A comparison of 3D interest point descriptors with application to airport baggage object detection in complex CT imagery

Flitton, G.; Breckon, T.P.; Megherbi, N.

Abstract

We present an experimental comparison of 3D feature descriptors with application to threat detection in Computed Tomography (CT) airport baggage imagery. The detectors range in complexity from a basic local density descriptor, through local region histograms and three-dimensional (3D) extensions to both to the RIFT descriptor and the seminal SIFT feature descriptor. We show that, in the complex CT imagery domain containing a high degree of noise and imaging artefacts, a specific instance object recognition system using simpler descriptors appears to outperform a more complex RIFT/SIFT solution. Recognition rates in excess of 95% are demonstrated with minimal false-positive rates for a set of exemplar 3D objects.

Citation

Flitton, G., Breckon, T., & Megherbi, N. (2013). A comparison of 3D interest point descriptors with application to airport baggage object detection in complex CT imagery. Pattern Recognition, 46(9), 2420-2436. https://doi.org/10.1016/j.patcog.2013.02.008

• Journal Article Type: Article
• Acceptance Date: Feb 7, 2013
• Online Publication Date: Feb 16, 2013
• Publication Date: 2013-09
• Deposit Date: Oct 1, 2013
• Journal: Pattern Recognition
• Print ISSN: 0031-3203
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 46
• Issue: 9
• Pages: 2420-2436
• DOI: https://doi.org/10.1016/j.patcog.2013.02.008
• Public URL: https://durham-repository.worktribe.com/output/1446253