Nutrient Deficiency Detection in Mobile Captured Guava Plants using Light Weight Deep Convolutional Neural Networks

Abstract

Nutrition deficiency in plants is a major problem that affects their growth, yield, and nutritional value. Over the past few years, there has been a significant growth in the application of machine learning and computer vision techniques, in early detection and classification of plant disorders. This study, proposes a deep learning-based approach for detecting nutritional deficiencies in guava leaf images. A dataset of guava leaf images captured using mobile devices, containing various nutritional deficiencies including magnesium and phosphorous, was acquired for training the model. A pre-trained deep CNN model is employed to extract convolved features and detect the affected regions, categorizing them as nutritional deficient or non-nutritional deficient Experimental results show that the proposed method achieved an accuracy of 87% in detecting nutritional deficiencies in guava leaf images. These outcomes demonstrate that the proposed approach provides a reliable and accurate method for early detection of nutritional deficiencies in guava leaves. This approach has the potential to be deployed in the agricultural domain for the effective diagnosis of plant nutrient deficiencies, ultimately increasing crop productivity and nutritional quality.