Implementation of Laplacian-Based Image Sharpening on X-Ray Images

Abstract

X-ray imaging plays an essential role in modern medical diagnostics; however, the resulting images often suffer from low contrast and unclear edge structures. These limitations reduce anatomical visibility and may negatively affect diagnostic accuracy. Therefore, there is a need for a simple, effective, and computationally efficient image enhancement method that can improve X-ray image sharpness while preserving critical diagnostic information. Objective: This study aims to implement and analyze the Laplacian method for enhancing the sharpness of chest X-ray images using digital image processing techniques based on Python and OpenCV. The study also evaluates the effectiveness of the proposed method in improving the visibility of anatomical structures in radiographic images. Methodology: This research adopts a quantitative experimental approach based on computational implementation. The dataset consists of digital X-ray images processed through several stages, including image acquisition, grayscale conversion, Laplacian filtering, image sharpening, and result visualization. The entire implementation is conducted using Python and OpenCV in the Google Colab cloud computing environment. Data analysis is performed using a descriptive-visual approach by comparing original and enhanced images. Findings: The results show that the Laplacian method significantly improves edge visibility in X-ray images. Anatomical structures such as ribs, lung boundaries, and fine edge details become more distinguishable compared to the original images. Local contrast enhancement is also observed, indicating that high-frequency information is effectively amplified. However, a slight increase in noise is detected due to the sensitivity of the Laplacian operator to high-frequency components. Implications: The findings suggest that the Laplacian method can be effectively used as a lightweight preprocessing technique for medical image enhancement, particularly in cloud-based environments such as Google Colab. The method is suitable for educational purposes, research applications, and engineering systems that require low computational cost while maintaining effective image enhancement performance. Originality: The originality of this study lies in the development of a simple, reproducible, and cloud-based implementation framework for Laplacian-based X-ray image enhancement using Python and OpenCV. The main contribution is a lightweight computational approach that balances implementation simplicity with effective image sharpening performance.