A Curve-based Material Recognition Method in MeV Dual-energy X-ray Imaging System

TL;DR

This paper presents a novel curve-based method for material recognition in high-energy dual-energy X-ray imaging, improving classification accuracy through calibration, correction, and image processing techniques.

Contribution

It introduces a new classification curve calibration and real-time correction strategy for enhanced material recognition accuracy in dual-energy X-ray systems.

Findings

Achieved improved material classification accuracy.

Enhanced image quality through segmentation, denoising, and colorization.

Demonstrated effectiveness of the proposed methods in cargo inspection scenarios.

Abstract

High energy dual-energy X-ray Digital Radiography(DR) imaging is mainly used in material recognition of the cargo inspection. We introduce the development history and the principle of the technology and describe the data process flow of our system. The system corrects original data to get the dual-energy transparence image. Material categories of all points in the image are identified by the classification curve which is related to the X-ray energy spectrum. For the calibration of classification curve, our strategy involves a basic curve calibration and a real-time correction devoted to enhance the classification accuracy. Image segmentation and denoising methods are applied to smooth the image. The image contains more information after colorization. Some results show that our methods achieve the desired effect.