You are on page 1of 1

2023 International Conference on Network, Multimedia and Information Technology (NMITCON)

Performance Analysis of Pre-trained Deep Learning


Architectures for Classification of Corn Leaf
Diseases
Praveen Kumar Nalli M. Venkata Subbarao Durga Prasad Garapati
Department of AI, Department of ECE, Department of AI,
2023 International Conference on Network, Multimedia and Information Technology (NMITCON) | 979-8-3503-0082-6/23/$31.00 ©2023 IEEE | DOI: 10.1109/NMITCON58196.2023.10275915

Shri Vishnu Engineering College for Women, Shri Vishnu Engineering College for Women, Shri Vishnu Engineering College for Women,
Bhimavaram, India Bhimavaram, India Bhimavaram, India
praveenkumar.nalli@svecw.edu.in mandava.decs@gmail.com durgaprasad_garapati@svecw.edu.in

Swaroop K P R.Priyakanth G Prasanna Kumar


Department of EEE, Department of ECE, Department of ECE,
Shri Vishnu Engineering College for Women, BVRIT Hyderabad College of Vishnu Institute of Technology,
Bhimavaram, India Engineering for Women, India Bhimavaram, India
swaroopkp@svecw.edu.in priyakanth.r@bvrithyderabad.edu.in godiprasanna@gmail.com

Abstract— The agriculture sector plays a crucial role in supplying Corn is highly adaptable and can be grown in a variety of
high-quality food and contributes the most to expanding climates and soil types. However, optimal growth requires
economies and populations. Plant infections can cause significant
mild temperatures and sufficient rainfall or irrigation.
harvest losses and the extinction of species. The swift
identification of plant illnesses by means of precise or automated Depending on the variety and geographic region, maize is
detection techniques can improve the quality of food production typically planted in the spring and harvested in the late summer
and reduce economic losses. In recent years, deep learning has or early fall. Corn crops provide producers with significant
significantly enhanced the accuracy of image classification and economic benefits and contribute to global food security and
object detection systems' recognition capabilities. This study
agricultural economies. The cultivation and processing of corn
discovers four distinct leaf types on the leaves of corn and
classifies them according to the plant diseases that cause them. supports industries involved in the production of sustenance,
These leaf varieties are referred to as blight, common rust, grey animal husbandry, ethanol, and other industrial applications.
leaf spot and healthy leaves. The number of samples collected for Overall, Corn crops are a vital component of global
each is 1306, 574, 1146, and 1164, respectively. By extracting deep agriculture, providing food, feed, and fuel and serving as a
features, three distinct enhanced deep neural networks (DNNs)
versatile and economically significant crop that plays an
are used to classify corn leaf disease. The validation accuracy, test
accuracy, prediction, recall, F1 score, and area under the curve essential role in meeting the agricultural and nutritional
(AUC) are analysed to determine performance. From the requirements of the world.
extensive investigations, it is noted that the classification accuracy Since these corn plants are primarily afflicted by the
for the models is as follows: 92.6% for CNN, 94.3% for AlexNet, diseases blight, grey leaf spot, and common rust, they are
95.7% for SqueezeNet, and 97.3% for Xception. The findings
susceptible to their spread [2]. These maladies have a major
indicate that the models produced during the investigation phase
to identify the leaf disease were superior to those of any current impact on crop cultivation. The effects of this disease are
machine learning (ML) classifiers. evident on the foliage of the corn plants. Multiple pathogens,
including fungi, bacteria, and viruses, can cause blights.
Keywords: Corn Leaf Disease classification, CNN, AlexNet, Lesions are frequently formed on the leaves, stalks, husks, and
SqueezeNet, Xception ears of the maize plant because of blight diseases. The size,
shape, and colour of lesions can vary depending on the specific
I. INTRODUCTION blight pathogen. They may appear as spots, patches, dashes, or
blotches of irregular shape. Grey leaf spot (GLS) is a fungal
Corn crops, scientifically known as Zea mays, are a disease caused by Cercospora zeae-maydis. It begins with tiny,
globally cultivated staple cereal crop. They are prized for their rectangular lesions that have a greyish centre and a dark brown
adaptability and nutritional value. Corn is cultivated for or tan border. As the disease progresses, the lesions can
multiple purposes, including human consumption, animal feed, elongate and coalesce, resulting in larger necrotic areas of
and industrial applications. The kernels may be ingested fresh, irregular shape on the foliage. Severe infections can cause
dried, or processed into a variety of food products, including premature leaf mortality, thereby diminishing a plant's
cornmeal, corn flour, and corn oil. In addition to its photosynthetic ability. The fungus Puccinia sorghi causes the
significance as a food commodity, maize plays an important malady known as common rust. Even though common rust can
role in the production of biofuels[1]. The kernels can be cause injury to maize plants, it is generally regarded as a less
converted into ethanol, a renewable fuel source used to severe disease than other maize diseases. On both surfaces of
decrease reliance on fossil fuels and greenhouse gas emissions. maize leaves, common rust appears as small, circular to

979-8-3503-0082-6/23/$31.00 ©2023 IEEE


Authorized licensed use limited to: G Narayanamma Institute of Technology & Science. Downloaded on January 06,2024 at 04:15:14 UTC from IEEE Xplore. Restrictions apply.

You might also like