Development of a Neural Network Model for Recognizing Red Palm Weevil Insects Based on Image Processing

Abstract

The red palm weevil (RPW) is an invasive pest insect that attacks palm trees and threatens their existence. Accordingly, RPW causes significant and massive economic losses during the last two decades. This issue makes the early detection of RPW is a hot research topic. This study proposes a machine learning technique based on image processing to easily recognize these insect species for people who do not know them. The basic idea of the proposed research is to develop a neural network model that can use image processing to identify RPW and distinguish it from other insects found in palm tree habitats. This model consists of three stages: image pre-processing (image enhancement and segmentation using Otsu's thresholding), feature extraction (texture and color moments features), and classification (artificial neural network). The dataset used in this study includes 913 images, where 448 are RPWs' images, and the rest are ants' images. The experimental results of the ten-fold cross-validation show that the accuracy of the proposed model is 92.22%.