Towards the Deployment of Deep Learning Solutions in Plant Nutrient Deficiency Identification and Classification

In recent years, identifying plant nutrient deficiency is considered a critical issue in smart agriculture research. Identifying plant nutrient deficiency at an early stage will undoubtedly improve the quality and quantity of agricultural products. However, identifying the nutrient deficiency in the affected plant leaves is challenging for the farmers. Therefore, developing an automated system becomes essential to detect the deficiency so that remedies can be suggested according to the nutrient deficiency. In this context, Deep Learning (DL) models have recently been used to identify and classify the type of nutrient deficiency in plants. Hence, this work investigates the importance of deploying the various DL models such as MobileNet, MobileNetV2, DenseNet121, DenseNet169 and DenseNet201 in automatically classifying plant nutrient deficiency on the benchmark Rice, Wheat and Okra dataset.