Tomato Plant Diseases Classification Using Deep Learning Based Classifier From Leaves Images
Sultana Umme Habiba, Md. Khairul Islam
Abstract
In most agricultural countries, farmers face a great loss every year due to diseases in crops. So, early detection of tomato plant diseases has achieved a great concern of the researchers. In this paper a deep convolutional neural network model is used to recognize unhealthy plants from the healthy plants and to classify the tomato plant diseases. We have used VGG16 deep cnn classifier to recognize unhealthy plants and their diseases from the images of tomato plants. We have used Plant Village dataset which contains ten different classes of tomato leaf images including healthy plants. Using transfer learning method in a pre-trained VGG16 model, this dataset shows a satisfying classification performance which about 95.5%. Top 2 accuracy of this model reaches to 99% to recognize tomato plant diseases. Without using any segmentation or preprocessing of leaves images our trained model shows a performance of approximately 100% to differentiate unhealthy plants from healthy plants.