AI-Based Arecanut Quality Grading and Disease Detection Using Deep Learning

Arecanut is an economically important plantation crop widely cultivated in India and Southeast Asia. The quality grading of arecanut plays a critical role in determining its market value. Traditional grading processes rely on manual inspection performed by experienced workers, which often leads to inconsistencies, subjectivity, and inefficiency in large-scale processing environments. Additionally, early detection of diseases affecting arecanut plants is essential for improving crop yield and preventing economic losses. This research proposes an Artificial Intelligence (AI)-based system for automated arecanut quality grading and disease detection using deep learning techniques. The proposed framework utilises Convolutional Neural Networks (CNNs) to classify arecanut images into different quality categories and detect disease symptoms. A dataset of approximately 1,000 images was collected from agricultural farms, local markets, and publicly available sources, spanning four classes: high-quality, medium-quality, low-quality, and diseased samples. Image preprocessing techniques including resizing, normalisation, and data augmentation were applied to enhance model performance. Experimental results demonstrate that the proposed CNN model achieves a classification accuracy of 94.2%, effectively identifying disease patterns and quality grades.