International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 03 | Mar 2025
p-ISSN: 2395-0072
www.irjet.net
Arecanut Plant Disease Detection System Using Deep Learning M S PRAKASH KUMAR REDDY, ANJANA DWARAKANATH B, SANJAY A, SANTHOSH KUMAR J, MUNIRAJU M, NAGENDRA BABU N C Student, dept of AI&ML, SJCIT College, Karnataka, India Student, dept of AI&ML, SJCIT College, Karnataka, India Student, dept of AI&ML, SJCIT College, Karnataka, India Student, dept of AI&ML, SJCIT College, Karnataka, India Assistant professor, dept of AI&ML, SJCIT College, Karnataka, India Assistant professor, dept of AI&ML, SJCIT College, Karnataka, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Arecanut (Areca catechu) is a major
and minimize losses. Recent advancements in artificial intelligence (AI) and deep learning, particularly Convolutional Neural Networks (CNN), have revolutionized automated disease detection. CNN models can analyze plant images and classify diseases with high accuracy, reducing dependency on expert evaluations. This study focuses on developing a CNN-based disease detection system to assist farmers in timely and effective crop management.
commercial crop in India, primarily grown in Karnataka, Kerala, and Assam. However, plant diseases significantly affect its yield and quality, leading to economic losses. Traditional disease detection methods rely on manual inspection, which is time-consuming, error-prone, and inefficient for large-scale plantations. This study proposes a deep learning-based automated disease detection system using Convolutional Neural Networks (CNN), specifically ResNet architecture. The system processes arecanut images, extracts disease-specific features, and classifies plant health conditions with high accuracy. The methodology includes data collection, preprocessing, CNN model development, and performance evaluation. The proposed model achieves over 97% accuracy, surpassing traditional approaches. A userfriendly interface enables farmers to upload plant images and receive instant disease diagnoses and treatment recommendations. This automated approach minimizes dependency on experts, facilitates early intervention, and reduces crop losses. Future improvements include IoT-based real-time monitoring and expansion to detect diseases in multiple crops. By integrating AI-driven solutions, this study aims to enhance disease management in agriculture, ensuring sustainable and profitable arecanut farming.
Need for Automated Disease Detection Arecanut cultivation faces significant challenges due to various plant diseases that affect yield and quality. Farmers traditionally rely on manual inspection, which is laborintensive, subjective, and prone to errors. Early and accurate detection of diseases is crucial to prevent crop losses and ensure sustainable farming. With advancements in artificial intelligence, deep learning models, particularly Convolutional Neural Networks (CNN), offer a reliable and efficient solution. This study aims to develop an automated disease detection system to assist farmers in timely disease identification and management.
Importance of Arecanut Cultivation
Key Words: (Deep learning, Convolutional Neural Networks, ResNet, Arecanut disease detection, Image classification, Smart agriculture, Automated diagnosis, IoT integration.)
Arecanut is widely used in chewing products, medicine, and cultural practices. The crop requires specific climatic conditions and is highly sensitive to environmental changes. With increasing demand in domestic and international markets, effective disease management is essential. Automated disease detection can help farmers maintain crop health and improve productivity.
INTRODUCTION Arecanut (Areca catechu) is a commercially important crop in India, primarily cultivated in Karnataka, Kerala, and Assam. It is widely used in chewing products, medicinal applications, and cultural practices. However, arecanut cultivation faces significant challenges due to various plant diseases, leading to reduced yield and financial losses for farmers. Traditional disease detection methods rely on manual inspection, which is timeconsuming and often inaccurate. Early and precise disease identification is crucial to prevent widespread infections
© 2025, IRJET
|
Impact Factor value: 8.315
Literature Review The field of automated plant disease detection has gained significant attention with advancements in artificial intelligence and deep learning. Traditional methods of disease detection, such as manual inspection and laboratory analysis, are time-consuming, labor-intensive, and prone to human error. Machine learning techniques,
|
ISO 9001:2008 Certified Journal
|
Page 176