Search

The citrus family provides healthy fruits to humans. The quality and quantity of the citrus fruits depend on the quality of the citrus leaves. Due to the diseases of citrus leaves, the quality and productivity of citrus fruit are degraded. This paper provides a computer automation system to detect the diseases of the citrus leaves using machine learning and deep learning techniques. In this paper, images of citrus leaves are captured using an Android Smartphone in natural environmental light. Three different classes of citrus leaves are collected using the Smartphone and destructive method. These are citrus healthy, citrus greening, and citrus CTV (Citrus Tristeza virus). Citrus images are processed for image resizing, image noise removal, image enhancement, and feature extraction. Features of the images are calculated using Gray Level Co-occurrence Matrix in the color and gray domain of the images. Finally, the detection and classification are done using K- Nearest Neighbor (KNN) and Deep Neural Network (DNN) classifier. The accuracy of the KNN classifier is 89.9% for the K value 3 whereas the accuracy of DNN is 99.89% with an error of 0.0219. The proposed system helps the farmer to detect diseases at an early stage.

Experts help farmers to diagnose the citrus diseases by using agriculture laboratories or viewing the visual symptoms. These methods may not be accessible to all the farmers due to the expert’s cost and non-availability of laboratories. The proposed work presents the comparison of two different Convolutional Neural Network (CNN) architectures to classify diseases of the citrus leaf. In this paper, two types of CNN architectures, such as MobileNet and Self-Structured (SSCNN) classifiers were used to detect and classify citrus leaf diseases at the vegetative stage. The proposed work prepared a smartphone image based citrus disease dataset. Both the models were trained and tested on the same citrus dataset. The performances of the models were evaluated using the accuracy and loss of the training and validation sets, respectively. The best training accuracy of the MobileNet CNN was 98% with 92% validation accuracy at the epoch 10. But the best training accuracy of the SSCNN was 98% with 99% validation accuracy at the epoch 12. The proposed system indicates that the SSCNN is more helpful and accurate for smartphone image based citrus leaf disease classification. In addition, the SSCNN algorithm takes less computation time as compared to MobileNet and it can be considered a cost-effective method for citrus disease detection.