Professional Documents
Culture Documents
Format of PPT For 7 CSE AND AI&DS
Format of PPT For 7 CSE AND AI&DS
Format of PPT For 7 CSE AND AI&DS
Project presentation
on
Submitted by:
GUIDE NAME: Dr. R. Anusuya 1. Digamber Mishra 20EMCCS038
2. Saurav Sharma 20EMCCS119
3. Tushar Saini 20EMCCS128
4. Vaibhav Gupta 20EMCCS131
5. Vinod Kumar Gupta 20EMCCS135
ABSTRACT
Agriculture is the primary source of livelihood for major rural population in India. Plant
leaf disease detection is a crucial aspect of modern agriculture, aiming to monitor and
mitigate the impact of diseases on crop yield and quality. With the rise of technology,
computer vision and machine learning techniques are being employed to develop
efficient and accurate disease detection systems. This abstract provides an overview of
the advancements in plant leaf disease detection, focusing on the integration of image
processing, pattern recognition, and artificial intelligence. Crop diseases are a
noteworthy risk to sustenance security. Emergence of accurate techniques in the field of
leaf-based image classification has shown impressive results. My proposed project
includes various phases of implementation namely dataset selection, feature extraction,
training the classifier and classification. The chosen dataset of diseased and healthy
leaves are collectively trained to classify the diseased and healthy images. Overall, using
deep learning to train the large data sets gives us a clear way to detect the disease
present in plants on a colossal scale.
PROJECT DESCRIPTION
In the context of the increasing importance of agriculture, particularly in rural areas of
India where a significant portion of the population depends on farming, the proposed
project aims to develop an automated plant disease detection system. Focusing on
tomato plants, the system utilizes image processing techniques to identify and analyse
diseases affecting the leaves. Early detection is crucial for effective disease control, and
this system provides a reliable and efficient solution.
1.Image Acquisition: The system starts with the collection of images of tomato plant
leaves, capturing various stages of health and disease.
2.Image Pre-processing: Raw images undergo pre-processing techniques to enhance
quality, remove noise, and standardize features, ensuring optimal input for subsequent
analysis.
3.Image Segmentation: Utilizing advanced image segmentation algorithms, the system
isolates the affected regions of the leaves, facilitating targeted analysis.
4.Feature Extraction: Relevant features are extracted from the segmented images,
providing valuable information for the disease classification process.
5.Classification: Leveraging deep learning techniques implemented through TensorFlow
and Keras, the system classifies the type and severity of the disease. This classification
is presented as a percentage of the affected part of the leaf.
Image Processing Phases
TECHNOLOGY STACK
Modules and Libraries for Model :
• Numpy
• scipy
• Scikit
• Tensorflow
• Keras
• Pandas
• Matplotlib
• Seaborn
• Opencv
Development Environments :
• Colab
• Pycharm
• VSCode
Front-End Framework /Libraries:
• React.js
• Bootstrap 5
Back-End Framework/Libraries :
• Flask(Python)
Working of the System
6. Send back the
result generated Backend Server
by the model
Internet
Model
REFERENCES
[1] Sebastian Raschka, Yuxi (Hayden), LiuVahid Mirjalili. "Machine Learning with
PyTorch and Scikit-Learn," , Publisher, Packt Publishing Ltd..
[2] A. Ng, "Neural Networks and Deep Learning." Deep Learning Specialization.
Deeplearning.ai, 2017. [Online]. Available: https://www.coursera.org/learn/neural-
networks-deep-learning.