Amalgamated convolutional long term network (CLTN) model for Lemon Citrus Canker Disease Multi-classification

Abstract

Lemon disease detection has been a hot topic of research for decades, thanks to the rising demand and supply for the commodity, which has increased the number of diseases found in the crop. Lemon citrus canker (LCC) is one of those diseases that has a draconian effect on lemon production, and to eliminate that factor, deep learning (DL) based convolutional long term network (CLTN) amalgamated model of convolutional neural networks (CNN) and long short term memory (LSTM) has been developed to build a system for detecting and classifying a 3000 image dataset of LCC disease based on four different disease levels. The implementation of the hybrid model resulted in a binary classification accuracy of 94.2%, while the best accuracy of 98.43% in the case of early level of LCC disease severity multi-classification. The proposed model is an effective model for image classification in terms of accuracy outcomes.