Plant Disease Diagnosis and Image Classification Using Deep Learning

Abstract

Indian agriculture is striving to achieve sustainable intensification, the system aiming to increase agricultural yield per unit area without harming natural resources and the ecosystem. Modern farming employs technology to improve productivity. Early and accurate analysis and diagnosis of plant disease is very helpful in reducing plant diseases and improving plant health and food crop productivity. Plant disease experts are not available in remote areas thus there is a requirement of automatic low-cost, approachable and reliable solutions to identify the plant diseases without the laboratory inspection and expert's opinion. Deep learning-based computer vision techniques like Convolutional Neural Network (CNN) and traditional machine learning-based image classification approaches are being applied to identify plant diseases. In this paper, the CNN model is proposed for the classification of rice and potato plant leaf diseases. Rice leaves are diagnosed with bacterial blight, blast, brown spot and tungro diseases. Potato leaf images are classified into three classes: healthy leaves, early blight and late blight diseases. Rice leaf dataset with 5932 images and 1500 potato leaf images are used in the study. The proposed CNN model was able to learn hidden patterns from the raw images and classify rice images with 99.58% accuracy and potato leaves with 97.66% accuracy. The results demonstrate that the proposed CNN model performed better when compared with other machine learning image classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree and Random Forest.

An Industrial-Grade Solution for Crop Disease Image Detection Tasks

“…Even the accuracy of the YOLO V5 model used by Mathew and Mahesh (2022) was 4.8% lower than our study. By comparing the model accuracy of the different number of disease categories, the model accuracy of Zhang et al (2020), Gao et al (2021), Sharma et al (2021), Zhao et al (2021), and Al-Wesabi et al ( 2022) is higher than our results, which is due to the smaller number of disease categories (up to 10 categories). Our study required the identification of up to 59 plant disease categories, which exceeded at least 85% of the disease categories in other studies and reduced the accuracy by up to 4.5% relative to other studies.…”

“…Afzaal et al ( 2021 ) reported the studies obtained using classical convolutional neural networks, namely GoogleNet, VGGNet, and EfficientNet, to identify potato leaf diseases at different growth stages. Sharma et al ( 2021 ) proposed a CNN model for rice and potato leaf disease classification, which was able to classify rice images and potato leaves with 99.58% accuracy, outperforming other advanced machine learning image classifiers, such as SVM, KNN, decision trees, and random forests. To demonstrate the feasibility of deep learning algorithms based on an encoder-decoder architecture for semantic segmentation of potato late blight spots based on field images, Gao et al ( 2021 ) used a SegNet-based encoder-decoder neural network architecture for lesion segmentation, which can extract semantic features from low to high level, in a disease test dataset with leaves and soil in the background to intersect and union (IOU) values of 0.996 and 0.386, respectively.…”

Comparing machine learning and deep learning classifiers for enhancing agricultural productivity: case study in Larache Province, Northern Morocco

“…The following are our main contributions to this study: − This study compares five machine learning models and five deep learning models to classify mint plant diseases in order to find the best classifier in the case of disease detection. − From literature reviews, various works reached that deep learning performed well in plant disease detection [9], [10]. Hence, this study proves and supports the previous works that DL is the best choice in analyzing the most important features affecting the detection and treatment of serious diseases versus ML since DL can perform feature extraction on its own.…”

A Mixed Method for Feature Extraction Based on Resonance Filtering

“…Some scholars are devoted to the study of image feature extraction [1,2]. Feature extraction can be used for image classification [3,4], image segmentation [4][5][6][7], target detection [8][9][10][11], attention mechanism of the visual system [11][12][13][14][15][16] and other research directions. Images have individual features and common features, which are adversarial and interdependent in image recognition.…”