfer Learning Enabled Biometric Iris Recognition (PODTL-BIR) model. The presented PODTL-BIR technique recog- nizes the iris for biometric security. In the presented PODTL-BIR model, an initial stage of pre-processing is carried out. In addition, the MobileNetv2 feature extrac- tor is utilized to produce a collection of feature vectors. The PODTL-BIR techni- que utilizes a bidirectional gated recurrent unit (BiGRU) model to recognise iris for biometric verification. Finally, the political optimizer (PO) algorithm is used as a hyperparameter tuning strategy to improve the PODTL-BIR technique’ s recog- nition efficiency. A wide-ranging experimental investigation was executed to vali- date the enhanced performance of the PODTL-BIR system. The experimental outcome stated the promising performance of the PODTL-BIR system over other existing algorithms. Keywords: Biometric verification; iris recognition; political optimizer; deep learning; feature extraction 1 Introduction Biometric security resolved the hindrances of earlier computing days and over the globe prefer to utilize biometric recognition systems as an alternative solution to traditional password-based authentication This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Computer Systems Science & Engineering DOI: 10.32604/csse.2023.034849 Article ech T Press Science