Enhancement of X-ray Images using OpenCV for Improved Medical Visualization in Low-Resource Settings

Medical X-ray imaging plays a critical role in diagnosis, but grayscale images often limit visual interpretability, especially in low-resource settngs where advanced imaging modalities are unavailable. This work presents an OpenCV-based approach for enhancing and colorizing X-ray images to improve medical visualization. The method applies Contrast Limited Adaptive Histogram Equalization (CLAHE) [6] [26] for contrast improvement, Gaussian smoothing and weighted sharpening [4] [7] for edge clarity, followed by a beige-tint colorization scheme and background masking for bone emphasis. The proposed method was tested on a dataset of 200 X-ray images collected from Kaggle and other open-access sources, with 10 representative images reported in the results. Quantitative evaluation was performed using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) [5] [23]. The results show average values of MSE 947, PSNR 18.6 dB, and SSIM 0.37, indicating significant enhancement while preserving anatomical structures. This lightweight and low-computational approach demonstrates that X-ray visualization can be improved without deep learning models [16][20], making it suitable for deployment in low-resource clinical environments. Future work includes integrating deep learning-based adaptive colorization [1] [18] [20] and clinical validation with expert radiologists. Keywords - ray Colorization, OpenCV, Medical Image enhancement, CLAHE, Image Enhancement, SSIM, PSNR, MSE