HoG-Based Machine Learning Models for Efficient Classification of COVID-19, Pneumonia, and Normal Chest X ray Images
Keywords:
COVID-19, X-ray, image classification, HOG, machine learning, medical imagingAbstract
Chest X-ray analysis remains a pivotal tool for the initial screening of COVID-19, despite limitations in sensitivity and specificity. This study investigates the integration of Histogram of Oriented Gradients (HoG) features with various machine learning algorithms to classify chest X-ray images into COVID-19,Pneumonia, and Normal categories. HoG features provide a robust foundation for feature extraction, and their integration with machine learning models such as Support Vector Machines (SVM), Random Forest, and k-Nearest Neighbors (KNN) has been comprehensively evaluated. The research highlights the strengths of SVM and Logistic Regression, which achieved an accuracy of 96% and an MCC of 0.92, showcasing their effectiveness for the task. In contrast, KNN and Random Forest exhibited moderate performance, while Decision Tree algorithms showed significant limitations. These findings underline the
foundational role of HoG features and machine learning models in advancing automated diagnostic systems. While hand-crafted features like HoG laid the groundwork, the field is evolving rapidly with the advent of more sophisticated approaches, including deep learning. Future research should focus on optimizing algorithms for better accuracy, integrating deep learning-based methods, and enhancing model generalizability. This work underscores the importance of interdisciplinary collaboration and emerging technologies in developing reliable diagnostic tools to combat the ongoing global pandemic.
References
Absar, N., Mamur, B., Mahmud, A., Emran, T. B., Khandaker, M. U., Faruque, M. R. I., ...&Elkhader, B. A. (2022). Development of a computer-aided tool for detection of COVID-19 pneumonia from CXR images using machine learning algorithm. Journal of Radiation Research and Applied Sciences,
(1), 32-43. Al-Jumaili, S., Al-Azzawi, A., Duru, A. D., & Ibrahim, A. A. (2021, October). Covid-19 X-ray image classification using SVM based on Local Binary Pattern. In 2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) (pp. 383-387). IEEE.Awotunde, J. B., Ajagbe, S. A., Oladipupo, M. A., Awokola, J. A., Afolabi, O. S., Mathew, T. O., &Oguns, Y. J. (2021, October). An improved machine learnings diagnosis technique for COVID-19 pandemic using chest X-ray images. In International Conference on Applied Informatics (pp. 319-330). Cham: Springer International Publishing.
