Improving X-ray Industrial Images: A Python-Based Approach

This article introduces an approach based on using Python in the processing of industrial X-ray radiographs. This approach utilizes three key image processing techniques including bilateral filtering, unsharp masking, and wavelet transformation to enhance the contrast, reduce noise, and improve structural detail of X-ray radiographs, especially in industrial applications. It targets and can help industry and nondestructive testing (NDT) specialists to further improve their analysis and decision-making accuracy. To perform the experimental tests, a laboratory test setup including an industrial x-ray generator and a flat panel detector were utilized. The obtained results show a good improvement in signal-to-noise ratio (SNR) while effectively preserving image structures. A detailed quantitative analysis using mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) approved the effectiveness of the mentioned techniques. The findings show the potential of the implemented method in industrial radiography, especially for improved defect detection and quality assurance.