Grey Blight Disease Detection on Tea Leaves Using Improved Deep Convolutional Neural Network

Abstract

We proposed a novel deep convolutional neural network (DCNN) using inverted residuals and linear bottleneck layers for diagnosing grey blight disease on tea leaves. The proposed DCNN consists of three bottleneck blocks, two pairs of convolutional (Conv) layers, and three dense layers. The bottleneck blocks contain depthwise, standard, and linear convolution layers. A single-lens reflex digital image camera was used to collect 1320 images of tea leaves from the North Bengal region of India for preparing the tea grey blight disease dataset. The nongrey blight diseased tea leaf images in the dataset were categorized into two subclasses, such as healthy and other diseased leaves. Image transformation techniques such as principal component analysis (PCA) color, random rotations, random shifts, random flips, resizing, and rescaling were used to generate augmented images of tea leaves. The augmentation techniques enhanced the dataset size from 1320 images to 5280 images. The proposed DCNN model was trained and validated on 5016 images of healthy, grey blight infected, and other diseased tea leaves. The classification performance of the proposed and existing state-of-the-art techniques were tested using 264 tea leaf images. Classification accuracy, precision, recall, F measure, and misclassification rates of the proposed DCNN are 98.99%, 98.51%, 98.48%, 98.49%, and 1.01%, respectively, on test data. The test results show that the proposed DCNN model performed superior to the existing techniques for tea grey blight disease detection.

TeaDiseaseNet: multi-scale self-attentive tea disease detection

“…Therefore, there is an urgent need for research on rapid and precise methods for early detection of tea diseases. Implementing such methods would enable tea farmers to promptly implement control measures, prevent disease spread, protect the health of tea plantations, and promote the sustainable development of the tea industry ( Debnath et al., 2021 ; Lanjewar and Panchbhai, 2023 ; Pandian et al., 2023 ).…”

Enhancing Tea Disease Identification with Lightweight MobileNetV2

“…It has have been widely applied and achieved remarkable results in tea disease recognition. Pandian et al [11] proposed a Deep Convolutional Neural Network (DCNN) based on inverted residual and linear bottleneck layers for the diagnosis of tea grey blight disease, which can effectively identify the disease. Prabu et al [12] developed a real-time disease prediction system for tea diseases using CNN on the Platform-as-a-Service (PaaS) cloud.…”

“…(8)-(11), 𝑇𝑃 stands for true positive, 𝑇𝑁 indicates true negative, 𝐹𝑃 is false positive, and 𝐹𝑁 is false negative of the predicted class.…”

Classification of Tea Leaf Diseases Based on ResNet-50 and Inception V3

“…Farmers face obstacles because of the emergence of diseases that attack tea leaves. Tea leaf diseases are a constant source of worry because they have a direct impact on the product's quality and yield when the harvesting season begins (Pandian et al, 2023). Fungi, bacteria, algae, viruses, or bad environmental conditions are basically the causes of disease in tea leaves (Rosyidah et al, 2023).…”