Epics Community

Project
Plant Health
Detection
Using ,
Convolutional Neural Network

1
 Project’s Supervisor: Dr. Akshara Makrariyara
Project’s Reviewer: Dr. Anirban Bhowmick
Team Members

Raj Lagas 18BCG10073

Abdulhussain Jarif 18BCE10003
Sachin Raj 18BCG10078
Arun Patel 18BCG10023
Heramb Khandway 18BCG10047
Fardeen Ahmed 18BCY10034
Snehasis Routray 18BOE10061
Ashish Kumar 18BOE10013
Nitish Pandey 18BEE10028
2
Sunil Kumar 18BEE10039
 AIM
❖ Real time identification of crops, weeds,
disease and pest damage and nutrient
deficiency symptoms.

❖ Fulfill the basic necessities of farmers,

like:
➢ Irrigation
➢ Soil management
➢ Reminder for pesticides and fertilizers
➢ Buying of Pesticides and fertilizers

3
 MOTIVE OF
WORK
Human society needs to increase food production by an estimated
70% by 2050 to feed an expected population size that is predicted

“
to be over 9 billion people.
Currently, infectious diseases reduce the potential yield by an
average of 40% with many farmers in the developing world
experiencing yield losses as high as 100%.
The widespread distribution of smartphones among crop growers
around the world with an expected 5 billion smartphones by 2020
offers the potential of turning the smartphone into a valuable tool
for diverse communities growing food.
4
 MOTIVE OF Cont.

WORK
One potential application is the development of mobile disease
diagnostics through machine learning and crowdsourcing. Here
we announce the release of over 50,000 expertly curated images
on healthy and infected leaves of crops plants through the
existing online platform PlantVillage.

We describe both the data and the platform. These data are the
beginning of an on-going, crowdsourcing effort to enable
computer vision approaches to help solve the problem of yield
losses in crop plants due to infectious diseases.
5
 Project
Plant Disease Detection Using Convolutional
Neural Network
- By Suman Chatterjee

Github Repository
6
 Differences
❖We are building an web API whereas in the project mentioned above there's no
API or any application linked to the project.
❖With the use of web API we have integrated many additional features such as
which pesticides are recommended to use along with when to use and in how
much quantity. Also we have added a reminder feature which reminds the user
when to water the plants and when to add pesticides.
❖We are also trying to integrate a market within the web API from where the
users can purchase the needful and recommended products directly which will be
7
delivered at their doorstep.
 Project Modules
⊷ A web application that facilitates farmers, scientists and botanists to
detect the type of plant or crops, detect pests and any other kind of
diseases in them.
⊷ The web API sends the image of the plant to the server where it is
analysed using CNN classifier model.

⊷ Once detected, the disease and its solutions are displayed to the
user. Also the closest pesticides selling centers are suggested.

⊷ This is an AI web application that detects diseases in plants using

FastAi which built on the top of Facebook’s deep learning platform:
8 PyTorch.
 Project Modules Cont.

⊷ Ordering fertilizer from ecommerce site, where we get the well

known and trusted companies.

⊷ We can set reminders for pesticides/watering etc. so that there will

be no loss due to climate change.

⊷ Advising on best practices to guide farmers so that they can use

advance techniques.

⊷ Contact us for personalised help, where one can ask their queries
and can conclude through the FAQs.
9
 Web API
Frontend
❖ The frontend uses basic knowledge of HTML and CSS
❖ We have created button and applied an animation for the button
❖ We created and applied icon for the page
❖ We applied CSS and interface of the form.
❖ Created the basic interface of the page using HTML

Backend
❖ The backend was created using basic knowledge of Javascript and Flask
❖ We created the synchronization between Flask (which used the model to provide output) , Javascript
( which supported the interface between frontend and backend).
❖ Created form’s backend using javascript.
❖ Provided the incoming of image and display of result after going through the model which was
trained previously.
❖ Upload of the image as file.
10
1. Flowchart for Disease detection
 Flowchart Explanation
❖ The input test image is acquired and preprocessed in the next stage and
then it is converted into array form for comparison.
❖ The selected database is properly segregated and preprocessed and then
renamed into proper folders.
❖ The model is properly trained using CNN and then classification takes
place.
❖ The comparison of the test image and the trained model take place
followed by the display of the result.
❖ If there is a defect or disease in the plant the software displays the disease
along with the remedy.

12
 Training and Testing

13
 Training
⊷ In this step, training the deep convolutional neural network for
making an image classification model will be done.
⊷ CaffeNet architecture will be used and adjusted to support our
different categories (classes).
⊷ Rectified Linear Units (ReLU) will subsequently be used as
substitute for saturating nonlinearities.
⊷ This activation function adaptively will learn the parameters of
rectifiers and improve accuracy at negligible extra computation.

Testing
⊷ In this phase, the test set for prediction of leaf as healthy/Unhealthy
with its disease name will be used to evaluate the performance of the
classifier..
14
15
16
 Watering plants

17
 The crop water need mainly depends on:

⊷ The climate: for example, in a sunny and hot climate crops need more water per day
than in a cloudy and cool climate

⊷ The crop type: crops like rice or sugarcane need more water than crops like beans and
wheat

⊷ The growth stage: grown crops need more water than crops that have just been planted

18
 Table 1
Effects of major climatic
factor on Crop water needs
Table 2

Average daily water need of

standard grass during
irrigation season
19
 Table 3
Indicative values
of the total
growing period

Table 4
Approximate values of
seasonal crop water
needs
20
 E- Commerce Purchase

21
Outcome
⊷ Identification of the plant diseases is the key to preventing the
losses in the yield and quantity of the agricultural product.
⊷ The studies of the plant diseases mean the studies of visually
observable patterns seen on the plant.
⊷ Health monitoring and disease detection on plant is very critical for
sustainable agriculture. It is very difficult to monitor the plant
diseases manually.
⊷ It requires tremendous amount of work, expertise in the plant
diseases, and also require the excessive processing time.
22
 Cont.
Outcome
⊷ Hence, image processing is used for the detection of plant diseases.
Disease detection involves the steps like image acquisition, image
pre-processing, image segmentation, feature extraction and
classification.

⊷ According to the Food and Agriculture Organization of the United

Nations (UN), trans-boundary plant pests and diseases affect food
crops, causing significant losses to farmers and threatening food
security.

23
 Reference
❖ https://github.com/sumanismcse/Plant-Disease-Identification-
using-CNN
❖ https://programminghistorian.org/en/lessons/creating-apis-wit
h-python-and-flask
❖ https://link.springer.com/article/10.1007/s41870-020-00437-5

24
 RESPONSIBILITI
ES

25
 ❖ Studying and Preparing a Dataset which consists of
Raj
plants and their diseases.
+
❖ Creating Necessary Dataset for Fertilizers and
Heramb
Pesticides.
+ ❖ Researching the details of plant growth according
Arun to their climatic regions.
+ ❖ Creation of Web Application Programming
Sachin Interface (API) and its functioning
+ ❖ Creating User Interface (UI) for our Mobile
Abdulhussain Application.
❖ Creating and Formulating PPT together.

26
 ❖ Researching Irrigation techniques useful for Farmers.
Fardeen
❖ Researching Availability of Pesticides and Fertilizers in
+ the E - Commerce Market.
Nitish ❖ Creating Flow-charts to depict the content in a well
+ organized manner.
Sunil ❖ Testing and Debugging of the Application
Programming Interface and Organizing the Datasets.

❖ Detection of plant diseases and there remedies to

solve them
Snehasis
❖ Identification of crops, weeds, disease, pest damage +
and nutrient deficiency symptoms. Ashish
❖ Analysing which and what amount of Fertilizer /
Pesticide is required for which Plant.
❖ Research Work
27
 Thanks!

28