Automatic Recognition of Rice Leaf Diseases Using Transfer Learning

Rice, the world’s most extensively cultivated cereal crop, serves as a staple food and energy source for over half of global population. A variety abiotic biotic factors such weather conditions, soil quality, temperature, insects, pathogens, viruses can greatly impact quantity quality rice grains. Studies have established that plant infections significant on crops, resulting in substantial financial losses agriculture. To accurately diagnose manage diseases affecting plants, pathologists are seeking efficient reliable methods. Traditional disease detection techniques, employed by farmers, involve time-consuming visual inspections result inadequate farming practices. With advancements agricultural technology, identification pathogenic organisms plants has become significantly more manageable through techniques machine learning deep learning, which receiving attention crop research. In this paper, we used transfer approach 15 pre-trained CNN models automatic Rice leave diseases. Results showed InceptionV3 model is outperforming with an average accuracy 99.64% Precision, Recall, F1-Score, Specificity 98.23, 98.21, 98.20, 99.80, AlexNet resulted poor performance 97.35% among others.