Materials-based 3D segmentation of unknown objects from dual-energy computed tomography imagery in baggage security screening

Abstract

(2015) 'Materials-based 3D segmentation of unknown ob jects from dual-energy computed tomography imagery in baggage security screening.', Pattern recognition., 48 (6). pp. 1961-1978. Further information on publisher's website: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. AbstractWe present a novel technique for the 3D segmentation of unknown objects from cluttered dual-energy Computed Tomography (CT) data obtained in the baggage security-screening domain. Initial materials-based coarse segmentations, generated using the Dual-Energy Index (DEI), are refined by partitioning at automatically-detected regions. Partitioning is guided by a novel random forest based quality metric, trained to recognise high-quality, single-object segments. A second novel segmentation quality measure is presented for quantifying the quality of full segmentations based on the random forest metric of the constituent parts and the error in the number of objects segmented. In a comparative evaluation between the proposed approach and three state-of-the-art volumetric segmentation techniques designed for single-energy CT data (two region-growing [1, 2] and one graph-based [3]) our method is shown to outperform both region-growing methods in terms of segmentation quality and speed.Although the graph-based approach generates more accurate partitions, it is characterised by high processing times and is significantly outperformed by the proposed method in this regard.The observations made in this study indicate that the proposed segmentation technique is well-suited to the baggage security-screening domain, where the demand for computational efficiency is paramount to maximise throughput.

A review of automated image understanding within 3D baggage computed tomography security screening

“…The computational complexity of sieves is approximately N log p, where p is image dependent and is proportional to the number of flat-zones (the largest connected components where the signal is constant) in the image. Mouton and Breckon [72] have recently presented a materials-based technique for the segmentation of unknown 3D objects from low-resolution, cluttered baggage-CT imagery.…”

“…Mouton [71] addresses these limitations by combining various methodologies for noise and artefact reduction, unsupervised segmentation and classification. More particularly, noise and metal streaking artefacts are reduced by NLM filtering and distance-driven MAR [17,74]; 3D segmentation of the data is performed via materials-based dual-energy techniques [72] and the segmented data is classified using ERC-forest codebooks [73]. Correct classification rates in excess of 97% with false-positive rates of less than 2% are obtained at low computational costs for the classification of two object classes (handguns and bottles) in realistic baggage-CT imagery (Section 2).…”

“…Based on the suboptimal performance of early works in the presence of artefacts and noise [34,67], image denoising and artefact removal have conventionally been considered mandatory precursors to automated image understanding tasks within baggage-CT screening and have demonstrated quantitative improvements in tasks such as 3D object segmentation [42,72] and classification [71].…”

An approach for adaptive automatic threat recognition within 3D computed tomography images for baggage security screening

“…Mouton et al [26] proposed a novel technique for the 3D segmentation of unknown objects in the baggage CT images. The proposed algorithm takes advantage of the appearance information of objects to be segmented (e.g., handguns and bottles) which, however, is not applicable to our problem since the concerned threat materials could appear in very different forms.…”

“…Automatic threat recognition (ATR) intends to enable baggage screening more efficient and effective with only limited human intervention. Attempts have been made in recent works to address the ATR problem in 2D X-ray images [3,1,23,6,2] and 3D CT images [11,40,9,22,28,27,26,7,20]. Most existing works, however, focus on the recognition of threat objects having specific shape-based appearances (e.g., firearms, bottles, knives, etc.…”