Scribd
Upload
26 views2 pages

Major Abstarct

This document summarizes current research on using deep learning for plant disease detection. It discusses how deep learning approaches can recognize and categorize diseased plant leaves from photographs. While deep learning shows potential, factors like lighting, development phases, and leaf orientation can impact accuracy. The document also reviews literature on using convolutional neural networks and machine learning to enable timely detection of plant diseases from leaf images in order to improve agricultural productivity and food security. However, more robust models and larger real-world datasets are still needed to address challenges in disease identification.

Uploaded by

mani MONEY
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
26 views2 pages

Major Abstarct

This document summarizes current research on using deep learning for plant disease detection. It discusses how deep learning approaches can recognize and categorize diseased plant leaves from photographs. While deep learning shows potential, factors like lighting, development phases, and leaf orientation can impact accuracy. The document also reviews literature on using convolutional neural networks and machine learning to enable timely detection of plant diseases from leaf images in order to improve agricultural productivity and food security. However, more robust models and larger real-world datasets are still needed to address challenges in disease identification.

Uploaded by

mani MONEY
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

ABSTRACT

Deep learning for plant disease detection has drawn a lot of interest since it has the
potential to completely alter agricultural methods. This project provides a thorough analysis
of current developments in the use of deep learning for plant disease diagnosis. The study
describes several approaches and architectures used to recognize and categorize sick plant
leaves from photographs. Additionally, it talks about how changes in illumination,
development phases, and leaf orientation might affect how accurately diseases can be
detected. This study intends to provide a significant resource for academics and practitioners
interested in harnessing deep learning for precise and effective plant disease diagnosis by
exploring the accomplishments, limits, and continuing research initiatives in this field. In the
end, utilizing deep learning's capabilities in this situation might considerably aid in assuring
global food security and sustainable agriculture methods.

PROBLEM STATEMENT
Agriculture holds significant importance in India's economy, engaging a substantial portion
of the workforce. India's global leadership in producing essential crops like pulses, rice,
wheat, and spices underscores its agricultural significance. The prosperity of farmers depends
on the quality of their produce, contingent on successful plant growth and yield. Disease
identification in plants is crucial due to its impact on agricultural productivity. Plant diseases
impede growth, posing ecological and economic challenges to farmers. Automated disease
detection is invaluable for early diagnosis, as plants are vulnerable to various diseases
affecting different parts, such as leaves. Manual diagnosis is time-consuming; hence,
computational methods are imperative to automate disease detection and classification using
leaf images.

LITERATURE SURVEY
1. Agriculture's central role in society is evident as nearly 60% of the population engages in
it directly or indirectly. The absence of disease detection technology in traditional
agricultural systems hampers productivity growth. Early identification of crop diseases is
crucial due to their impact on growth. While Machine Learning (ML) models have been
used, recent advancements in Deep Learning (DL) offer improved accuracy. This
proposed approach employs convolutional and deep neural networks for precise crop
disease symptom recognition, evaluated using various metrics. The review explores DL
models for visualizing crop diseases and identifies research gaps for early detection. The
proposed methodology focuses on a convolutional neural network-based strategy for
timely plant leaf disease detection.
2. Deep learning is effective in identifying plant leaf diseases, but inadequacies exist. Many
proposed frameworks lack robustness across different datasets, necessitating more
adaptable models. Larger real-world datasets are needed for better evaluation, and
challenges in labeled datasets and identifying invisible disease symptoms hinder
hyperspectral imaging's potential for plant disease detection.
3. Deep Learning (DL) emerged as a subset of Machine Learning (ML) in 1943, with two
distinct evolutionary phases: 1943–2006 and 2012–present. The first phase witnessed
foundational developments like backpropagation, Neocognitron, and LeNET architecture.
The second phase brought about breakthroughs in various domains including self-driving
cars, healthcare, text recognition, and finance, with pivotal architectures such as AlexNet
winning the ImageNet challenge in 2012. Performance evaluation employed metrics like
top-1%/top-5% error, precision, recall, F1 score, and classification accuracy.

REFERNCE
[1] Special Issue of Second International Conference on Advancements in Research and
Development (ICARD 2021) “Plant Disease Detection Using Deep Learning”.

[2] “Plant Disease Detection and Classification by Deep Learning”—A Review LILI LI1 , SHUJUAN
ZHANG 2 , AND BIN WANG 2.

[3]” Plant Disease Detection and Classification by Deep Learning “ by Muhammad Hammad Saleem,

Johan Potgieter,Khalid Mahmood Arif.

[4]

You might also like