DROWSINESS DETECTION IN DRIVERS: A MACHINE LEARNING APPROACH USING HOUGH CIRCLE CLASSIFICATION ALGORITHM FOR EYE RETINA IMAGES

Abstract

Driving has become one of the most important routine works in our everyday life. For many people it is difficult to imagine a life without driving. Accidents are a persistent and inevitable part of driving. Hence automatic drowsiness detection has become a major challenge in research perspective. In this research work, drowsiness detection technique has been implemented using machine learning (ML) techniques. In this methodology, a preprocessing, segmentation, feature extraction and classification steps to perform. This work proposed hough circle (HC) classification algorithm for detecting drowsiness of the eye retina images. The primary objective of this study is to evaluate the performance of the suggested hierarchical clustering method through the utilization of diverse metrics. According to the results of the performance evaluation, the suggested HC algorithm demonstrated a 90.8% accuracy rate, along with a minimal execution time and a lower error rate compared to existing algorithms. © 2025 selection and editorial matter, Jaiteg Singh, S B Goyal, Rajesh Kumar Kaushal, Naveen Kumar and Sukhjit Singh Sehra; individual chapters, the contributors.