Automated Classification of Blackgram Plant Diseases Using ResNet-50: A Focus on Cuscuta Detection
Journal Title: International Journal for Modern Trends in Science and Technology - Year 2024, Vol 10, Issue 10
Abstract
The identification and classification of plant diseases are crucial for ensuring the health and productivity of crops like blackgram (Vigna mungo), a widely cultivated legume. Among various threats, parasitic plants like Cuscuta (dodder) pose significant challenges, leading to severe yield losses. Traditional manual disease detection methods are time-consuming and prone to human error, highlighting the need for automated, accurate solutions. In this study, we propose a deep learning-based approach utilizing the ResNet-50 architecture to automatically classify diseases affecting blackgram plants, with a special focus on detecting Cuscuta infestations. ResNet-50, a robust convolutional neural network (CNN), is employed due to its ability to handle complex image recognition tasks while maintaining high accuracy. A dataset of blackgram plant images, including healthy plants and those affected by Cuscuta, was curated for training and validation. The model was trained using labeled images, achieving high classification accuracy through transfer learning and fine-tuning techniques. Data augmentation was employed to increase the dataset's diversity and improve model generalization. Our results demonstrate that the ResNet-50 model can effectively distinguish between healthy plants and those infested by Cuscuta, with an accuracy exceeding 98%. This automated system offers a scalable, efficient solution for early detection, enabling timely intervention and minimizing crop damage. Future work will focus on expanding the model's scope to identify other diseases and improving its real-time deployment capabilities in agricultural settings.
Authors and Affiliations
Nadakuditi Swarna Jyothi and Raavi Satya Prasad
Keywords
Related Articles
- EP ID EP752206
- DOI https://doi.org/10.46501/IJMTST1010002
- Views 51
- Downloads 0
Predicting Autism Spectrum Disorders Through Machine Learning Techniques
These days, autism spectrum disorder complaint is getting a wider issue affecting people of all periods. The conservation of the case's physical and internal health can be mainly backed by early opinion of this neurologi...
Advanced Power Management and Control for EV Charging Using Magnetically Linked Converters with AC-DC Load Balancing and Grid-Connected Solar, Wind, and Battery Integration
This paper presents an advanced power management system for electric vehicle (EV) charging applications, integrating a magnetically linked power converter with grid-connected renewable energy sources like solar photovolt...
The Big Five Factors and Facial Recognition: An Exploratory Study
Facial recognition is a key social and cognitive ability that allows individuals to identify and remember faces. While cognitive models explain the processes involved, they often overlook why some individuals perform bet...
Optimized Design and Control of a Solar-Battery Powered BLDC Drive Using Ultra High-Gain Switched-Capacitor Boost Converter Ripple Reduction
This paper presents the design and control of a solar battery powered Brushless DC (BLDC) motor drive system utilizing an ultra high gain switched capacitor boost DC DC converter for efficient energy management and rippl...
Coordinated Control and Power Quality Enhancement of a Hybrid DC/AC Microgrid Using DPFC and Renewable Energy Integration
This paper presents a coordinated control strategy for a hybrid DC AC microgrid integrating photovoltaic PV wind turbine driven permanent magnet synchronous generator PMSG and a battery energy storage system BESS focusin...