A novel approach to iris recognition at-a-distance: leveraging BW-CNN framework

• Published in: Engineering Research Express Vol. 6; no. 4; pp. 45225 - 45238
• Main Authors: Shirke, Swati, Midhunchakkaravarthy, Divya, Deshpande, Vivek
• Format: Journal Article
• Language: English
• Published: IOP Publishing 01.12.2024
• Subjects: accuracy; BW-CNN; BWO; iris recognition; precision; ScaT-LOOP
• ISSN: 2631-8695; 2631-8695
• DOI: 10.1088/2631-8695/ad8722

This paper introduces a novel iris recognition framework by integrating the Black Widow Optimization (BWO) algorithm with Convolutional Neural Networks (CNNs), forming the Black Widow-CNN (BW-CNN) framework. The necessity of this work stems from the increasing demand for secure and reliable biometric systems, particularly in iris recognition, which has become a critical tool in sectors such as national security, financial transactions, and contactless access controls. Traditional iris recognition systems face significant limitations under varying environmental conditions and subject distances, often compromising accuracy. The proposed BW-CNN framework is necessary as it addresses these challenges by offering a robust solution capable of precise iris detection even at a distance and in challenging real-world conditions. This approach enhances feature extraction and classification accuracy and streamlines the recognition process. The experimental results, evaluated across multiple datasets, demonstrate the superior performance of the BW-CNN framework over existing methods, showcasing its potential for deployment in high-security and real-time applications.