DenseNet Based Model for Plant Diseases Diagnosis

The biggest threat to the safety of food is plant diseases. They have ability dramatically lower quantity and quality agricultural products. Recognizing diseases issue in industries. Convolutional Neural Networks (CNN) are effective solving image classification problems computer vision. Numerous deep learning architectures been used diagnose This study presents a transfer learning-based model for identifying leaves. In this paper, CNN classifier based on called DenseNet201 proposed. An analysis four models (VGG16, Inception V3, ResNet152V2, DenseNet201) done see which one can detect with greatest degree accuracy. Web application developed disease diagnosing from defected leaf proposed identify give recommended treatment. images dataset contains 28310 leaves photos 3 crops, tomato, potato pepper divided into 15 different classes, 9 disorders healthy class 2 1 disorder pepper. our experimental, results shows that achieves highest training accuracy 99.44% validation 98.70%.