https://www.irjet.net/archives/V9/i5/IRJET-V9I5309.pdf

1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1307
Plant Disease Prediction Using Image Processing
Gautam Lambe1, Akshad Chaudhari2, Harshal Gaikwad3, Aniket Khatake4, Dr. S. B. Sonkamble5
1-4Dept. of Computer Engineering, JSPM’s Narhe Technical Campus, Pune, Maharashtra. India
5Professor, Dept. of Computer Engineering, JSPM’s Narhe Technical Campus, Pune, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
ABSTRACT
In these years we get to know that, agriculture is
the fundamental wellspring of public pay by and large non-
industrial nations. Consequently, thisisoneofthesignificant
and primary motivation to be considered for the
identification of plant sickness, as infection is the primary
driver of rottening of natural products or vegetables or
yields. Along these lines we can expect to be that on the off
chance that appropriate consideration isn't taken in regards
to this thing then it prompts deficiency of cash, time, quality,
amount, and so on. Consequently the primary intention is to
lessen the utilization of pesticides and accordingly yield a
decent harvest and increment the creation rate. Plantillness
can be identified utilizing image handling. Illness location
follows a few stages like pre-handling of the image,highlight
extraction, grouping, and expectation of arranged illness.
Consequently making an acknowledgment framework can
help in assessing high accuracy image of the plant for
appropriate fix and further anticipation.
Keyword:- Digital Image Processing, Image Segmentation ,
Tomato
1. INTRODUCTION
Farming, from numerous years have been related
with the development of fundamental harvests that are
thought of significant for our eating routine and generally
significant for our living. Farming is generally repaying the
monetary development of the country. It very well may be
viewed as the significant piece of society. Since numerous
businesses have been arrangementthewholewayacrossthe
world, we can say that industrialization and reasons for it
are obliterating the way of horticulture. Globalizationcanbe
considered as one more reason for low cultivating action.
The increment of populace and have to develop crops
likewise and changes in climatic condition have cause an
incredible effect in the creation as changes in climatic
circumstances can likewise cause development of different
sickness in plants. Subsequently our principal point is
decline the utilization of pesticides to decline development
cost and save our current circumstance. Presently a days,
information mining a strong and broadly utilized strategy
can be utilized in plant illness forecast. Consequently
utilizing information mining ideas with picture handling it
will be simple as far as we're concerned to perceive whether
yield is tainted or then again not, arrange infection as
indicated by different issues and with the assistance of
varieties created because of sickness and accordingly
recommending different solutions for it in view of
seriousness of infection. Accordinglytheexplorationcenters
around gathering of the information of infections on plants
and preparing a model for illness recognition. Ongoing high
level innovation has utilized profound convolutional
networks which helps inacknowledgment,arrangement and
additionally advanced mobile phone based size and variety
recognition of leaves on plant for location of sickness.
2. RELATED WORK
In framework, they utilized the convolutional brain
organization (CNN), through which plant leaf infections are
grouped, 15 classes were ordered, including 12 classes for
illnesses of various plants that were distinguished, like
microorganisms, growths, and so on, and 3 classesforsound
leaves. Accordingly, they acquired great precision in
preparing and testing, they have an exactness of (98.29%)
for preparing, and (98.029%)fortestingforall informational
index that were utilized. [1] An outline of picture division
involving K-implies bunching and HSV subordinate
arrangement for perceiving contaminated piece of the leaf
and element extraction utilizing GLCM. The productivity of
the proposed strategy can recognize and arrange the plant
illnesses effectively with a precision of 98% when handled
by Random Forest classifier. [2]
Proposed anincorporatedprofoundlearningsystemwherea
pre-prepared VGG-19 model isutilizedforincludeextraction
and stacking outfit model is utilized to distinguish and
characterize leaf infections from pictures in order to lessen
creation and financial loses in horticulture area. A dataset
comprising of two classes (Infected and Healthy) and a sum
of 3242 pictures was utilized to test the framework. Their
proposed work hasbeencontrastedandothercontemporary
calculations (kNN, SVM, RF and Tree). [3].
A CNN for programmed include extraction and arrangement
was proposed. Variety data is effectively utilized for plant
leaf sickness investigates. In model, the channelsareapplied
to three channels in light of RGB parts. The LVQ has been
taken care of with the result include vector of convolution
part for preparing the organization [4].
The principal thought processwastodiminishtheutilization
of pesticides and in this way yield a decent harvest and
increment the creation rate. Plant sickness can be identified
utilizing picture handling. Sickness identification follows a

2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1308
few stages like pre-handling of the picture, highlight
extraction, arrangement, and forecast of characterized
infection. In this way making an acknowledgment
framework can help in assessing highaccuracypictureof the
plant for appropriate fix and furtheravoidance[5].Profound
learning strategies were utilized to identify illnesses.
Profound learning design choice was the central point of
contention for the execution. So that, two differentprofound
learning network designs were tried first AlexNet and
afterward SqueezeNet. For both of these profound learning
networks preparing and approval were done on the Nvidia
Jetson TX1. Tomato leaf pictures from the Plant Village
dataset has been utilized for the preparation. Ten unique
classes including sound pictures are utilized. Prepared
networks are additionallytriedonthepicturesfromtheweb.
[6]
Two distinct models in[7], Faster R-CNN and Mask
R-CNN, are utilized in these techniques, whereFasterR-CNN
is utilized to distinguish the sorts of tomato illnesses and
Mask R-CNN is utilized to recognize and portion the areas
and states of the tainted regions. To choose the model that
best fits the tomato sickness discovery task, four unique
profound convolutional brain networks are consolidated
.Data are gathered from the Internet and the dataset is
partitioned into a preparation set, an approval set,anda test
set utilized in the trials. The exploratory outcomes
demonstrated the way that their proposed models can
precisely and immediately recognize the eleven tomato
illness types and section the areas and states of the tainted
regions. The principal objective of this framework is to
precisely identify messes in tomato plant utilizing IoT,
Machine Learning, Cloud Computing, and Image Processing
[8].
3. SYSTEM ARCHITECTURE
The photos, or dataset, were gathered from Kaggle and
include normal and several sorts of afflicted tomato leaf
images. Applying pre-processing techniques such as RGB to
greyscale conversion and enhancing them with a filtering
algorithm to eliminate noise from the imageisthefirststage.
The image is then segmented once the edges are detected
using edge detection algorithms. The following phase is
segmentation, which is followed byfeature extraction, which
converts the image into a set of images. Certain visual
features of interest are discovered and displayed here for
further processing. The resulting representationcanthen be
fed into a variety of pattern recognition and classification
algorithms, which will categorise or recognise the image's
semantic contents. The detection of leaf is noticed after
feature extraction. All of this is accomplished in the
classification block. Convolutional neural networks were
used to complete all of these steps. Finally, the suggested
system's performance and accuracy are assessed.
Fig: - System Architecture
4. METHODOLOGY
The proposed system contains following:
Pre-processing
The framework will stack the information, check for
neatness, and afterward trim and clean given dataset for
examination. Ensure that the record steps cautiously and
legitimize for cleaning choices. The information which was
gathered could contain missing qualities that might prompt
irregularity. To acquireimprovedresultsinformationshould
be pre-handled in order to work on the productivity of the
calculation. The exceptions must be eliminated and
furthermore factor transformation should be finished.
Building the classification model
The foreseeing the wistful examination by regulated AI like
choice tree calculation expectation model is successful on
account of the accompanying reasons: It gives improved
brings about arrangement issues.
5. EXPERIMENTAL RESULT

3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1309
6. CONCLUSION
The convolution neural network, is the deep feed-forward
artificial neural network which is applied for detecting the
leaf disease. We are considering one leaf per image because
the surrounding leaves may have the same or different
disease and it will be difficult to detect accurately. In the
proposed method, we are performing series of steps like
data pre-processing for improving detection accuracy and
other image processing methods to improve our result
accuracy. If this method is fully implemented then the
disease can be detected at early stage and this will reduce
the cost and the time consumed manually.
REFERENCES
1. Marwan Adnan Jasim and Jamal Mustafa AL-Tuwaijari ,
“Plant Leaf Diseases Detection and Classification Using
Image Processing and Deep LearningTechniques”,2020
International Conference on Computer Science and
Software Engineering, IEEE 2020.
2. Poojan Panchal, Vignesh Charan Raman and Shamla
Mantri , “Plant Diseases Detection and Classification
using Machine Learning Models”, IEEE 2019
3. Jiten Khurana and Anurag Sharma ,“ An IntegratedDeep
Learning Framework ofTomatoLeafDiseaseDetection”,
International Journal of Innovative Technology and
Exploring Engineering (IJITEE),2019
4. Melike Sardogan, Adem Tuncer and Yunus Ozen, “Plant
Leaf Disease Detection and Classification Based on CNN
with LV Algorithm”, IEEE 2018.
5. Gaurav Langar, Purvi Jain and Nikhil, “Tomato Leaf
Disease Detection using Artificial Intelligence and
Machine Learning”, International Journal of Advance
Scientific Research and Engineering Trends, 2020
6. Halil Durmus and Murvet Kirci, “Disease Detection on
the Leaves of the Tomato Plants by Using DeepLearning
”,International Conference on Agro-Geo
informatics,2018
7. Minghe Sun and Jie xue , “Identification of Tomato
Disease Types and Detection of Infected Areas Based on
Deep Convolutional Neural Networks and Object
Detection Techniques”, Research Article, 2019
8. Saiqa Khan and Meera Narvekar, “Disorder detection of
tomato plant(solanum lycopersicum) using IoT and
machine learning”, Journal of Physics: ConferenceSeries
,2019
9. Li Zhang and Guan Gui,“ Deep Learning Based Improved
Classification System for Designing Tomato Harvesting
Robot”, Special Section on AI-Driven Big Data
Processing: Methodology, and Applications, 2018
10. P. Narvekar, and S. N. Patil, “Novel algorithm for grape
leaf diseases detection” International Journal of
Engineering Research and General Science Volume 3,
Issue 1, pp.no 1240-1244, 2015.
11. R. Kaur and M. Kaur” An Adaptive Model to Classify
Plant Diseases Detection using KNN”International
Journal of Trend in ScientificResearchandDevelopment
(IJTSRD) ISSN: 2456-6470.
12. P. V,Rahul Das,and V. Kanchana , “Identification of Plant
Leaf Diseases Using Image Processing Techniques”978-
1-5090-4437- 5/17/$31.00 ©2017 IEEE International
Conference on Technological Innovations in ICT For
Agriculture and Rural Development.
13. M. J. Vipinadas and A.Thamizharasi, “A Survey on Plant
Disease Identification” International Journal of
Computer Science Trends and Technology (IJCST) –
Volume 3 Issue 6, Nov-Dec 2015
14. K. P. Ferentinos, “Deep learning modelsforplantdisease
detection and diagnosis,” Computers and Electronics in
Agriculture, no. September 2017, pp. 311–318.
15. J. M. AL-Tuwaijari and S. I. Mohammed, "Face Image
Recognition Based on Linear Discernment Analysis and
Cuckoo Search Optimization with SVM", International
Journal of Computer Science and Information Security.
ISSN 1947 5500, IJCSIS November 2017 Volume 15 No.
11

4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 05 | May 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 1310
16. S. P Mohanty, D. P Hughes, and Marcel Salathe, “Using
deep learning for image-based plant disease detection”,
In:Frontiers in plant science 7 (2016), p. 1419.
17. Gittaly Dhingra & Vinay Kumar & Hem DuttJoshi”Study
of digital image processing techniques for leaf disease
detection and classification” © Springer
Science+Business Media, LLC, part of Springer Nature
2017 https://doi.org/10.1007/s11042-017-5445-8 .
18. S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D.
Stefanovic, “Deep neural networks based recognition of
plant diseases by leaf image classification,”
Computational IntelligenceandNeuroscience,vol.2016,
Article ID 3289801, 11 pages, 2016.
19. G. L. Grinblat, L. C. Uzal, M. G. Larese, and P. M. Granitto,
“Deep learning for plant identification using vein
morphological patterns,” Computers and Electronics in
Agriculture, pp. 418-424.