Rice plant nutrient deficiency classification using modified MOBILENET convolutional neural network

MobileNet Convolutional Neural Network is a predominately used Deep Learning (DL) model in various computer/mobile vision applications. However, it is clear from the literature that the researches using MobileNet Convolution Neural Network (CNN) reported with only minimal level of classification accuracy in the case of plant nutrient deficiency classification. As a result, on the benchmark rice plant dataset, a modified MobileNet CNN architecture is proposed in this study for nutrient deficiency classification. Insertion of additional new layers, a system to handle dropout and selecting appropriate optimizer are among the alterations included in this proposed method to increase the model performance accuracy. Subsequently, the performance of the modified MobileNet CNN model is evaluated using well-defined performance metrics such as accuracy, Fl-score, precision, and recall. In addition, the performance of the proposed modified MobileNet CNN model is compared with the state-of-the-art conventional DL models such as VGG16, VGG19, ResNet152, ResNet152V2, ResNet101, ResNet101V2, ResNet50, ResNet50V2, InceptionV3, InceptionResNetV2, MobileNet, and MobileNetV2. Empirical evaluation of the proposed model with the cutting-edge DL models shows that the modified MobileNet CNN model outperforms the aforementioned DL models. Finally, we have developed a web and mobile application for automatically classifying nutrient deficiency in rice plants that the farmers could easily use.