Plant Disease Detection and Classification Using a Deep Learning-Based Framework

Ghosh, Mridul; Lasker, Asifuzzaman; Banerjee, Poushali; Manna, Anindita; Obaidullah, Sk Md; Gonçalves, Teresa; Roy, Kaushik

doi:10.1007/978-3-031-48232-8_5

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper presents a CNN framework for detecting 15 types of leaf diseases in Tomatoes, Potatoes, and Bell peppers, utilizing the Plant Village dataset. Our model, evaluated on metrics like Accuracy, Precision, Recall, and F1-score, demonstrated superior performance over existing techniques, offering promising results in disease identi cation and classi cation accuracy [9].…”

Section: Literature Reviewmentioning

confidence: 95%

“…In this paper, we delineate our proposed system architecture, elucidating the integration of CNN-based disease detection algorithms with hardware modules for fertilizer preparation. We also discuss the implementation challenges and considerations pertinent to deploying such a system in real-world agricultural settings [9]. Through experimental validation and case studies, we showcase the e cacy and potential impact of our approach on enhancing crop productivity, sustainability, and food security.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Deep Learning-Driven Plant Disease Detection and Custom Fertilizer Formulation

Chavan(Cholke),

Mahajan,

Patil

et al. 2024

Preprint

View full text Add to dashboard Cite

Plant Disease Detection aims to revolutionize agricultural management by integrating an InceptionV3 for precise, real-time detection of plant diseases with an innovative hardware system for the custom preparation of fertilizers. Traditional farming practices, plagued by inefficient resource usage, generalized disease management, and suboptimal fertilization, often lead to reduced crop health and environmental damage. Our approach leverages InceptionV3 that achieves a 97.34% accuracy rate in diagnosing various plant diseases by analyzing field images. Our custom fertilizer formulation system is designed to automatically mix two liquid fertilizers into a single, properly proportioned solution, eliminating the need for manual handling. This automated approach not only ensures precise blending but also enhances safety by preventing direct contact with potentially harmful substances. By integrating this system into agricultural practices, we aim to improve both efficiency and safety in fertilizer application. This integrated solution not only optimizes resource management but also promotes sustainable farming practices by ensuring precise nutrient application and effective disease control. The results highlight the benefits of combining advanced technologies to address agricultural challenges, advocating for their broader implementation in modern farming systems to improve crop yield and quality.

show abstract

Section: Literature Reviewmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 98%