A classifier based approach for the detection of potential threats in CT based Baggage Screening

  title={A classifier based approach for the detection of potential threats in CT based Baggage Screening},
  author={Najla Megherbi Bouallagu and Gregory T. Flitton and T. Breckon},
  journal={2010 IEEE International Conference on Image Processing},
Recent years have seen increased use of Computed Tomography (CT) based Unaccompanied Baggage and Package Screening (UBPS) systems for luggage examination to ensure air travel security. In this paper we present a research work on developing a system for automatic detection of potential threat items in cluttered 3D CT imagery originating from UBPS systems by combining 3D medical image segmentation techniques with 3D shape classification and retrieval methods. 

Figures, Tables, and Topics from this paper

A comparison of classification approaches for threat detection in CT based baggage screening
By combining 3D medical image segmentation techniques with 3D shape classification and retrieval methods, this work compares five varying final classification stage approaches and presents significant performance achievements in the automated detection of specified exemplar items. Expand
Investigating existing medical CT segmentation techniques within automated baggage and package inspection
3D Computed Tomography (CT) image segmentation is already well established tool in medical research and in routine daily clinical practice. However, such techniques have not been used in the contextExpand
A review of automated image understanding within 3D baggage computed tomography security screening.
The recent and most pertinent advancements are discussed and topics for future research within the challenging domain of automated image understanding for baggage security screening CT are identified. Expand
On artefact reduction, segmentation and classification of 3D computed tomography imagery in baggage security screening
The overall contribution of this work is a novel, fully-automated and efficient framework for the classification of objects in cluttered 3D baggage-CT imagery, extending the current state-of-the-art by improving classification performance in the presence of noise and artefacts; by automating the previously-manual isolation of objects and by decreasing processing times by several orders of magnitude. Expand
Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
This paper forms a more challenging multi-class 3D object detection problem within 3D CT imagery and proposes a viable solution (3D RetinaNet) to tackle this problem and investigates a variety of strategies including data augmentation and varying backbone networks. Expand
Materials-based 3D segmentation of unknown objects from dual-energy computed tomography imagery in baggage security screening
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. Expand
Radon transform based automatic metal artefacts generation for 3D threat image projection
Threat Image Projection (TIP) plays an important role in aviation security. In order to evaluate human security screeners in determining threats, TIP systems project images of realistic threat itemsExpand
3D object classification in baggage computed tomography imagery using randomised clustering forests
An improvement over the state-of-the-art both in terms of accuracy as well as processing time is demonstrated using a codebook constructed via randomised clustering forests, a dense feature sampling strategy and an SVM classifier. Expand
A machine learning color-based segmentation for object detection within dual X-ray baggage images
A comparative study of several ML algorithms with heuristics over a large data set of X-ray images is presented for the classification of organic and inorganic objects for a future dangerous object detection work. Expand
Object classification in 3D baggage security computed tomography imagery using visual codebooks
It is demonstrated that the underlying imaging modality and the irrelevance of illumination and scale invariance within the transmission imagery context considered here result in the favourable performance of simpler density histogram descriptors over 3D extensions of the well-established SIFT and RIFT feature descriptor approaches. Expand


Automatic image analysis process for the detection of concealed weapons
The goal of this research is to develop a process, using current imaging hardware and without human intervention, that provides an accurate and timely detection alert of a concealed weapon and itsExpand
CAXSS: an intelligent threat-detection system
Array Systems Computing Inc. (ASC) is developing a prototype Computer Assisted X-ray Screening System (CAXSS) which uses state-of-the-art image processing and computer vision technology to detectExpand
Survey of 3d image segmentation methods
This report reviews selected image binarization and segmentation methods that have been proposed and which are suitable for the processing of volume images. The focus is on thresholding, regionExpand
Intelligent Illicit Object Detection System for Enhanced Aviation Security
ABSTRACT Although aviation security is not a new phenomenon to the world, current threats are much more sophisticated such that it is extremely difficult to detect possible threats of terrorismExpand
Explosives detection systems (EDS) for aviation security
This paper discusses the application of computers for the analysis of data and images generated from security equipment and some of these technologies are reviewed. Expand
Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation
A theory of fuzzy objects forn-dimensional digital spaces based on a notion of fuzzy connectedness of image elements and algorithms for extracting a specified fuzzy object and for identifying all fuzzy objects present in the image data are presented. Expand
Content-Based 3-D Model Retrieval: A Survey
  • Yang Yubin, Lin Hui, Zhang Yao
  • Computer Science
  • IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)
  • 2007
The system framework and some key techniques of content-based 3D model retrieval are identified and explained, including canonical coordinate normalization and preprocessing, feature extraction, similarity match, query representation and user interface, and performance evaluation. Expand
Shape retrieval using 3D Zernike descriptors
Practical analysis of 3D Zernike invariants along with algorithms and computational details are provided along with a detailed discussion on influence of the algorithm parameters like the conversion into a volumetric function, number of utilized coefficients, etc. Expand
Content-Based 3D Model Retrieval: A Survey
The primary key techniques of content-based 3D model retrieval, including canonical coordinate normalization, geometrical shape feature extraction, appearance features extraction, similarity measurement, query specification, user interface, and index and retrieval mechanism, are analyzed and reviewed in detail. Expand
Three-dimensional shape searching : state-ofthe-art review and future trends
Three-dimensional shape searching is a problem of current interest in several different fields. Most techniques have been developed for a particular domain and reduce a shape into a simpler shapeExpand