The application of artificial intelligence in plant disease detection has become a critical tool in promoting precision agriculture and ensuring global food security. This research emphasises the use of state-of-the-art methods, including convolutional neural networks (CNNs), for distinguishing various plant diseases through image analysis. The approach involves robust image preprocessing and feature extraction techniques, enabling high performance in detecting diseases such as leaf blight, powdery mildew and rust across diverse plant types. Experimental results demonstrate the system’s efficacy, achieving an accuracy of 91.5%, precision of 94.5%, recall of 93.8% and an F1-score of 94.1%. The model’s robustness and adaptability to multiple datasets highlight its potential for wide-scale application in identifying plant diseases through tissue images, paving the way for advancements in precision agriculture and early disease management.