Early Detection of Autism Spectrum Disorder in Children Using Facial Images and AI-Based Deep Learning Models

The condition in which an individual's communication abilities and social interactions are affected during early development is called autism spectrum disorder (ASD). Such people feel more anxious, react to emotions in different ways, and experience sounds, lights, or touch differently. Early diagnosis and timely interventions can significantly improve behavioural and language development. Traditional methods for ASD detection, such as subjective questionnaires and behavioural observations, are often time-consuming, costly, and reliant on specialized expertise, leading to a delay in intervention. To address these challenges, this work introduces a novel approach for the early identification and detection of ASD in children using facial images. The research focuses on utilizing YOLOv8n for facial features identification and ASD classification, harnessing its advanced object detection capabilities to enhance both accuracy and efficiency. This paper also presents a comparative analysis of YOLOv8n and YOLOv9c to conclude with the most effective solution. This study facilitates real-time ASD screening, providing healthcare professionals with timely and effective interventions in clinical environments.