Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection

Ahmad, Iftikhar; Hamid, Muhammad; Yousaf, Sohail; Shah, Syed Tanveer; Ahmad, Muhammad Ovais

doi:10.1155/2020/8812019

Cited by 113 publications

(50 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training loss decreases linearly from epoch to epoch but the validation loss oscillates up and down initially and it was very high and gradually declines. Tomato leaf disease detection using optimized pre trained convolutional neural network is conducted (20) using two types of datasets which are collected from the real field in uncontrolled environment then augmented to maximize the number of datasets used for the experiment and public dataset collected from controlled environment which is a real world representation . In this experiment authors have proved to be more challenging for pre trained network models.…”

Section: Resultsmentioning

confidence: 99%

Image-based Tomato Disease Identification Using Convolutional Neural Network

Gardie¹,

Azezew²,

Asemie³

2021

IJST

View full text Add to dashboard Cite

Objectives: Agriculture is the main food source and farmers are challenging a great production loss annually due to plant leaf disease. Early identification of tomato plant diseases help farmers to take preventive measure to reduce production loss. As a result, to recognize tomato plant leaf diseases in its early stage, a deep learning approach is discussed. Methods: For tomato disease identification and classification a convolutional neural network model is used in this study. CNN is capable for fine-grained disease identification as a technique which avoids feature engineering and threshold segmentation through automatic feature extraction. Findings: In this experiment, we have used 22,930 leaf image dataset are taken from plant village dataset, some are collected from Awash Melkasa tomato cultivation area in various seasons. Image processing is conducted along with pixel with operations it enhance the image data followed with feature extraction of patterns of collected leaves to detect the leaf diseases. The extracted patterns are fit into the neural network model with 100 epochs, 80/20 splitting ratio, and 0.001 learning rate. Hence the tomato disease network model achieves an overall 98.3% accuracy performance. Novelty: In order to detect tomato leave disease, we performed image processing with pixel-wise operation to enhance the leaf images that can be followed by feature extraction to classify patterns. We extend, and adopt neural network using local images collected under challenging environment datasets and optimization is performed in Adam optimizer with categorical entropy as loss function.

show abstract

Section: Resultsmentioning

confidence: 99%

Image-based Tomato Disease Identification Using Convolutional Neural Network

Gardie¹,

Azezew²,

Asemie³

2021

IJST

View full text Add to dashboard Cite

show abstract

“…In the recent past machine learning applications have seen widespread use in various domains [51,52]. However, there is limited work to evaluate the usability aspect of machine learning applications [53].…”

Section: Discussionmentioning

confidence: 99%

A Systematic Mapping Study of Software Usability Studies

Almazroi¹

2021

IJACSA

View full text Add to dashboard Cite

Among software quality attributes "software usability" is considered as one of the vital factors in software engineering literature. Software usability is the ability for users to generally understand, use, and learn a software with ease. Due to the importance of usability in software quality, a considerable amount of literature is published in the past decade. Few review and survey studies are also published to critically review the existing literature in the domain. However, there is limited research covering systematic mapping study of software usability. Mapping studies help in analyzing the general trends and research productivity in a research area. To fill this gap, this work critically examines the overall research productivity, demographics, trends, and challenges of software usability. The objective is to classify the current contributions and trends in the area of software usability. We retrieved 9,874 research articles from six research databases and 62 works are selected as primary studies using an evidence-based approach. The result of this mapping study shows that software usability is an active research area, with a promising number of works published in the last decade (2011 -2020). We identified that the current literature spans over multiple article classes of which investigative papers, model proposals and evaluation papers are the most frequently published article types. We found experiments and theoretical validations to be the most common validation techniques. In terms of application domains; web, software development and mobile applications are the most frequent domains where usability studies are conducted. We identified that future usability studies should focus more on field studies as well as on the usability testing of scientific software packages. It will be of importance to consider ethical issues in usability testing as well.

show abstract

“…Ahmad et al [54] used four different pretraining convolution neural networks VGG19, VGG16, ResNet, and Inception V3, and the models were trained by fine-tuning parameters. The experimental results showed that the Inception V3 had the best performance on the two datasets(the laboratory dataset and the field dataset).…”

Section: A Leaf Disease Detection By Well-known Deep Learning Architectures 1) Classic Deep Learning Architectures For Leaf-disease Detecmentioning

confidence: 99%

Plant Disease Detection and Classification by Deep Learning—A Review

Zhang

2021

IEEE Access

432

View full text Add to dashboard Cite

Deep learning is a branch of artificial intelligence. In recent years, with the advantages of automatic learning and feature extraction, it has been widely concerned by academic and industrial circles. It has been widely used in image and video processing, voice processing, and natural language processing. At the same time, it has also become a research hotspot in the field of agricultural plant protection, such as plant disease recognition and pest range assessment, etc. The application of deep learning in plant disease recognition can avoid the disadvantages caused by artificial selection of disease spot features, make plant disease feature extraction more objective, and improve the research efficiency and technology transformation speed. This review provides the research progress of deep learning technology in the field of crop leaf disease identification in recent years. In this paper, we present the current trends and challenges for the detection of plant leaf disease using deep learning and advanced imaging techniques. We hope that this work will be a valuable resource for researchers who study the detection of plant diseases and insect pests. At the same time, we also discussed some of the current challenges and problems that need to be resolved. INDEX TERMSDeep learning, plant leaf disease detection, visualization, small sample, hyperspectral imaging.

show abstract

Optimizing Pretrained Convolutional Neural Networks for Tomato Leaf Disease Detection

Cited by 113 publications

References 12 publications

Image-based Tomato Disease Identification Using Convolutional Neural Network

Image-based Tomato Disease Identification Using Convolutional Neural Network

A Systematic Mapping Study of Software Usability Studies

Plant Disease Detection and Classification by Deep Learning—A Review

Contact Info

Product

Resources

About