Efficient x-ray image enhancement algorithm using image fusion

Abstract

Multiresolution Analysis (MRA) plays an important role in image and signal processing fields, and it can extract information at different scales. Image fusion is a process of combining two or more images into an image, which extracts features from source images and provides more information than one image. The research presented in this article is aimed at the development of an automated imaging enhancement system in digital radiography (DR) images, which can clearly display all the defects in one image and don't bring blocking effect. In terms of characteristic of the collected radiographic signals, in the proposed scheme the subsection of signals is mapped to 0–255 gray scale to form several gray images and then these images are fused to form a new enhanced image. This article focuses on comparing the discriminating power of several multiresolution images decomposing methods using contrast pyramid, wavelet, and ridgelet respectively. The algorithms are extensively tested and the results are compared with standard image enhancement algorithms. Tests indicate that the fused images present a more detailed representation of the x-ray image. Detection, recognition, and search tasks may therefore benefit from this.