Reference Hub16
Smart Farming: An Approach for Disease Detection Implementing IoT and Image Processing

Smart Farming: An Approach for Disease Detection Implementing IoT and Image Processing

Hui Pang, Zheng Zheng, Tongmiao Zhen, Ashutosh Sharma
Copyright: © 2021 |Volume: 12 |Issue: 1 |Pages: 13
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781799861584|DOI: 10.4018/IJAEIS.20210101.oa4
Cite Article Cite Article

MLA

Pang, Hui, et al. "Smart Farming: An Approach for Disease Detection Implementing IoT and Image Processing." IJAEIS vol.12, no.1 2021: pp.55-67. http://doi.org/10.4018/IJAEIS.20210101.oa4

APA

Pang, H., Zheng, Z., Zhen, T., & Sharma, A. (2021). Smart Farming: An Approach for Disease Detection Implementing IoT and Image Processing. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 12(1), 55-67. http://doi.org/10.4018/IJAEIS.20210101.oa4

Chicago

Pang, Hui, et al. "Smart Farming: An Approach for Disease Detection Implementing IoT and Image Processing," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 12, no.1: 55-67. http://doi.org/10.4018/IJAEIS.20210101.oa4

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

With the increasing demand on smart agriculture, the effective growth of a plant and increase its productivity are essential. To increase the yield and productivity, monitoring of a plant during its growth till its harvesting is a foremost requirement. In this article, an image processing-based algorithm is developed for the detection and monitoring of diseases in fruits from plantation to harvesting. The concept of artificial neural network is employed to achieve this task. Four diseases of tomato crop have been selected for the study. The proposed system uses two image databases. The first database is used for training of already infected images and second for the implementation of other query images. The weight adjustment for the training database is carried out by concept of back propagation. The experimental results present the classification and mapping of images to their respective categories. The images are categorized as color, texture, and morphology. The morphology gives 93% correct results which is more than the other two features. The designed algorithm is very effective in detecting the spread of disease. The practical implementation of the algorithm has been done using MATLAB.