Symptom recognition of disease and insect damage based on Mask R-CNN, wavelet transform, and F-RNet

Abstract

Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.

A deep learning model for rapid classification of tea coal disease

“…It was consistent with prior research findings. In our team’s study by Li et al [ 29 ], five models, F-RNet, ResNet18, VGG16, AlexNet and SVM, were developed to identify three tea pests and disease symptoms. The results showed that the deep learning models such as ResNet18, VGG16 and AlexNet had 82%, 80% and 73% accuracy, respectively, which were significantly greater than the SVM machine learning model with 65% accuracy.…”

“…To better extract the feature information of the leaves of tea coal disease, the images of the diseased leaves were enhanced by wavelet transform. [ 29 ]This is because the wavelet transform enhancement processing applied in previous studies has made good progress in improving model accuracy, and the model has strong generalization ability and is suitable for tea tree disease classification. Wavelet transform can reduce or remove the correlation between different features of the extracted diseased leaf images by selecting appropriate filters.…”

“…The “FP” (False Positive) is the number of samples incorrectly identified as tea coal disease. The “TN” (True Negative) is the number of samples correctly identified as health samples [ 29 ].…”

Review of the application of in-situ sensing techniques to address the tea growth characteristics from leaf to field

“…Figure 2 Technique role of tea plant monitoring on leaf-scale [6,11,12] RNet) based on R-CNN and wavelet trans-form on RGB images to identify the diseases and pests of tea leaves. Karmokar et al [14] developed a tea leaf disease identifier that integrates a neural network to recognize diseases by extracting features from tea leaf images.…”

Highly Accuracy and Lightweight Detection of Apple Leaf Diseases Based on YOLO

“…Singh [8] used multilayer convolutional network MCNN to classify mango anthracnose leaf disease with 97.3% accuracy. He [9] proposed a Mask-RCNN based model for detecting leaf diseases of tea tree with F1 scores of 88.3% and 95.3% for tea coal diseases and boll weevil leaf diseases, but the F1 scores was lower in distinguishing between brown leaf disease and target spot disease, with scores of only 61.1% and 66.6%. The analysis showed that the two-stage detection model needs to generate candidate frames before target classification and bounding box regression, which is difficult to apply because of high model complexity, slow speed, and low accuracy, although it can identify crop diseases.…”