A Novel Hybrid Framework to Enhance Dual-Energy X-Ray Images. (17th April 2023)

• Record Type: Journal Article
• Authors: Ullah, Burhan; Khan, Aurangzeb; Shah, Said Khalid; Su'ud, Mazliham Mohd; Alam, Muhammad Mansoor; Alam, Mahmood
• Other Names: Vargas-Rodriguez Everardo Academic Editor.
• Is Part Of: Journal of sensors. Volume 2023(2023)
• Publication Date: 2023-04-17
• Subjects: Detectors -- Periodicals; 681.205
• DOI: 10.1155/2023/8552175
• Languages: English
• ISSNs: 1687-725X

Abstract

Abstract : This research paper presents an efficient hybrid framework for the enhancement of X-ray images using the DWT (discrete wavelet transform), Gaussian, and Wiener filters. Digital X-ray images perform an important role in detecting explosives or illegal items. However, lately used X-ray images have certain shortcomings like noise, blurriness, and low contrast. Noise affects the object's edges and values of intensity of pixels which gives rise to ambiguity for the system to separate objects and also hampers the decision-making process. To overcome these issues, a new hybrid framework is proposed here that consists of two layers. First, it reads high- and low-energy X-ray images and fuses them through various fusion rules in the wavelet realm using DWT and is reconstructed using iDWT (inverse discrete wavelet transform). Subsequently, the Gaussian filter is applied to the fused image to remove the Gaussian noise, and finally, the Wiener filter is used to reduce blurriness and improve image quality. The quality of the image is measured using PSNR (peak signal-to-noise ratio) and MSE (mean squared error) values, which exhibits that an average of the MSE values of fused images is 40% lower, and the PSNR values are 10% higher than the single images. Experimental results show that this hybrid framework successfully reduced noise and blurriness and enhanced contrast and accuracy.