<p>Foliar diseases pose substantial obstacles to the health and productivity of vegetable crops and the prompt detection of their early symptoms is crucial for their successful management. Conventional diagnostic methods such as visual inspection, microscopy, serological and molecular methods suffer from limitations in terms of time requirements, subjectivity, and the level of expertise needed. Consequently, there has been a surge of interest in artificial intelligence (AI) techniques for automating and enhancing disease detection. This review provides an extensive exploration of various artificial intelligence (AI) techniques, such as machine learning, computer vision, and deep learning, and their practical implementations for detecting foliar diseases with a particular emphasis on the importance of early detection, precise quantification, and targeted intervention in vegetable crops. These approaches utilize diverse data sources, such as images and spectral reflectance, to achieve precise and reliable detection of foliar diseases. The review also delves into the challenges associated with acquiring datasets and emphasizes the importance of data annotation and curation. Furthermore, the review evaluates the performance of different AI models and algorithms, considering crucial factors such as accuracy, speed, and scalability. It underlines the need for user-friendly and cost-effective disease detection systems to promote wider adoption of AI-based approaches. In conclusion, this comprehensive analysis examines AI-based foliar disease detection in vegetable crops, while identifying research gaps and outlining future directions for sustainable agriculture and crop disease management.</p>