Welcome to the InfoSci Platform
Reference Hub1
Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves

Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves

Udit Jindal, Sheifali Gupta
Copyright: © 2021 |Volume: 12 |Issue: 2 |Pages: 15
ISSN: 1947-8186|EISSN: 1947-8194|EISBN13: 9781799861515|DOI: 10.4018/IJISMD.2021040105
Cite Article Cite Article

MLA

Jindal, Udit, and Sheifali Gupta. "Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves." IJISMD vol.12, no.2 2021: pp.67-81. http://doi.org/10.4018/IJISMD.2021040105

APA

Jindal, U. & Gupta, S. (2021). Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves. International Journal of Information System Modeling and Design (IJISMD), 12(2), 67-81. http://doi.org/10.4018/IJISMD.2021040105

Chicago

Jindal, Udit, and Sheifali Gupta. "Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves," International Journal of Information System Modeling and Design (IJISMD) 12, no.2: 67-81. http://doi.org/10.4018/IJISMD.2021040105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Agriculture contributes majorly to all nations' economies, but crop diseases are now becoming a very big issue that has to be resolving immediately. Because of this, crop/plant disease detection becomes a very significant area to work. However, a huge number of studies have been done for automatic disease detection using machine learning, but less work has been done using deep learning with efficient results. The research article presents a convolution neural network for plant disease detection by using open access ‘PlantVillage' dataset for three versions that are colored, grayscale, and segmented images. The dataset consists of 54,305 images and is being used to train a model that will be able to detect disease present in edible plants. The proposed neural network achieved the testing accuracy of 99.27%, 98.04%, and 99.14% for colored, grayscale, and segmented images, respectively. The work also presents better precision and recall rates on colored image datasets.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.