Plant Disease Identification Based on Encoder–Decoder Model

Identifying plant diseases has been mainstay in any farming and agricultural activity since time immemorial. The most common method has been visually assessing the plants by experts to identify the diseases of the plants and recommending pesticides and chemicals which can be used to treat diseases in plants. Technologies like mobile apps have brought about advancements to this traditional method of identifying and addressing plant diseases. Although there are now a plethora of mobile apps aiding farmers with addressing the issue of plant diseases, there is a scarcity of studies that explore the strategies that are being employed by these apps. This paper identifies the strategies that are being used by mobile apps in plant disease identification to set a foundation for further studies with regards to this field. This is performed through analyzing mobile apps on both Google Play Store and Apple Store, through the description given by the developers and the use of the installed apps to determine the content offered and how it aids farmers in identifying curbing plant diseases. The findings using the inclusion and exclusion criteria that was set showed that overall, they are a few mobile apps in plant pest and disease identification with 152 apps only examined. The database strategy was identified as the most used strategy by developers with 78 mobile apps and the AI Diagnostics was the second most used strategy with 26 mobile apps from both the Google Play Store and Apple App Store combined.

With the rapid development of precision agriculture and smart agriculture, the need to build an automatic identification and detection system for diseases and insect pests is increasing. Using computers to correctly label plant diseases and insect pests is an important prerequisite for achieving accurate classification of plant diseases and insect pests and ensuring system performance. In order to improve the accuracy of computer classification of plant pests and diseases, this paper proposes an automatic pest identification method based on the Vision Transformer (ViT). In order to avoid training overfitting, the plant diseases and insect pests data sets are enhanced by methods such as Histogram Equalization, Laplacian, Gamma Transformation, CLAHE, Retinex-SSR, and Retinex-MSR. Then use the enhanced data set to train the constructed ViT neural network, so as to realize the automatic classification of plant diseases and insect pests. The simulation results show that the constructed ViT network has a test recognition accuracy rate of 96.71% on the plant disease and insect pest public data set Plant_Village, which is about 1.00% higher than the Plant disease and pest identification method based on traditional convolutional neural networks such as GoogleNet and EfficentNetV2.

The aim of this article to introduces various image processing and machine learning techniques used to identify plant diseases based on images of diseased plants in order to recognize disease in plants from images and necessary in image processing and machine learning as they apply to the identification and categorization of plant diseases. We meticulously review more content and provide important standards. These characteristics include things like the size of the photo collection, preprocessing, segmentation techniques, classifier types, classifier resolution, and other things. To suggest and arrange our work on the classification and identification of plant diseases, we explain our study here. Then, based on the principal technical solution used in the method, each of these groups is split using machine learning techniques. Photos of plant disease samples were processed using support vector (SVM) and k-mean clustering techniques to extract color and texture information. The results show that the SVM classifier is a very good tool for detecting and identifying plant-borne diseases in agricultural crops.

Plant diseases are responsible for economic loss in agricultural industry, as they destroy the crops. Although pesticides have been used to modify crop production, the excess amount of use of pesticides affects the environment negatively. Hence detection of diseases and differentiating it from nutritional deficiency has a considerable impact in deciding the requirement of pesticides. The conventional methods for plant diseases identification involve tedious chemical processes to be carried out in the laboratory and is also time consuming. This paper presents an automated system for identification and classification of plant diseases using Machine Learning (ML) and image processing technique. The feature extraction method is applied on images for training the algorithm. The skill of different Machine Learning algorithms is evaluated using the training data to find the best suiting algorithm for disease identification. The test folder contains the unseen images and is used for validating the performance of system in identification of plant diseases. The overall accuracy of the system is 95 percent. The system can be trained with large amount of images and yields accurate results at a faster rate.

This paper is intended to explore the research done on identifying the diseased plants and crops using Machine Learning (ML) and Deep Learning (DL) techniques during last 10 years using bibliometric methods. In this study, we used Scopus database to analyze on “Plant disease” or “Crop disease” using “Machine Learning” or “Deep Learning” or “Neural Networks”. This paper focuses on the importance of ML and DL techniques in identifying plant or crop diseases. The database collected from the Scopus is analyzed using VOSviewer software of version 1.6.16. The study is limited to publications from conferences, journals with subject areas are limited to Computer Science, Engineering and languages limited to English and Chinese. Scopus search outputs 824 articles on Plant or Crop diseases with ML, DL and Neural Networks covering conference papers and journal articles. Statistics showed that more articles were published during the last five years and major contributions were from India. By analyzing database on Authors, Subject area, Keywords, Affiliation, Source type it is evident that there is plenty of research scope in this area. Network analysis on diverse parameters specifies that there is a good scope to do research in this topic using advanced deep learning techniques.

In order to mitigate decreases in agricultural yield and production, the identification of diseases in plants assumes paramount importance. The agricultural sector has been employing various methodologies rooted in machine learning and image processing to address these challenges. This comprehensive analysis focuses specifically on the detection of diseases in rice plants by leveraging a diverse array of machine learning and image processing techniques with input images of infected rice plants. Furthermore, we delve into significant concepts pertaining to machine learning and image processing that aid in the identification and categorization of plant diseases. Various classification methods such as the k-Nearest Neighbor Classifier (KNN), Support Vector Machine (SVM), Probabilistic Neural Network (PNN), Genetic Algorithm (GA), and others find applications in agricultural research endeavors. The selection of an appropriate classification method assumes critical importance as the quality of the output is contingent on the input data. The classification of plant leaf diseases finds utility across multiple domains, including agriculture and biological research. This paper presents an extensive exploration of rice plant diseases, encompassing aspects such as image dataset size, preprocessing techniques, segmentation methods, and classifiers.

Among the major occupational sectors around the world, agriculture has the highest level of involvement. Every year, this sector faces a substantial loss in production and profit due to a large number of diseases in crops and plants. If those diseases are not detected early and taken measures for prevention, it can bring about a devastating result that can financially burden agriculture personnel. Traditional methods of detecting diseases in plants and crops offer high accuracy. However, the procedure is time-consuming, which might be insidious in most cases. Crop diseases need to be detected and cured as soon as possible as most diseases are highly contagious among crops and plants. In this paper, we have used the transfer learning approach with three pre-trained models: EfficientNetV2L, MobileNetV2, and ResNet152V2, to detect various plant diseases. We have proposed a framework to detect 38 types of leaf diseases in 14 different plants, compared the three pre-trained models based on various quantitative performance evaluation parameters, and demonstrated that EfficientNetV2L performed best with 99.63% accuracy. In the end, Explainable Artificial Intelligence (XAI) technique: LIME has been implemented in our model to understand the insight view of the model EfficeintNetV2L's for such prediction. It is used to make our model's predictions more reliable and gives a clear explanation about the reason of such decision.

Plant diseases and pests have always been major contributors to losses that occur in agriculture. Currently, the use of deep learning-based convolutional neural network models allows for the accurate identification of different types of plant diseases and pests. To enable more efficient identification of plant diseases and pests, we design a novel network architecture called Dise-Efficient based on the EfficientNetV2 model. Our experiments demonstrate that training this model using a dynamic learning rate decay strategy can improve the accuracy of plant disease and pest identification. Furthermore, to improve the model's generalization ability, transfer learning is incorporated into the training process. Experimental results indicate that the Dise-Efficient model boasts a compact size of 13.3 MB. After being trained using the dynamic learning rate decay strategy, the model achieves an accuracy of 99.80% on the Plant Village plant disease and pest dataset. Moreover, through transfer learning on the IP102 dataset, which represents real-world environmental conditions, the Dise-Efficient model achieves a recognition accuracy of 64.40% for plant disease and pest identification. In light of these results, the proposed Dise-Efficient model holds great potential as a valuable reference for the deployment of automatic plant disease and pest identification applications on mobile and embedded devices in the future.

Identification of plant diseases and advice on crops are essential duties for agricultural businesses. The use of algorithms based on deep learning and machine learning has become crucial due to the rising demand for food supply and the need to maximize agricultural yields. In this article, we suggest a paradigm for the use of the machine and deep learning methods to identify plant illnesses and to prescribe crops and fertilizers. The framework consists of three main components: plant disease identification, crop recommendation, and fertilizer recommendation. In the plant disease identification component, we use the image classification technique to identify the type of disease affecting the plant based on its symptoms. We then use deep learning algorithms such as convolutional neural networks (CNNs) to classify the disease accurately. In the crop recommendation and fertilizer recommendation components, we use regression algorithms to predict the yield of crops based on various factors such as soil type, climate, and the presence of plant diseases. The results of our experiments demonstrate the efficiency of our framework in accurately identifying plant diseases and recommending crops with high yields. Our approach can help farmers make informed decisions about the crops they should grow, and the diseases they should be aware of, leading to better crop yields and reduced crop losses

With the development of plant phenomics, the identification of plant diseases from leaf images has become an effective and economic approach in plant disease science. Among the methods of plant diseases identification, the convolutional neural network (CNN) is the most popular one for its superior performance. However, CNN's representation power is still a challenge in dealing with small datasets, which greatly affects its popularization. In this work, we propose a new method, namely PiTLiD, based on pretrained Inception-V3 convolutional neural network and transfer learning to identify plant leaf diseases from phenotype data of plant leaf with small sample size. To evaluate the robustness of the proposed method, the experiments on several datasets with small-scale samples were implemented. The results show that PiTLiD performs better than compared methods. This study provides a plant disease identification tool based on a deep learning algorithm for plant phenomics. All the source data and code are accessible at https://github.com/zhanglab-wbgcas/PiTLiD.

The agriculture industry significantly contributes to economic and population growth through the provision of high-quality food. Plant diseases decrease crop yields, which directly influences food production systems and leads to economic losses. Insufficient diagnosis and treatment of plant diseases can significantly affect agricultural productivity. Accurate identification is essential in order to prevent a severe decline in agricultural yield. Automatic detection models are crucial for accurate plant disease prediction and effective agricultural disease management. Deep Learning (DL) models are in great demand right now for identifying plant diseases because of how well they can anticipate and improve farmers’ crop yields. This study examines various DL algorithms for visual data-based plant disease detection and classification in great detail. Firstly, a brief overview is provided on various plant disease identification and classification systems developed by researchers, which utilize DL algorithms. Subsequently, a comprehensive analysis is undertaken to get deeper insights into the constraints of current algorithms and propose an innovative methodology for categorizing various forms of plant diseases, thereby contributing to the enhancement of agricultural output.

Plant fungal diseases are one of the most important causes of crop yield losses. Therefore, plant disease identification algorithms have been seen as a useful tool to detect them at early stages to mitigate their effects. Although deep-learning based algorithms can achieve high detection accuracies, they require large and manually annotated image datasets that is not always accessible, specially for rare and new diseases. This study focuses on the development of a plant disease detection algorithm and strategy requiring few plant images (Few-shot learning algorithm). We extend previous work by using a novel challenging dataset containing more than 100,000 images. This dataset includes images of leaves, panicles and stems of five different crops (barley, corn, rape seed, rice, and wheat) for a total of 17 different diseases, where each disease is shown at different disease stages. In this study, we propose a deep metric learning based method to extract latent space representations from plant diseases with just few images by means of a Siamese network and triplet loss function. This enhances previous methods that require a support dataset containing a high number of annotated images to perform metric learning and few-shot classification. The proposed method was compared over a traditional network that was trained with the cross-entropy loss function. Exhaustive experiments have been performed for validating and measuring the benefits of metric learning techniques over classical methods. Results show that the features extracted by the metric learning based approach present better discriminative and clustering properties. Davis-Bouldin index and Silhouette score values have shown that triplet loss network improves the clustering properties with respect to the categorical-cross entropy loss. Overall, triplet loss approach improves the DB index value by 22.7% and Silhouette score value by 166.7% compared to the categorical cross-entropy loss model. Moreover, the F-score parameter obtained from the Siamese network with the triplet loss performs better than classical approaches when there are few images for training, obtaining a 6% improvement in the F-score mean value. Siamese networks with triplet loss have improved the ability to learn different plant diseases using few images of each class. These networks based on metric learning techniques improve clustering and classification results over traditional categorical cross-entropy loss networks for plant disease identification.

Disease identification of plants has been proved to be beneficial for agro industries, research, and environment. Due to the era of industrialization, vegetation is shrinking. Early detection of diseases by processing the image of the leaf can be rewarding and helpful in making our environment healthier and green. Data clustering is an unsubstantiated learning technology where pattern recognition is used extensively to identify diseases in plants and its main cause. The objective is divided into two components. First, the identification of the symptoms on the basis of primary cause using K-mean. Second, validating the clusters using Elitist based Teaching Learning Based Optimization (ETLBO), and finally comparing existing models with the proposed model. Implementation involves relevant data acquisition followed by preprocessing of images. It is followed by feature extraction stage to get the best results in further classification stage. A K-mean and ETLBO algorithms are used for identification and clustering of diseases in plants. The implementation proves the suggested technique demonstrates better results on the basis of Histogram of Gradient (HoG) features. The chapter is organized as follows. In the introduction section, we have briefly explained about the existing and proposed methods. In the proposed approach section, different methods have been discussed in training and testing phases. The next section describes the algorithms used in the proposed approach followed by the experimental setup section. At the end, we have discussed analysis and comparison of experimental results. The outcome of the proposed approach provides the promising results in identification and verification of the spots disease in the plants.

To further the progress of sustainable development and solve real-life problems we have seen many processes are applied in our life, like artificial intelligence and decision-making. Morocco is one of the countries that rely heavily on agriculture and food production. So, food production is considered the basic needs of a human being for that we have seen fast advancements in agriculture productivity to meet the projected demand. However, with the time passing by, all species of plants are subjected to various types of diseases that cause huge damage. Although the observation of variation in the infected part of the leaf plant is very important but not enough because the perception of the human eye is not so much stronger. The identification of plant diseases is a very important task in the agriculture area. So, the best identification means there is a huge gain on agricultural productivity, quality, and quantity. To detect plant diseases in an earlier stage we require efficient and precise techniques to assist farmers in decision-making. This article presents, first, an overview of plant diseases from leaves images and different disease classification approaches that can be used for plant leaf disease detection.

Plant disease identification and classification play a pivotal role in improving the agricultural sector's efficiency and impact. Traditional laboratory testing methods have inherent limitations, including time-consuming processes and the poten-tial for misdiagnosis when relying on visual inspection alone. To address these challenges, the application of deep learning techniques, particularly convolutional neural networks (CNNs), has significantly reduced the need for manual, on-field efforts by utilizing cutting-edge technology. More recently, vision processing based transformers have emerged as a promising approach to enhance the accuracy of disease classification using high-dimensional visual data. Leveraging self-attention mechanisms and transformer architectures, these models have shown great potential for improving classification accuracy. In this research, we propose a vision transformer-based approach for classifying plant disease images. Our study utilizes the publicly available New Plant Diseases Dataset, comprising 70,295 training images and 17,572 validation images, encompassing 38 distinct plant disease and healthy classes. We fine-tune pre-trained vision transformer and VGG 16 models, achieving impressive validation accuracy rates of 99.16 % and 94 % respectively. Furthermore, we have developed a web-based application using the MobileNet model and deployed it using the Streamlit framework. This application provides a real-time classification of plant leaves, presenting the top three probabilities along with corresponding classes. It has demonstrated a validation accuracy rate of 98.72 % on the New Plant Diseases Dataset.