Systematic review of deep learning techniques in plant disease detection

Automatic identification of diseases through hyperspectral images is a very critical and primary challenge for sustainable farming and gained the attention of researchers during the past few years. The technologies proposed, and techniques adopted so far are slighted in their scope and utterly conti...

Full description

Saved in:

Bibliographic Details
Published in:	International journal of system assurance engineering and management 2020-06, Vol.11 (3), p.547-560
Main Authors:	Nagaraju, M., Chawla, Priyanka
Format:	Article
Language:	eng
Subjects:	Artificial neural networks Crop diseases Data analysis Deep learning Engineering Engineering Economics Hyperspectral imaging Image acquisition Image detection Image processing Logistics Machine learning Marketing Medical imaging Neural networks Organization Plant diseases Quality Control Reliability Review Papers Safety and Risk
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Automatic identification of diseases through hyperspectral images is a very critical and primary challenge for sustainable farming and gained the attention of researchers during the past few years. The technologies proposed, and techniques adopted so far are slighted in their scope and utterly contingent on deep learning models. The performance of convolutional neural networks is emerging as the most powerful tool to diagnose and predict the infections from the crop images. The present article has reviewed some of the existing neural network's techniques that are used to process image data with prominence on detecting crop diseases. First, a review of data acquisition sources, deep learning models/architectures, and different image processing techniques used to process the imaging data provided. Second, the study highlighted the results acquired from the evaluation of various existing deep learning models and finally mentioned the future scope for hyperspectral data analysis. The preparation of this survey is to allow future research to learn larger capabilities of deep learning while detecting plant diseases by improving system performance and accuracy.
ISSN:	0975-6809 0976-4348