Rice Leaf Disease Detection Using Deep Learning Models: A Comprehensive Approach

Rice serves as a primary food source for more than half of the global population. However, a range of diseases brought on by pathogens, including as bacteria, viruses and fungus are posing a growing threat to rice agriculture. These diseases have the potential to seriously reduce crop productivity and threaten food security. Conventional disease detection techniques mostly depend on the labor-intensive, time consuming and frequently prone to human error manual inspection performed by qualified agronomists. We concentrate on two cutting edge architectures: Vision Transformers (ViT) and DenseNet169, which is well-known for its high accuracy in image classification applications and efficiency in feature reuse which make use of self-attention mechanisms to identify complex patterns in images. We developed these models to precisely categorize various rice leaf diseases, including Bacterial Leaf Blight, Brown Spot, Leaf Blast, Leaf Scald, Narrow Brown Spot, Neck Blast, Rice Hispa, Sheath Blight, Tungro, and healthy leaves. This was achieved using a comprehensive dataset containing 15,910 annotated images of rice leaves. Our proposed systems improve crop management practices by enabling prompt interventions based on precise predictions but it helps to guarantee ensuring global food security and maximizing overall crop yield. This study highlights the revolutionary potential of artificial intelligence in agriculture, paving the way for further advancements that can enhance sustainability and productivity.