Objective
a. Developed an algorithm using deep learning that allows the user to be able to identify the type of a disease that is infested on the leaf of a plant.
b. By showing the picture of the diseased leaf, the program should correctly identify the health of the leaf and the microorganism it has been infected by.
I. Neural Network Classifier
The deep learning algorithm studies the different dataset images and classifies into one of the 5 categories :
-
Bacteria
-
Fungi
-
Virus
-
Nematode
-
Normal Leaf (Not infected at all)
After classifying feature extraction of the infected leaf has been done using Digital Image Processing technique.
II. Image processing
Studied the images in the dataset and understanding the different patterns in which the organisms infect the leaf. Thus, the main objective of the technique of image processing is to extract the infected area of the leaf and isolating the background and the green part of the leaf. This would help us to highlight the only the infected area.
III. Fuzzy Rule Base System
Finally after the feature extraction , to determine the health of the leaf in terms of percentage a set of rules have been aggregated.
FINAL RESULT :