The way a doctor can predict what kind of diseases a patient is suffering from, similarly, the fastest stratagem of predicting plant diseases is to analyze leaf's physiognomy changes and compare them with their actual color, shape, structure, etc. Plant disease recognition on the basis of leaf's physiognomy changes is the fundamental purpose of our project. We have used Convolutional Neural Network as a training method. CNN works via 3 dimensions of layers where neurons of every layer aren't fully connected to the next layer rather only a small portion is connected and the output will be decreased to a single dimension. For this, even with big datasets CNN works faster than any other networks. That's why we have used it for achieving a satisfying accuracy outcome. The program will exert plant images as input and detaching them to predict plant diseases. So it will help to identify and differentiate various types of plant diseases like aster yellows, bacterial wilt, scab, etc. quite easily & correctly.
Dataset:
Collection of images from different websites and images captured by smartphone from various fields construct our dataset. Some of the images have been downloaded through the Google search engine as well. We collected a total of 14 different plants leaves images which we classified in a total of 38 classes where 26 classes are diseases of those plants and 12 classes are healthy class.
A total of 217204 images have been collected among them 152044 images are for training the model, 43440 images are for manually testing the model and 21720 images for checking the validity of the model.
Plant Disease is common in plants.
Plant Immune System:
Click on the play button to learn more.
Proposed Methodology:
Throughout the proposed model, CNN is used to detect
different image pattern of various diseased plants, having
38 classes and achieved 97.33% recognition rate.
To run the model, need to go with below steps:
Image Collection
Image Preprocessing:
Re-sizing Image
Contrast Enchancement of Image
Recognition and Classifier:
Train and Test
Evaluation
Recognition
The Learn More button button is a clickable button.
Class
Plant Name
Disease Name
Images (Number)
I
Apple
Apple Scab
4,208
II
Cherry(sour)
Powdery mildew
2,520
III
Grape
Esca (Black Measles)
5,532
Apple scab
common disease that affects apple and crabapple trees.
Powdery mildew
a fungal disease that affects many different types of plants.
Leaf scorch
Leaf scorch is a infectious non-infectious physiological disorder that causes plant tissue to brown, yellow, or die.
Fig.1 - Leaf scorch
Researche Paper Published in:
2019 8th International Conference SMART
Author: Nagifa Anjum Dola
Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh
The IEEE Xplore Digital Library is a database that provides access to more than 5 million documents related to electrical engineering, telecommunications, power, and computer science literature. It also includes journals, conferences, standards, eBooks, and educational courses.
