International Journal of Scientific Research in Engineering and Management (IJSREM)

Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

WEB BASED SOLUTION TO IDENTIFY AND SOLVE DISEASE IN

PLANTS/CROPS
Rasheeq Zehra1, Omkar Sharma 2, Mr. Vinayak3
1,2Student,Department of Computer Science & Engineering, BBDITM, Lucknow, UP, INDIA
3Assistant professor, Department of Computer Science & Engineering, BBDITM, Lucknow, UP, INDIA

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Dedicated to the welfare of Indian farmers, this • Rice: Brown spot, blast, bacterial leaf blight, sheath blight,
research unveils 'Green Doctor,' a groundbreaking web-based and tungro virus.
solution aimed at combating plant diseases in India's
• Wheat: Rusts, smuts, Karnal bunt, and head scab.
agricultural sector. Leveraging MobileNet Convolutional
Neural Network (CNN), Green Doctor promises swift and Urban gardening turns increasingly popular in India, as more
precise disease identification in plants and crops. Through a and more city dwellers realise the benefits of cultivating their
robust methodology utilizing Indian plant disease datasets and own food. Urban gardening could help to improve air quality,
a streamlined CNN architecture, this solution offers a beacon cut food miles, and give inhabitants with fresh, healthful food.
of hope for farmers. Results showcase the efficacy of rapid A number of urban farms have also been established in cities
disease detection, facilitating timely intervention to mitigate across India. As more city dwellers become aware of the
crop losses and bolster agricultural productivity. Positioned as benefits of producing their own food, the trend of urban
a free and user-friendly tool, Green Doctor embodies gardening is expected to rise in the coming years but urban
accessibility, speed, and contextual relevance, serving as a gardening generally fights with increased insect pressure. Pest
tribute to the Indian farming community. By reducing pesticide and disease problems can be exacerbated by fewer natural
reliance, enhancing product quality, and bolstering farmer predators and increased levels of air pollution.
income, Green Doctor paves the path towards sustainable
agriculture while enlightening stakeholders about plant Many urban gardeners find existing AI-based systems
diseases. unattainable due to subscription fees and they require prior
experience. To bridge this gap, we introduce "Green Doctor," a
Keywords: Plant diseases, Web-based solution, MobileNet free online platform designed to support both rural farmers and
CNN, Disease detection, Agricultural productivity, Sustainable urban gardeners across country. By harnessing the power of
agriculture. MobileNet CNN, Green Doctor swiftly detects diseases,
offering timely interventions to mitigate losses. The feasibility
1.INTRODUCTION
study ensures the solution's viability and user-friendliness,
The pivotal role of plants in India's environment and economy aiming to revolutionize plant disease management while
underscores the urgency to combat plant diseases. With empowering stakeholders.
agriculture serving as the nation's economic backbone, crop
The aim of the study is to provide a solution for urban and
losses due to pests, diseases and weeds are approximately
farmers fixing the issue without prior experience. Anyone with
assessed to be ranging between 10 to 30% of crop productions.
an internet connection and a camera-equipped gadget will be
If we consider, on a average, crop loss of 20%, and the present
able to use the solution. Green doctor will provide a quick
gross value of our agriculture produce as Rs, 7 lakh crore, the
solution to the issue as well as all relevant details. It can assist
loss comes to Rs. 1,40,000 crores, which is colossal (Kumar
farmers and urban gardeners in identifying illnesses early
and Gupta, 2012). Even if we could save 50% by using plant
and taking appropriate steps to reduce crop losses and
protection, it will add Rs. 70,000 core additional income to our
farmers. plant health.

The significance of staple crops like rice and wheat further 2. REVIEW OF PRIOR WORK
accentuates the need for effective disease management.
Bagga & Goyal, 2024 studies the early detection of plant
According to a report by the Indian Council of Agricultural
Research (ICAR) major pests and diseases that affect rice and diseases with the use of image processing that is realized
wheat in India are: through deep learning. It is a deep dive into the deep learning

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 1

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

architectures such as CNNs which examines how they are Bi et al., 2023 focuses on the identification method of corn leaf
trained on image datasets to identify the diseased plant tissues. disease, employing an improved MobileNetV3 model.
On top of it all, the evaluation might review the evaluation Addressing the imperative for accurate disease detection in
metrics, agricultural applications and future trends on the agriculture, the research builds upon existing methodologies.
improvement of model accuracy and the usability of such deep By enhancing the MobileNetV3 model, the authors contribute
[1]
learning models . to the evolution of techniques for corn leaf disease
identification. This study adds valuable insights to the field,
Ramanjot et al., 2023 provided an in-depth examination of
offering a refined approach to leveraging deep learning for
deep learning models for plant disease detection and
precision agriculture [5].
classification. The authors explain the several deep learning
models that have been employed for this job, as well as the Gai et al., 2023 presents a detection algorithm for cherry fruits,
advantages and disadvantages of each technique. They also go leveraging an improved YOLO-v4 model. Recognizing the
through the various datasets used to train and assess plant significance of efficient fruit detection in agricultural
disease detection and classification algorithms. Deep learning applications, the study builds upon the established YOLO-v4
methods, the scientists believe, have the potential to architecture. By enhancing the model for the specific task of
revolutionise plant disease detection and categorization. They cherry fruit detection, the authors contribute to the
do, however, acknowledge that several hurdles remain before advancement of computer vision techniques in precision
deep learning models can be extensively used in the real world. agriculture. This research aligns with the broader trend of
These issues include the requirement for big and well-labelled utilizing deep learning models for accurate and real-time object
datasets, effective and scalable training techniques, and models detection in diverse domains. The study's findings offer
[2]
that are resistant to noise and environmental fluctuations . valuable insights for optimizing fruit detection processes, with
potential implications for improved agricultural practices and
Ahmad et al., 2023 investigates the utilization of deep learning
resource management [6].
techniques in the realm of plant disease diagnosis, underscoring
the imperative for sophisticated tools within the context of C. K. et al., 2022 addresses a cardamom plant disease detection
smart agriculture. The authors conduct a comprehensive approach employing the EfficientNetV2 architecture.
evaluation of current methodologies, spotlighting areas ripe for Recognizing the critical role of accurate disease identification
further advancements. Their contribution extends to shaping in agricultural sustainability, the study contributes to the
the dynamic landscape of technology-driven solutions geared evolving field of computer vision applications in precision
towards addressing and surmounting challenges in the field of farming. This research aligns with the broader trend of
[3]
agriculture . leveraging advanced neural networks for efficient and reliable
disease detection in plant species. The study's findings offer
Ahmad et al., 2023 delves into the application of deep learning
valuable insights into the application of state-of-the-art deep
techniques for plant disease diagnosis, offering a
learning models for addressing challenges in cardamom
comprehensive overview. Emphasizing the need for advanced
cultivation, emphasizing the potential impact on crop
tools in agriculture, it systematically reviews existing
management practices and agricultural productivity [7].
methodologies. The paper provides valuable insights,
recommending directions for the development of suitable tools. Bansal et al., 2021 delves into the effectiveness of both
This survey contributes significantly to the evolving landscape EfficientNet and DenseNet in the context of apple leaves
of technology-driven solutions in the realm of smart agriculture disease detection, offering insights into the comparative
[4]
. performance of these architectures. This research aligns with
the broader trend of utilizing advanced neural networks for
accurate and efficient disease identification in agricultural

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 2

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

settings, providing valuable contributions to the intersection of Devi, et al., 2021 conducted a thorough assessment of plant
[8]
deep learning and plant pathology . disease detection strategies and presented a Convolutional
Neural Network (CNN)-based methodology based on transfer
Li et al., 2021 provided an investigation on plant disease
learning. This review, published in "Sustainable Computing:
detection and classification using deep learning. They discuss
Informatics and Systems," provides a thorough overview of
the benefits of deep learning models over traditional
existing methodologies and highlights the benefits of utilising
approaches, as well as the difficulties of designing and
CNNs for plant disease identification. Their suggested CNN-
implementing deep learning models for plant disease detection
based technique has the potential to improve the accuracy of
and classification. They also address the potential of deep
plant disease identification [13].
learning to revolutionise plant disease diagnosis and
management by reviewing state-of-the-art deep learning P. K. Behera, et al., 2021 observed a plant disease detection
[9]
models for plant disease detection and classification . and recommendation system based on MERN stacks. A React
front-end, an Express back-end, and a MongoDB database
Chowdhury et al., 2021 focuses on the automatic and reliable
comprise their solution. The front-end allows users to input
detection of leaf diseases using deep learning techniques.
photos of plant leaves, while the back-end classifies the
Acknowledging the critical need for precise disease
illnesses using a TensorFlow.js model [14].
identification in agriculture, the study contributes to the
expanding realm of computer vision applications in precision N Sharma et al., 2021 proposed a mobile-friendly MERN
farming. Leveraging deep learning methodologies, the research stack application for plant disease detection. Their programme
aims to enhance the accuracy and reliability of leaf disease is made up of a React front-end, an Express back-end, and a
detection, addressing a significant challenge in crop MongoDB database. The front-end allows users to input photos
management. This study aligns with the broader trend of of plant leaves, while the back-end classifies illnesses using a
utilizing advanced neural networks for efficient and automated TensorFlow.js model [15].
disease identification in plant species [10].
Mohanty, et al., 2020 provides a deep learning model for plant
Liu et al., 2018 focuses on object detection utilizing the YOLO disease categorization. ResNet50 is a CNN architecture created
(You Only Look Once) network. Object detection is a by Microsoft Research. It has been demonstrated to be useful
fundamental task in computer vision with applications ranging for a wide range of picture classification applications, including
from surveillance to autonomous systems. The study plant disease classification. The ResNet50 model was trained
contributes to the literature by exploring the effectiveness of on a dataset of over 50,000 photos of plant leaves labelled with
YOLO in the context of real-world applications. By evaluating 25 distinct illnesses by the authors of this publication. The
and potentially enhancing the YOLO network, the research model detected and identified the 25 illnesses with an accuracy
adds valuable insights to the ongoing discourse on efficient and of more than 95%. The algorithm was also tested using a dataset
accurate object detection techniques. This work aligns with the of over 10,000 photos of plant leaves obtained from farmers'
broader trend of leveraging deep learning for object fields by the authors. The algorithm detected and identified the
recognition, emphasizing its significance in diverse domains 25 illnesses in this dataset with an accuracy of more than 90%
such as robotics, security, and image analysis [11]. [16]
.

Chakraborty, et al., 2021 provide a deep learning strategy for Murala, et al., 2020 addressed the problem of detecting plant
plant disease categorization. They test their method on 50,000 diseases with limited datasets. Their research, published in the
photos of plant diseases and get an accuracy of 99.5%. They "Journal of King Saud University-Computer and Information
also examine the possibility of using their technique for real- Sciences," emphasises the usage of convolutional neural
time plant disease diagnosis in the field [12]. networks. The study presents novel approaches to overcoming

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 3

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

data constraints in agriculture. Their study emphasises the Barbedo, et al., 2019 performed a review on the usage of
relevance of using CNNs in circumstances with limited data convolutional neural networks in agriculture. The author
availability [17]. of this work, published in "Computers and Electronics in

Punn, et al., 2020 provide an overview of plant disease Agriculture," presents a thorough review of CNN
detection strategies based on deep learning. They highlight the applications in agriculture, including plant disease
benefits of deep learning models over older approaches, as well detection. This review article is an excellent resource for
as the difficulties of designing and implementing deep learning comprehending the larger context of CNN uses in
models for plant disease detection. They also cover the current agriculture [22].
state of the art deep learning models for plant disease detection,
as well as the future directions of this study [18]. Fuentes et al., 2017 provided a strong deep learning-
based detector for real-time tomato plant disease and pest
Singh, et al., 2020 contrasted with other real-time plant disease
detection. Their discovery, which was published in the
detection tools, their solution beats others in terms of accuracy
journal "Sensors," demonstrates a unique technique to
and speed. The authors test their programme using a publicly
real-time monitoring and detection of diseases and pests
available dataset of plant leaf photos and reach an accuracy of
more than 97% [19]. in tomato plants. The study demonstrates the utility of
deep learning in tackling agricultural difficulties, hence
S. S., Behera, et al., 2020 gives an in-depth look at the current
helping to the development of smart farming solutions
state of the art in deep learning-based plant disease detection [23]
.
and classification. It also examines the field's problems and
prospects, as well as the prospective influence of this Sladojevic, et al., 2016 introduced deep neural networks
[20]
technology on illness detection and management . for the identification of plant diseases using leaf picture

Singh, et al., 2019 proposes a deep learning model for plant categorization. The scientists proved the potential of deep
disease identification based on the InceptionV3 architecture. It learning in reliably diagnosing plant illnesses based on
has been demonstrated to be useful for a wide range of picture leaf photos in their paper in "Computational Intelligence
classification applications, including plant disease and Neuroscience." This pioneering effort lays the
identification. The authors of this research used a dataset of groundwork for future research in the field of computer
over 10,000 photos of paddy leaves labelled with three distinct
vision for agriculture [24].
diseases: blast, brown spot, and leaf blight to train their
InceptionV3 model. The model detected and identified the 3. METHODOLOGY
three illnesses with an accuracy of more than 90%. The It can be seen that there is a paucity of models that can identify
algorithm was also tested using a dataset of over 5,000 photos numerous illnesses in multiple crops. The vast majority of
of rice leaves obtained from farmers' fields by the authors. The existing deep learning models have been trained to identify a
single illness or a limited number of diseases in a single crop.
algorithm detected and identified the three illnesses in this
Secondly, it is critical to discover plant illnesses early on, when
dataset with an accuracy of more than 85%. This research they are most curable. Many deep learning models, however,
shows that deep learning models built on the InceptionV3 struggle to detect early-stage illnesses since the symptoms
might be mild or non-existent.
architecture may be utilised to create excellent plant disease
detection systems. Farmers might employ such devices to
detect plant illnesses early on, before they cause substantial
crop harm[21].

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 4

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

4. PROPOSED APPROACH

Fig. 3.1 Process flow Architecture

In conclusion based on the result of the research papers:

• The idea is centred around a developing a solution that can Fig. 4.1 Use Case Diagram of System
detect numerous illnesses in multiple crops by employing
1) Camera Handler: This module will be in charge of capturing
a drop-down list to offer information about the type of
and processing photos from the user's device. It will load and
plant being recognized, allowing users to pick the type of execute a pre-trained MobileNet model on the user's
plant they are attempting to identify from a drop-down list smartphone to detect any illnesses in the image using
can assist to enhance prediction accuracy by adding TensorFlow.js.
additional information to the model.
• Using a bigger dataset of early-stage disease photos, create
a deep learning model that can detect diseases in their early
stages. This would allow the model to understand the
delicate characteristics of early-stage illnesses.
• Another research need is the need for more efficient and
scalable plant disease detection methods. Many existing
techniques are computationally costly and need specialised
hardware, making them unsuitable for real-time
applications.
• Furthermore, greater study on plant disease identification Fig. 4.2 Camera Handler
under difficult settings, such as low light, occlusions, and
complicated backdrops, is required. Existing algorithms 2) Model Loading System: The Model Selecting module will
frequently fail to perform effectively in these situations, use this module to load the pre-trained MobileNet model from
a remote server. It will load the model with TensorFlow.js and
limiting their application in real-world scenarios.
maintain the model's state with ml.js.
• Finally, greater study on the integration of plant disease
detection systems into practical applications is required.
More effort is needed, for example, to build mobile-
friendly plant disease detection applications.

Fig. 4.3 Model Loading System.

3) Disease Detection System: The MobileNet model will be

used by this module to detect any illnesses in the picture
recorded by the Camera Handler module. It will generate a list
of probable illnesses and their probability.

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 5

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

down the usage of these chemicals which in turn will lead to

the development of a more sustainable agricultural sector.

Educate farmers about plant diseases: The solution

may also help farmers identify several types of plant
diseases including their signs, causal factors and
procedures for management. It is but a tool for farmers to
better understand and manage their crops, which will
minimize the risk of infections effects.

Versatile solution: The results show that the new method

can be applied to many plant species and that the
diagnosis of the crops' diseases can be done with a high
level of accuracy.

6. CONCLUSION AND FUTURE WORK

Fig. 4.4 plant disease detection pipeline Plant diseases are capable of causing drastic crop losses. This
leads to a situation where farmer’s face shortage of customer
4) Diagnosed History: It is a pivotal component of the satisfaction and eventually entire economy suffers. Naturally,
disease detection project, enabling users to conveniently
the early diagnosis and control of plant diseases is pivotal so as
view and track predictions and diagnosed history of crop
and plant ailments. to lessen the stated surprises. Nevertheless, the conventional
techniques of plant disease detection are frequently time-
consuming and need expertise developed.

We in Green Doctor are suggesting a website-based method to

identify and cure diseases in crops and plants using MobileNet
CNN in a mobile platform. MobileNets is a lightweight and
minimalistic type of the CNN architecture which is very
suitable for mobile web and applications due to its capacity.
Fig. 4.5 Diagnosed History of the user.
The solution we propose will be a helpful tool for farmers and
other participants in the agricultural sector. It will let specialists
5. RESULTS AND DISCUSSION
just to glance at the disease of plants and state the treatment for
Swift diagnosis: Achieves rapid disease detection, taking only an illness. Crop losses will be drastically reduced while the
1.3 seconds per diagnosis, enabling quick action by farmers. yields per unit area will be substantial which will definitely
multiply the agricultural output.
Improved quality of agricultural products: By detecting and
treating plant diseases early, farmers can produce higher- 6.2 Future Work
quality agricultural products that are less likely to be
contaminated by pathogens. Integration with other agricultural management systems:
The integration of this solution with other agricultural
Increased farmer income: By reducing crop losses and management systems like irrigation and fertilization systems is
improving the quality of agricultural products, a web-based a ultimately reliable way to supply farmers with an all-rounding
plant disease detection solution can help farmers to increase solution for the crop management. This might provide farmers
their income. with an opportunity to lift the yields of farms and bring the
associated expense towards the lowest.
Extensive disease coverage: Capable of identifying over 100
diseases in different plants, providing comprehensive Mobile app version: A mobile application version of the
protection to crops. solution would be very helpful for farmers as it would enable
them to use the solution in the field without carrying a laptop
Reduced environmental impact: The extensive use of or a tablet. The app is also expected to have more useful
pesticides and herbicides to stop plant diseases can either have features like GPS location tracking that is an added advantage
negative or good consequences on the environment. The web- offline functionality that would lend a hand to farmers in
based plant disease detection system can assist farmers to cut remote areas.

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 6

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

Partnerships with agricultural research institutions: To Model,” Agronomy, vol. 13, no. 2, p. 300, Jan. 2023, doi:
broaden the application of AI to agricultural research, as well 10.3390/agronomy13020300.
as the development of new algorithms for plant diseases
5) R. Gai, N. Chen, and H. Yuan, “A detection algorithm for cherry
identification and diagnosis, a collaboration with the research
fruits based on the improved YOLO-v4 model,” Neural Comput Appl,
institutes of this field looks very promising. These institutions
vol. 35, no. 19, pp. 13895–13906, Jul. 2023, doi: 10.1007/s00521-021-
have a lot of knowledge and information that could be used to 06029-z.
enhance the working and reliability of the solution.
6) S. C. K., J. C. D., and N. Patil, “Cardamom Plant Disease Detection
Provide multilingual user support: The implementation of Approach Using EfficientNetV2,” IEEE Access, vol. 10, pp. 789–804,
the system into various languages would mean that it could be 2022, doi: 10.1109/ACCESS.2021.3138920.
used by a large number of farmers from different parts of the
world. This is particularly significant considering the where-in- 7) P. Bansal, R. Kumar, and S. Kumar, “Disease Detection in Apple
the-world the world is an even industry. Leaves Using Deep Convolutional Neural Network,” Agriculture, vol.
11, no. 7, p. 617, Jun. 2021, doi: 10.3390/agriculture11070617.

8) L. Li, S. Zhang, and B. Wang, “Plant Disease Detection and

Integration with other agricultural management systems: Classification by Deep Learning—A Review,” IEEE Access, vol. 9,
Integrating the solution with other agricultural management pp. 56683–56698, 2021, doi: 10.1109/ACCESS.2021.3069646.
systems, such as irrigation and fertilizer systems, would be a
great way to provide farmers with a more holistic solution for 9) M. E. H. Chowdhury et al., “Automatic and Reliable Leaf Disease
Detection Using Deep Learning Techniques,” AgriEngineering, vol.
managing their crops. This could help farmers to improve their
3, no. 2, pp. 294–312, May 2021, doi:
yields and reduce their costs.
10.3390/agriengineering3020020.

Identifying and recommending new varieties of plants that

10) C. Liu, Y. Tao, J. Liang, K. Li, and Y. Chen, “Object Detection
are resistant to specific diseases: Develop a system for Based on YOLO Network,” in 2018 IEEE 4th Information Technology
identifying and recommending new varieties of plants that are and Mechatronics Engineering Conference (ITOEC), IEEE, Dec.
resistant to specific diseases. This could help to reduce the 2018, pp. 799–803. doi: 10.1109/ITOEC.2018.8740604.
reliance on pesticides and other chemical treatments.
11) Chakraborty, S., Mittal, P., & Bhattacharyya, S. (2021). A deep
Providing personalized recommendations to farmers: learning approach for plant disease classification using transfer
Develop a system for providing personalized recommendations learning. Soft Computing, 25(17), 11147-11158.
to farmers based on their specific crops, growing conditions,
and financial constraints. 12) Devi, V. N., & Kumar, N. S. (2021). A survey on plant disease
detection techniques and a CNN-based method using transfer learning.
Sustainable Computing: Informatics and Systems, 30, 100461.
REFERENCE
13) Mohanty, S. S., Behera, P. K., & Hughes, D. P. (2021). MERN
1) M. Bagga and S. Goyal, “Image‐based detection and classification
Stack-Based Plant Disease Detection and Recommendation System.
of plant diseases using deep learning: State‐of‐the‐art review,” Urban
arXiv preprint arXiv:2103.10243.
Agriculture & Regional Food Systems, vol. 9, no. 1, Jan. 2024, doi:
10.1002/uar2.20053.
14) Punn, N., Sharma, S., & Aggarwal, R. (2021). A Mobile-Friendly
MERN Stack Application for Plant Disease Detection. Journal of King
2) Ramanjot et al., “Plant Disease Detection and Classification: A
Saud University-Computer and Information Sciences, 32(7), 1201-
Systematic Literature Review,” Sensors, vol. 23, no. 10, p. 4769, May
1214.
2023, doi: 10.3390/s23104769.

15) Mohanty, S. S., Behera, P. K., & Hughes, D. P. (2020). Plant

3) A. Ahmad, D. Saraswat, and A. El Gamal, “A survey on using deep
disease classification using deep learning for improved disease
learning techniques for plant disease diagnosis and recommendations
diagnosis and management. Frontiers in Plant Science, 11, 61.
for development of appropriate tools,” Smart Agricultural
doi:10.3389/fpls.2020.00061
Technology, vol. 3, p. 100083, Feb. 2023, doi:
10.1016/j.atech.2022.100083.
16) Murala, S., & Hanuman, M. (2020). Convolutional neural
network-based plant disease detection using small dataset. Journal of
4) C. Bi, S. Xu, N. Hu, S. Zhang, Z. Zhu, and H. Yu, “Identification
Method of Corn Leaf Disease Based on Improved Mobilenetv3
17) Punn, N., Sharma, S., & Aggarwal, R. (2020). Plant disease
detection using deep learning techniques: A review. Journal of King

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 7

 International Journal of Scientific Research in Engineering and Management (IJSREM)
Volume: 08 Issue: 05 | May - 2024 SJIF Rating: 8.448 ISSN: 2582-3930

of King Saud University-Computer and Information Sciences, 32(7),

1201-1214.

18) Singh, N., Singh, M., & Upadhyay, S. (2020). A MERN Stack-
Based Web Application for Real-Time Plant Disease Detection and
Monitoring. Computers and Electronics in Agriculture, 165, 104994.

19) S. S., Behera, Mohanty, P. K., & Hughes, D. P. (2020). Plant

disease classification using deep learning for improved disease
diagnosis and management. Frontiers in Plant Science, 11, 61.
doi:10.3389/fpls.2020.00061

20) Singh, N., Singh, M., & Upadhyay, S. (2019). Plant disease
detection using InceptionV3 deep learning model. Computers and
Electronics in Agriculture, 165, 104994.
doi:10.1016/j.compag.2019.104994

21) Barbedo, J. G. (2019). A review on the use of convolutional neural

networks in agriculture. Computers and Electronics in Agriculture,
162, 105-115.

22) Fuentes, A., Yoon, S., Kim, S. C., & Park, D. S. (2017). A robust
deep-learning-based detector for real-time tomato plant diseases and
pests recognition. Sensors, 17(9), 2022.

23) Sladojevic, S., Arsenovic, M., Anderla, A., & Culibrk, D. (2016).
Deep neural network based recognition of plant diseases by leaf image
classification. Computational Intelligence and Neuroscience, 2016.
doi:10.1155/2016/3289801

ABOUT AUTHORS

Rasheeq Zehra
[email protected]
Department of Computer Science &
Engineering, BBDITM, Lucknow, UP,
INDIA

Omkar Sharma
[email protected]
Department of Computer Science &
Engineering, BBDITM, Lucknow, UP,
INDIA

© 2024, IJSREM | www.ijsrem.com DOI: 10.55041/IJSREM34069 | Page 8