Digitalization of X-Ray Films Using Image Stitching

Abstract

This dissertation describes the technical and algorithmic details of a fast low cost method for the digitalization of X-ray films of allstandard sizes. In order to keep costs low, a standard A4 size flatbed scanner with transparency media adapter was used. Since most X-ray films are larger than the A4 size image capturing area of the scanner, it was necessary to develop an image processing algorithm that could stitch two or four partial images of the whole X-ray film, depending on its size, into a seamless full image of the film. Another important feature of the algorithm is that it automatically detects and corrects the most common user error of slightly tilted partial images and produces a warning message if the tilt is large enough that it may affect the quality of the stitched image. Similarly, non-uniformity of the brightness in the partial images is also compensated for in the stitching process. The proposed image stitching algorithm produces high resolution seamless images with good contrast and quality that permits their use in a tele-radiology project, which is the final goal.