A Novel Image Processing Algorithm for Enhancing the Probability of Detection of Flaws in X-Ray Images

Application of Digital Signal Processing (DSP) techniques in x-ray radiography is a field that is gaining a rapidly growing interest. Dealing with digital x-ray images and enhancing these images using DSP techniques allow the automation of x-ray inspection, which offers several advantages over the traditional film-based inspection. These advantages include reducing the inspection time and cost requirements, obtaing a consistent decision regarding the integrity of the object under test, and allowing the use of real-time inspection [1]. Typically processing of x-ray images to detect and size flaws involves edge detection. In this paper, we primarily focus on an image processing algorithm that is based on a new Gaussian weighted image moment vector edge operator. Application of this operator enhances image edges and suppresses the noise, which results in a significant improvement in the probability of detection of flaws in x-ray images.