|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Agriculture provides energy and a solution to global warming while feeding an ever-increasing population. Plant diseases are very significant since they can lower the quality and quantity of crops cultivated in agriculture. Early detection of plant diseases is crucial for curing and controlling the condition. The naked eye method is often used for diagnosing ailments. This technique involves experts who can recognize changes in leaf color. This process is labor-intensive, time-consuming, and unsuitable for large areas. Frequently, many specialists will identify the same ailment as a different one. This technology is expensive since it requires constant expert monitoring. Plant diseases can increase the cost of agricultural output and, if not treated promptly, can result in a producer's complete financial disaster. Producers must monitor their crops and spot early signs of plant illness to restrict disease spread at a low cost while saving the bulk of the product. Hiring skilled agriculturists can be expensive, especially in distant and isolated locations. Deep learning algorithms in photos can give an alternative method for plant monitoring, and a professional can administer such an approach to provide more affordable services. It includes feature extraction and classification and an image classification technique that employs a neural network algorithm to predict various illnesses. Also, expand the technique to incorporate pesticide recommendations depending on severity and data.
Keyword
Plant disease prediction, Features extraction, Classification, pesticide recommendation, Neural network approach
PDF Download (click here)
|
|
|
|
|