Review of Machine Learning Techniques for Identifying Nutrient Deficiencies in Okra Leaves: Progress and Future Prospects

Abstract

Nutrient deficiencies in plants often present as visual symptoms on leaves, but manual identification is imprecise and depends heavily on expert knowledge. Traditional diagnostic methods are time-consuming and labor-intensive. This study introduces an automated approach that applies machine learning and image processing to detect nutrient deficiencies in okra (Abelmoschus esculentus L.) leaves. By analyzing features such as color, texture, and shape, the model is trained to classify deficiencies using Convolutional Neural Networks (CNNs), known for their strong performance in image analysis. The system leverages a diverse dataset of leaf images to ensure reliability under real-world conditions. This approach offers a scalable and efficient tool for supporting farmers in nutrient management, contributing to improved crop yields, optimized fertilizer use, and more sustainable agricultural practices