DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

SCHOOL OF COMPUTING
1156CS701- MAJOR PROJECT(INHOUSE)
WINTER SEMESTER 20-21
REVIEW - II

“CLASSIFICATION AND SEGMENTATION OF PLANTS USING

ADAM OPTIMIZATION BASED ON DEEP NEURAL
NETWORKS”

SUPERVISED BY PRESENTED BY

Dr. CARMEL MARY BELINDA 1. K.V.SUBBAREDDY(VTU9252)(17UECN0099)

2. GALLACHAITANYA(VTUNO9225)(17UECN0016)
3. P.HARI HARA MANIKANTA(VTU8913)(17UECS0579)

11-05-2021 BATCH NO:40 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 1

 AGENDA

• ABSTRACT
• OBJECTIVE
• INTRODUCTION
• LITERATURE REVIEW (SOFT COPY OF PAPERS TO BE LINKED AS HYPERLINK)
• DESIGN AND METHODOLOGIES
• IMPLEMENTATION
• TESTING
• INPUT AND OUTPUT
• INCLUDE DEMO VIDEO-1 (Till REVEW-1)
• INCLUDE DEMO VIDEO-2(Complete Implementation of Project)
• CONCLUSION
• WEB REFERENCES LINK (TILL REVIEW DATE ALL LINKS TO BE INCLUDED DAY WISE)
• PLAGIARISM REPORT OF PPT
• REFERENCES

11-05-2021 BATCH NO:40 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 2

ABSTRACT

Crop diseases are a major threat to food security and their rapid identication
remains difficult in many parts of the world due to the lack of the necessary
infrastructure. The advent of machine and deep learning techniques has paved way
for detection of plants affected with disease and also identify the type of disease.
This will be very useful for the farmers to take a decision in combating the disease
and also in achieving good yield which in turn serves to improve our economical
growth as agriculture is the main backbone of our country.

In this project a plant disease detection based on deep learning is proposed.

Initially a CNN architecture based on Dense Net is used to train a dataset that is of
publicly available, containing images of healthy leave and that which are affected
by various diseases. This Dense Net makes use of convolution layers, dense
blocks, transition layers for deep feature extraction and nally uses global average
pooling and soft max layer for classication. The proposed work provides a training
efficiency 99.1% and validation accuracy of 97.38%. The performance of the
network is also compared in terms of recall, precision and f1-score for different
classes and is found to have an average value of 97.67%, 97.08%and 97.313%
respectively.

BATCH NO:40 DEPARTMENT OF

11-05-2021 3
COMPUTER SCIENCE & ENGINEERING
OBJECTIVES

Aim of the Project:

• To design a deep learning model to identify and classify the diseased images of
all plants in the data set provided.
• To make use of a suitable CNN architecture for feature extraction and fully
connected network for classification.

Scope of the Project:

• To use a suitable objective function(optimizer) for obtaining high accuracy.

BATCH NO:40 DEPARTMENT OF

11-05-2021 4
COMPUTER SCIENCE & ENGINEERING
INTRODUCTION

•Plant diseases are threat to food security in global scale.

•They have disastrous consequences on small hold farmers livelihood.

•So there is a necessity of identification of plant diseases in early stage correctly.

•So in order to identify plant diseases correctly, we are using a deep learning
approach.

•Deep neural networks are recently employed successfully in many diverse

domains as example of end-end learning.

BATCH NO:40 DEPARTMENT OF

11-05-2021 5
COMPUTER SCIENCE & ENGINEERING
LITERATURE REVIEW

• Junde Chen,Jinxiu Chen,Defu Zhang,Yuandong Sun,Y.A. Nanehkaran, June

2020, Using deep transfer learning for image-based plant disease
identification, Elsevier. Conclusion: The performance of proposed approach is
indicated by accuracy, sensitivity. The accuracy in rice disease estimation is
reached up to 92 percent. It's a heavier model and it takes more training time in
spite of having these limitations it can obtain high accuracy.

• Yang Lu,Shujuan Yi,Nianyin Zeng,Yurong Liu,Yong Zhang, 6 December 2017,

Identification of rice diseases using deep convolutional neural networks,
Neurocomputing. Conclusion: Images can be input directly to model. The
proposed method has better training performance, faster convergence rate as
well as a better recognition ability. So many layers and so many neurons must
be included and this is an efficient algorithm but still it is depending on large
scale datasets.

BATCH NO:40 DEPARTMENT OF

11-05-2021 6
COMPUTER SCIENCE & ENGINEERING
•
LITERATURE REVIEW

• Shanwen Zhang,Xiaowei Wu,Zhuhong You,Liqing Zhang, March 2017, Leaf

image based cucumber disease recognition using sparse representation
classification, Elsevier. Conclusion: The results obtained are they proposed a
novel crop disease recognition method based on cucumber leaves. The merits
are model is effective, model is feasible. The demerits are it didn't explain how
to construct the over complete dictionary of SR effectively.

• Jayme G.A. Barbedo, August 2018, Factors influencing the use of deep
learning for plant disease recognition, Elsevier. Conclusion: The
characteristics of the images that were misclassified by the CNNs were
carefully analyzed, and nine factors were identied as having the most impact on
the results.

BATCH NO:40 DEPARTMENT OF

11-05-2021 7
COMPUTER SCIENCE & ENGINEERING
LITERATURE REVIEW

• Xiaodong Bai,Zhiguo Cao,Laiding Zhao,Junrong Zhang,Chenfei Lv,Cuina

Li,Jidong Xie, 15 September 2018, Rice heading stage automatic
observation by multi-classifier cascade based rice spike detection method,
Elsevier. Conclusion: Training and test samples didn't overlap. Afterwards,
SVM classier model was built based on the description in. During the test
phase, the recognition rate of the spike pixel by the SVM classier reached 93.2
percent.

BATCH NO:40 DEPARTMENT OF

11-05-2021 8
COMPUTER SCIENCE & ENGINEERING
DESIGN AND METHODOLOGIES

• MODULE 1:
Data Collection and training using Machine Learning Algorithms
Algorithm: CNN architecture based on Dense Net
Data collection: Kaggle database
• MODULE 2:
Real Time data gathering and prognostics GUI design
a)The dataset named Plant Village is taken from Kaggle database.

b)It contains different types of leaf images like: Pepper, Tomato, Potato with
different diseases like early blight, Late blight, Leaf module etc. Belonging to
15 classes.

BATCH NO:40 DEPARTMENT OF

11-05-2021 9
COMPUTER SCIENCE & ENGINEERING
IMPLEMENTATION

• ARCHITECTURE DIAGRAM
• DATA FLOW DIAGRAM
• ER DIAGRAM
• SEQUENCE DIAGRAM
• COLLABORATION DIAGRAM

BATCH NO:40 DEPARTMENT OF

11-05-2021 10
COMPUTER SCIENCE & ENGINEERING
 ARCHITECTURE DIAGRAM

DATA FROM GET THE

KAGGLE DATA OUTPUT

APPLYING
STORE IN DRIVE ALGORITH
MS
TEST THE
OUTPUT

IMPLEME GIVE
NT IN CONNECTION
COLABS TO DRIVE

BATCH NO:40 DEPARTMENT OF

11-05-2021 11
COMPUTER SCIENCE & ENGINEERING
 DATA FLOW DIAGRAM

COLLECTION OF DATA

PRE- PROCESS THE

DATA

CREATE A PERFECT
DATA

APPLY MACHINE
LEARNING ALGORITHM

TRAINING THE DATA

TESTING THE DATA

GET THE OUTPUT

BATCH NO:40 DEPARTMENT OF 11-05-2021

11-05-2021 12
COMPUTER SCIENCE & ENGINEERING
 ER- DIAGRAM

INPUTTING THE TEST THE

DATA OUTPUT

GET THE
DATA BASE
OUTPUT
FROM KAGGLE

COLLECTION OF PROCESS THE

DATA DATA

BATCH NO:40 DEPARTMENT OF 11-05-2021

11-05-2021 13
COMPUTER SCIENCE & ENGINEERING
 SEQUENCE DIAGRAM

BATCH NO:40 DEPARTMENT OF

11-05-2021 14
COMPUTER SCIENCE & ENGINEERING
 COLLABORATION DIAGRAM

BATCH NO:40 DEPARTMENT OF

11-05-2021 15
COMPUTER SCIENCE & ENGINEERING
TESTING

• UNIT TESTING
• INTEGRATION TESTING
• FUNCTIONAL TESTING
• WHITE BOX TESTING
• BLACK BOX TESTING

BATCH NO:40 DEPARTMENT OF

11-05-2021 16
COMPUTER SCIENCE & ENGINEERING
 UNIT TESTING:

In the unit testing we test each module individually and integrate with the
overall system. Unit testing focuses verification efforts on the smallest unit of
software design in the module. This is also known as module testing. The
module of the system is tested separately. This testing is carried out during
programming stage itself. In the testing step each module is found to work
satisfactorily as regard to expected output from the module. There are some
validation checks for fields also. For example the validation check is done for
varying the user input given by the user which validity of the data entered. It is
very easy to find error debut the system.
Each Module can be tested using the following two Strategies:
1.Black Box Testing
2.White Box Testing

BATCH NO:40 DEPARTMENT OF

11-05-2021 17
COMPUTER SCIENCE & ENGINEERING
 INTEGRATION TESTING
Data can be lost across an interface, one module can have an adverse effort on
the other sub functions, when combined, may not produce the desired major
functions. Integrated testing is the systematic testing for constructing the uncover
errors within the interface. The testing was done with sample data. The
developed system has run successfully for this sample data. The need for
integrated test is to find the overall system performance.

WHITE BOX TESTING:

White Box Testing is the testing of a software solution's internal coding and
infrastructure.It focuses primarily on strengthening security, the flow of inputs
and outputs through the application, and improving design and usability.White
box testing is also known as clear, open, structural, and glass box testing.

BATCH NO:40 DEPARTMENT OF

11-05-2021 18
COMPUTER SCIENCE & ENGINEERING
 BLACK BOX TESTING

• Black box testing is a software testing techniques in which functionality

of the software under test (SUT) is tested without looking at the internal
code structure, implementation details and knowledge of internal paths of
the software. This type of testing is based entirely on the software
requirements and specifications.

• In Black Box Testing we just focus on inputs and output of the software
system without bothering about internal knowledge of the software
program.

BATCH NO:40 DEPARTMENT OF

11-05-2021 19
COMPUTER SCIENCE & ENGINEERING
INPUT AND OUTPUT

INPUT:

BATCH NO:40 DEPARTMENT OF

11-05-2021 20
COMPUTER SCIENCE & ENGINEERING
OUTPUT:

BATCH NO:40 DEPARTMENT OF

11-05-2021 21
COMPUTER SCIENCE & ENGINEERING
CONCLUSION

• Plant diseases are the main harms to the agricultural development of the
world, and they have a disastrous impact on the safety of food production.

• In severe cases, plant diseases may lead to no harvest completely. Therefore,

the automatic identification of plant diseases is highly desired in agricultural
information.

• Deep learning techniques, particularly CNNs, have shown promising

performance in addressing most of the challenging problems associated with the
classification.
• In this project , we have proposed CNN architecture.

• Proper training up to 25 epochs helped in achieving better results.

BATCH NO:40 DEPARTMENT OF

11-05-2021 22
COMPUTER SCIENCE & ENGINEERING
REFERENCES(as per IEEE format only)

1. Junde, C., Jinxiu, C., Zhang, D., Sun, Y., 2020. Using deep transfer learning for
image based plant disease identication. Computers and electronics in Agriculture
173-105393.
2. Lu, Y., Yi, S., Zeng, N., Liu, Y., Zhang, Y., 2017. Identication of rice diseases
using deep convolutional neural networks. Neurocomputing 267, 378{384}.
3. Bai, X., Cao, Z., Zhao, L., Zhang, J., Lv, C., Li, C., Xie, J., 2018. Rice heading
stage automatic observation by multi-classier cascade based rice spike detection
method. Agriculture. Forest Meteorol. 259, 260{270}.
4. Barbedo, J.G., 2018. Factors influencing the use of deep learning for plant
disease recognition. Biosystem. Eng. 172, 84{91.
5. Zhang, S., Wu, X., You, Z., Zhang, L., 2017. Leaf image based cucumber
disease recognition using sparse representation classification. Computer Electron
Agriculture 134.

BATCH NO:40 DEPARTMENT OF

11-05-2021 23
COMPUTER SCIENCE & ENGINEERING