INVESTIGATING THE IMPACT OF DEGREE OF FREEDOM ON IRIS RECOGNITION ACCURACY: A COMPARATIVE ANALYSIS OF TRADITIONAL ALGORITHMS AND DEEP LEARNING TECHNIQUE

Abstract

Biometric identification relies heavily on iris recognition systems because of their high accuracy and dependability. In order to better understand how the degree of freedom affects iris recognition accuracy, this study compares state-of-the-art deep learning technique with conventional algorithms in-depth. This paper investigates the effects of different degrees of freedom on these system’s performance, taking precision, robustness, and adaptability into account. This comparative study compares the state-of-the-art deep learning approaches with classical algorithms based on well-established methodology. The goal of the study is to shed light on the advantages and disadvantages of each paradigm by offering a comprehensive knowledge of how various degrees of freedom affect iris identification accuracy. The research attempts to provide important insights into the ideal configuration of degrees of freedom for iris recognition systems, ultimately improving their overall performance and reliability through rigorous experimentation and methodical review.