Automatic X-ray image segmentation and clustering for threat detection

Abstract

Firearms currently pose a known risk at the borders. The enormous number of X-ray images from parcels, luggage and freight coming into each country via rail, aviation and maritime presents a continual challenge to screening officers. To further improve UK capability and aid officers in their search for firearms we suggest an automated object segmentation and clustering architecture to focus officers' attentions to high-risk threat objects. Our proposal utilizes dual-view single/ dual-energy 2D X-ray imagery and is a blend of radiology, image processing and computer vision concepts. It consists of a triple-layered processing scheme that supports segmenting the luggage contents based on the effective atomic number of each object, which is then followed by a dual-layered clustering procedure. The latter comprises of mild and a hard clustering phase. The former is based on a number of morphological operations obtained from the image-processing domain and aims at disjoining mild-connected objects and to filter noise. The hard clustering phase exploits local feature matching techniques obtained from the computer vision domain, aiming at sub-clustering the clusters obtained from the mild clustering stage. Evaluation on highly challenging single and dual-energy X-ray imagery reveals the architecture's promising performance.

An Optimized Mask R-CNN with Bag-of-Visual Words and Fast+Surf Algorithm in Sharp Object Instance Segmentation for X-ray Security

“…The study used dual-view single/dual-energy 2D X-ray imagery and a triplelayered processing scheme based on the atomic number of the contents of the luggage. It combined radiology, image processing, and computer vision concepts [6]. The study supports the research as it aims to improve the current method of detecting high-risk objects and enhancing the results [6].…”

“…The SURF algorithm can achieve this by using color invariant transformations, information entropy theory, and a set of constraint conditions to improve feature point identification and matching. In line with the study, a study from 2017 suggested using an automated object segmentation and clustering architecture to detect high-risk threat objects in the UK [6]. The study used dual-view single/dual-energy 2D X-ray imagery and a triplelayered processing scheme based on the atomic number of the contents of the luggage.…”

Towards automatic threat detection: A survey of advances of deep learning within X-ray security imaging

“…Instead of using shape information, some approaches utilises chemical (attenuation) proporties [28] and high atomic numbers [55]. Nearest Neighbour Distance Ratio [114] on SURF [100] features computed on regions disconnected with morphological operations achieves promising results (RMS error: 1.15 on 23 X-ray images).…”

A Rail Fault Diagnosis Method Based on Quartic C2 Hermite Improved Empirical Mode Decomposition Algorithm

“…However, the deep learning model has high computational complexity and limited recognition accuracy, which may lead to misjudgment. There are other nondestructive testing methods such as magnetic particle testing [5], ray detection [6], and ultrasonic testing [7]. Ultrasonic testing is widely used among them, as its accuracy is high and it is easily operated.…”