Enhancing chest x-ray classification performance through contrast stretching and MobileNetV2

Oktiana, Maulisa and Salima, Mutia and Mina Rizky, Muharratul and Haja Mohideen, Ahmad Jazlan (2026) Enhancing chest x-ray classification performance through contrast stretching and MobileNetV2. In: 22nd IEEE International Colloquium on Signal Processing & Its Applications (CSPA), 1-2 May 2026, Kuala Lumpur.

	PDF - Published Version Restricted to Repository staff only Download (503kB) | Request a copy
Preview	PDF - Supplemental Material Download (150kB) | Preview

Abstract

Chest X-ray imaging is widely used for diagnosing pulmonary diseases. However, suboptimal contrast and image noise can degrade image quality and limit deep learning models' ability to extract discriminative features. This paper proposes the integration of contrast stretching as an image enhancement technique to improve the performance of a MobileNetV2-based chest X-ray classification system. Experiments were conducted on 854 chest X-ray images collected from Dr. Zainoel Abidin Regional General Hospital, Banda Aceh, Indonesia, comprising three classes: Normal, Pneumonia, and COVID-19. The experimental results show that the proposed approach improves classification accuracy from 91% to 95%, with consistent gains in precision, recall, and F1 Score. The findings suggest that contrast stretching improves image quality and supports more effective feature learning in the lightweight MobileNetV2 architecture, contributing to better classification performance while maintaining low computational complexity.

Item Type:	Proceeding Paper (Plenary Papers)
Uncontrolled Keywords:	chest x-ray, image enhancement, contrast stretching, MobileNetV2, SDG 3: Good Health and Well-Being
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices > TK7885 Computer engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Mechatronics Engineering Kulliyyah of Engineering
Depositing User:	Dr Ahmad Jazlan Haja Mohideen
Date Deposited:	17 Jun 2026 15:37
Last Modified:	17 Jun 2026 15:37
Queue Number:	2026-06-Q3665
URI:	http://irep.iium.edu.my/id/eprint/129259

Actions (login required)

View Item