Graph clustering and variational image segmentation for automated firearm detection in X‐ray images. Issue 7 (29th April 2019)

• Record Type: Journal Article
• Authors: Mallia‐Parfitt, Noeleene; Giasemidis, Georgios
• Is Part Of: IET image processing. Volume 13:Issue 7(2019)
• Page Start: 1105
• Page End: 1114
• Publication Date: 2019-04-29
• Subjects: image classification -- graph theory -- image segmentation -- pattern clustering -- X‐ray imaging; graph clustering -- variational image segmentation -- automated firearm detection -- X‐ray images -- parcels -- border control -- high‐security buildings -- security agents -- time‐consuming -- automation -- automatic threat detection -- particular firearms -- X‐rays -- hybrid algorithm -- well‐established image segmentation algorithms -- two‐step clustering method -- semisupervised spectral clustering algorithm -- image level -- handful images -- different algorithms -- individual algorithms; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5198
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Millions of parcels and pieces of luggage are scanned daily for threat detection at border control or high‐security buildings. Currently, the process is manually operated by security agents and it is slow and time‐consuming. The automation of this process will lift the burden from the security agents and will allow larger volumes of items to be scanned. The authors consider the problem of automatic threat detection, in particular firearms, in X‐rays. To achieve this goal, they propose a hybrid algorithm that combines two well‐established image segmentation algorithms into a two‐step clustering method. The first step is a semi‐supervised spectral clustering algorithm at the image level, which classifies whole images into benign or containing a threat. The images classified as threatening from the first step proceed to the second stage, where a variational image segmentation algorithm performs clustering at the pixel level to locate the threat if it exists. The hybrid algorithm is designed to scale‐up the processing of hundreds of images, in comparison to the academic literature where only a handful images are used for demonstration. Numerical experiments establish that the combination of two different algorithms produces better results than using individual algorithms.