Enhanced Iris Recognition with Histogram Cut Selection and Genetic Algorithms for Robust Classification

Iris recognition is a critical component in biometric identification systems, known for its high accuracy and reliability. However, traditional methods often struggle with challenges related to feature extraction and classification, especially under varying conditions like lighting and occlusions. This paper addresses these challenges by proposing an enhanced iris recognition approach that combines Histogram Cut Selection (HCS) with Genetic Algorithms (GA). The HCS technique is employed for initial feature extraction and segmentation, which effectively isolates the most significant iris features while reducing noise and irrelevant data. Following this, Genetic Algorithms are applied to optimize the classification process by iteratively refining the decision boundaries, ensuring a robust and accurate recognition system. To further enhance segmentation accuracy, we introduce a recursive entropy discretization model. This model works in tandem with HCS to segment the iris with higher precision, leading to improved feature representation. The proposed method was tested on several benchmark iris datasets, demonstrating superior performance compared to traditional methods. Specifically, the recognition accuracy improved by 8.5%, and the computational efficiency increased by 15%, making this method highly suitable for real-time biometric identification applications. The integration of HCS with GA not only enhances the robustness of the system but also ensures its adaptability across different environments.