This paper is published in Volume-7, Issue-3, 2021
Area
Electronics And Communication
Author
Tasleema Jan, Dr. Rajat Joshi
Org/Univ
Adesh Institute of Technology, Gharuan, Punjab, India
Keywords
CNN features, Image Segmentation, Machine Learning
Citations
IEEE
Tasleema Jan, Dr. Rajat Joshi. Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Tasleema Jan, Dr. Rajat Joshi (2021). Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches. International Journal of Advance Research, Ideas and Innovations in Technology, 7(3) www.IJARIIT.com.
MLA
Tasleema Jan, Dr. Rajat Joshi. "Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches." International Journal of Advance Research, Ideas and Innovations in Technology 7.3 (2021). www.IJARIIT.com.
Tasleema Jan, Dr. Rajat Joshi. Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.
APA
Tasleema Jan, Dr. Rajat Joshi (2021). Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches. International Journal of Advance Research, Ideas and Innovations in Technology, 7(3) www.IJARIIT.com.
MLA
Tasleema Jan, Dr. Rajat Joshi. "Detection of plant leaf disease using image segmentation and Convolution Neural network and machine learning approaches." International Journal of Advance Research, Ideas and Innovations in Technology 7.3 (2021). www.IJARIIT.com.
Abstract
Productivity in agriculture is a big concern. Disease is important in agriculture because it occurs naturally in plants. if good precaution is not taken, so these plants and quantity is diminished. h. As a primary goal of the new Proposed architecture, the use of disease and classifier features is needed to identify proper disease features. The primary aim of successful design is residual learning such that vital facets of firm learning are also improved. Non-linear discriminative learning at the base of a neural network experiments were run in the Village with the measurements of 11 different diseases was designed using the CNN features, which yielded an accuracy rate of 98% on the validation sets.