e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

Crop Disease Prediction System

ABSTRACT
The Crop Disease Detection System is a groundbreaking and timely solution that aims to tackle the challenges
faced by agriculture. As the global population continues to grow and put pressure, on food production it is crucial
to adopt farming practices and effectively manage crop diseases. This system utilizes the power of machine
learning and image recognition to empower farmers, gardeners and agricultural professionals with a tool that
can accurately diagnose diseases affecting their crops. By uploading images of affected plants users can rely on
algorithms within the system to identify the specific disease and provide customized solutions, for mitigating its
impact.

Keywords: python, Disease, VGG-16 Algorithm

In an era where agriculture plays a pivotal role in ensuring global food security, the development of innovative
technologies to safeguard crops is of paramount importance. The Crop Disease Detection System represents a
cutting-edge solution that harnesses the power of machine learning and image recognition to empower farmers
and gardeners. This revolutionary system enables users to swiftly and accurately diagnose diseases in their crops
by simply uploading images of affected plants. Through advanced algorithms and data-driven insights, the Crop
Disease Detection System not only identifies the ailments but also provides tailored solutions, thereby offering a
critical tool to enhance agricultural productivity, minimize crop losses, and promote sustainable farming
practices. With the fusion of technology and agriculture, this system stands as a beacon of hope in the quest to
meet the ever-growing demands of our global population while safeguarding our environment and resources.

II. METHODOLOGY

For the purpose of detecting plant diseases, many approaches may be applied. However, machine learning-based
image classification is a widely utilized strategy. Here is fundamental process for creating a machine learning
model for plant/crop disease detection:

1. Data Collection and Preparation: Gather a comprehensive dataset of images of healthy and diseased
plants for training and validation. Here we will be using plant village dataset which consists of several
crops and plants classified into a total of 39 classes. Clean, preprocess and annotate the dataset if not
labelled. The preparation of dataset includes image resizing and transformation,

2. Preprocessing Data: Remove any extraneous information from data, such as HTML elements,
punctuation, and stop words. To get a collection of pertinent characteristics, also do text normalization
and feature extraction.

3. Split the dataset into test dataset and training dataset respectively.

4. Transfer Learning: It is a machine learning method where we use the knowledge learned from one task
to solve another related task. In this technique, a pretrained model is used to optimize our task and apply
some modifications to achieve the result. We will be using vgg16 model which is a CNN model consisting
of 16 layers pretrained on a dataset of millions of images which are classified into 1000 different classes.

5. Model Training: The training dataset is used to train the machine learning model by importing Torch
library. Torch is a machine-learning library useful for creating deep neural networks. The original model

[1]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science

training includes adding several convolution layers as well as batch normalization and max pooling
layers.

6. Model Evaluation: Evaluate the trained model's performance using test dataset. To evaluate the model's
performance, find the losses and accuracy acquired in different batches of test dataset.

7. Deployment: To be used in crop disease detection, import the model to enable it to integrate with the
frontend and deploy it.
It's crucial to remember that the aforementioned technique is only a general outline, and the specifics may change
based on the demands of the unique application. access to the attendance.

III. MODELING AND ANALYSIS

Below the image of our frontend show how the user can upload the image easily and get the predicted answer
and also we create mobile friendly interface, we also provide the supplements also for defected crop.

[2]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science

[3]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science

IV. CONCLUSION

The development and application of a Crop Disease Detection System is an advancement, in agriculture and
horticulture. This innovative system, which utilizes the power of machine learning and image recognition
provides a solution for detecting and managing diseases at a stage. It has the potential to revolutionize farming
by not identifying diseases and pests but also offering practical strategies, for disease control and prevention. By
addressing the challenge of disease detection and providing recommendations this system can greatly boost crop
productivity minimize financial losses and contribute to ensuring food security.

V. ACKNOWLEDGEMENTS

We are very thankful to our faculty project coordinator for supporting us during the project, teaching us about
various technologies and how to implement machine learning in coding, and helping to make our project
successful. We are also thankful to each member of the team, especially those who worked hard to make this
project successful.

VI. REFERENCES

[1] Anand H. Kulkarni, Ashwin Patil R. K., Applying image processing technique to detect plant diseases,
International Journal of Modern Engineering Research, vol.2, Issue.5, pp: 3661-3664, 2012.

[2] Tushar H. Jaware, Ravindra D. Badgujar and Prashant G. Patil, Crop disease detection using image
segmentation, National Conference on Advances in Communication and Computing, World Journal of Science and
Technology, pp:190- 194, Dhule, Maharashtra, India, 2012.

[3] Prof.Sanjay B. Dhaygude, Mr.Nitin P. Kumbhar, Agricultural plant Leaf Disease Detection Using Image
Processing, International Journal of Advanced Research in Electrical, Electronics and Instrumentation
Engineering , S & S Publication vol. 2, Issue 1, pp: 599- 602, 2013.

[4]