Material Detection Based on GMM-Based Power Density Function Estimation and Fused Image in Dual-Energy X-ray Images

Material detection is a vital need in dual-energy X-ray luggage inspection systems at security of airport and strategic places. In this paper, a novel material detection algorithm based on power density function (PDF) estimation of three material categories in dual-energy X-ray images is proposed. In this algorithm, PDF of each material category is estimated from grayscale values of a synthetic image that is called fused image, using Gaussian Mixture Models (GMM). The fused image is obtained from wavelet sub bands of high energy and low energy X-ray images. High and low energy X-ray images enhance using two background removing and denoising stages as a preprocessing procedure. The proposed algorithm is evaluated on real images that have been captured from a dual-energy X-ray luggage inspection system. The obtained results show that the proposed algorithm is effective and operative in detecting of metallic, organic and mixed materials with acceptable accuracy.