Authors:
Kamalpreet Kaur, Kotova Anna Sergeevna
Addresses:
Department of Computer Science, Lovely Professional University, Phagwara, Punjab, India. Department of Pathological Physiology, Kyrgyz-Russian Slavic University, named after the first President of the Russian Federation Boris Nikolaevich Yeltsin, Bishkek, Kyrgyzstan, Russia.
Abstract:
Strawberry cultivation is highly susceptible to various diseases, significantly impacting yield and quality. Early and accurate detection of plant diseases is crucial for effective management and mitigation strategies. Traditional disease detection methods, such as visual inspection and laboratory testing, are time-consuming and often inaccurate. This study uses image-based analysis to explore the application of deep learning techniques for the automated detection of diseases in strawberry plants. We employed transfer learning on pre-trained convolutional neural network (CNN) models, including Xception, DenseNet169, and MobileNet, to classify and predict plant diseases. The models were trained and evaluated using a diseased and healthy strawberry plant images dataset. Furthermore, an ensemble model was developed to enhance prediction accuracy by combining multiple deep-learning models. A web-based application was designed using Flask, HTML, CSS, JavaScript, and Bootstrap, enabling farmers to upload plant images and receive real-time disease diagnosis and treatment recommendations. Experimental results indicate that deep learning models offer high accuracy in disease detection, thereby providing an efficient and scalable solution for disease management. This research demonstrates the potential of AI-driven approaches in precision agriculture, contributing to improved crop health, yield, and sustainable farming practices.
Keywords: Deep Learning; Strawberry Disease Detection; Transfer Learning; Ensemble Models; Precision Agriculture; Convolutional Neural Networks (CNN); Crop Diseases; Agricultural Sector.
Received: 08/05/2024, Revised: 22/08/2024, Accepted: 01/10/2024, Published: 07/12/2024
AVE Trends in Intelligent Health Letters, 2024 Vol. 1 No. 4 , Pages: 217-227