A Statistical Feature Extractor-Based Method Using Row and Column Grid for Monkeypox Detection

Abstract

Monkeypox disease, currently called Mpox, was declared a global pandemic by the World Health Organization (WHO) in 2024. The most prominent symptom of the disease is lesions that appear on the hands and body. In this study, these lesions were detected from images. Detection of lesions is similar to fault detection on the image. Therefore, statistical feature extraction was performed using a row and column grid. After applying the Relief algorithm to the obtained features, they were classified with the help of the k-Nearest Neighbors (k-NN) algorithm. In this form, a lightweight method that does not employ deep learning has been presented. The Monkeypox Skin Lesion Dataset (MSLD) was used as the dataset in its raw and augmented form. The obtained results are better or closer to deep learning-based methods. © 2024 IEEE.