Search

The economic, social, cultural growth of most developing countries depends upon the agriculture sector. However, plant disease may lead to inferior crop yield economic growth. Various computer vision and artificial intelligence-based schemes have been presented in past for automatic plant leaf disease detection but their performance is inadequate due to underprivileged feature representation, lower-order correlation of raw features, data imbalance problem, less generalization. This paper presents automatic plant leaf disease detection using Deep Convolutional Neural Network (DCNN) to increase the feature representation and correlation and Generative Adversarial Network (GAN) for data augmentation to cope up with data imbalance problem. Extensive experimentations are performed on ten classes of tomato plant disease from Plant Village leaf disease database. Effectiveness of proposed scheme is evaluated based on accuracy, precision, recall, F1 score which has shown momentous improvement over customary methods for plant leaf disease database (Accuracy- 99.74%, precision- 0.99, recall-0.99, F1 score -0.99). [ABSTRACT FROM AUTHOR]