Potato Plant Leaf Disease Detection using optimized CNN and Transfer Learning

The plant disease is a significant concern in the agriculture field. Many diseases destroy the crop badly. Optimized Convolutional neural network (CNN) model having seven convolutional layer with weight pruning is used for detecting disease on potato leaves. Further transfer learning is used to compare the results of the proposed model. Plant Village dataset which contains potato disease-Early blight and late blight is used. Both the diseases are fungaldiseases. Used transfer learning models are Resnet50, VGG16 and VGG19.