Development of a Coati-Optimized Convolutional Neural Network for infected citrus fruit detection and classification system

Abstract

Pest and disease management plays a significant role in minimizing losses to crops, particularly in citrus fruit production. Traditional methods for detecting and classifying infected citrus fruits are complex and tasking, while Convolutional Neural Networks (CNNs) offer promising solutions but still face challenges such as high computational requirements and data dependency. Therefore, this study developed an improved convolution neural network for infected citrus fruit detection and classification system using Coati Optimization Algorithm (COA). A dataset of 1,790 citrus images, containing samples of black spot, greening spot, citrus canker, and healthy fruits, was acquired from www.kaggle.com. The images underwent preprocessing involving cropping to remove unwanted elements, conversion to grayscale to simplify processing, normalization to enhance data consistency and reduce redundancy, and filtering to minimize noise. An optimized CNN model was formulated using COA to tune the hyperparameters (weight and learning rate) of CNN to produce Coati Optimization Algorithm–based Convolutional Neural Network (COA-CNN). The preprocessed images serve as input to the COA-CNN model. The COA-CNN was used for the extraction of edges, corners, texture, patterns and shapes, and classification of citrus fruits as infected or healthy. The developed system was implemented using MATLAB R(2023a). The system’s performance was evaluated using accuracy, false positive rate, sensitivity, specificity, and recognition time. A comparative analysis of CNN and COA-CNN was also carried out. The accuracy, false positive rate, sensitivity, specificity, and recognition time for CNN were 95.83%, 6.02%, 96.63%, 93.98% and 202.17 s, respectively, while the corresponding values for COA-CNN were 96.92%, 4.22%, 97.41%, 95.78% and 136.86 s. This research showed that COA-CNN performed better and is recommended for citrus disease detection and classification systems.