• Dr.S.Karthika
• Jecintha Roselin J
• JERIN WINCY W
• Mathumitha M
• Iruthaya Britto Sherin A

In India, cotton is considered one of the most important cash crops, with a large number of farmers cultivating it extensively. Over the past few decades, diseases affecting cotton have led to significant losses in yield and productivity. Early-stage diagnosis of cotton diseases is crucial for effective management. The goal of our proposed work is to present a deep learning (DL)-based approach for cotton leaf disease detection using fine-tuned Transfer Learning (TL) algorithms. This approach involves tuning the layers and parameters of existing TL models. The proposed method evaluates the performance of several fine-tuned TL models, such as Inception-V3 and DenseNet121, using a publicly available cotton leaf disease dataset. Among these, DenseNet121 achieved the highest accuracy of 98.49% and was selected for developing a web-based smart application aimed at real-life cotton disease prediction in farming, ultimately helping to increase cotton production. The model’s high accuracy demonstrates its potential for reliable diagnosis of cotton leaf diseases and opens the door for automatic leaf disease diagnosis in other crops as well

Cotton leaf, Disease, Deep learning, Transfer learning, Diagnose, Prediction

"A Deep Learning Model for Cotton Leaf Disease Detection with Smart Web Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.c736-c744, May-2025, Available :http://www.jetir.org/papers/JETIR2505299.pdf

"A Deep Learning Model for Cotton Leaf Disease Detection with Smart Web Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppc736-c744, May-2025, Available at : http://www.jetir.org/papers/JETIR2505299.pdf