Classification of X-Ray images of shipping containers

被引:13
作者
Abdolshah, Majid [1 ]
Teimouri, Mehdi [1 ]
Rahmani, Rohallah [1 ]
机构
[1] Univ Tehran, Fac New Sci & Technol, Tehran, Iran
关键词
Shipping containers; Tree augmented naive Bayes (TAN); Bag of visual words (BOVW); Scale Invariant Feature Transform (SIFT);
D O I
10.1016/j.eswa.2017.01.030
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Smuggling has long played an important role in the inefficiency of economies. To secure the borders against this illegal act, X-Ray Inspection Systems are often deployed at the borders and customs. In this paper, we present a new method for classification of shipping containers X-Ray images, produced in the inspection lines. The aim is to improve the matching accuracy of the presented manifest, which lists the claimed contents of the shipping containers, with the real contents of the container. The proposed method is based on utilizing Scale Invariant Feature Transforms (SIFT) feature vectors, Bag of visual words (BOVW) and tree augmented naive Bayes (TAN) approach for classifying containers X-Ray images. The prior research on classification of X-Ray images of shipping containers has focused mostly on working with greedy algorithms such as sliding windows for task of classification. More recent studies introduced filter banks and visual words for extraction of features. The proposed method for the first time considers the salient points and keypoints for the task of feature extraction. In addition, this paper presents a framework using the tree augmented naive Bayes based on the theory of learning Bayesian networks, which is proved to have a significant improvements upon the prior designed systems by considering the correlations among the extracted features. For experimental evaluations, our method is compared with two recently proposed methods on containers X-Ray images categorization. The results show that the proposed method is more accurate and time-efficient in categorization of X-Ray images. (C) 2017 Elsevier Ltd. All rights reserved.
引用
收藏
页码:57 / 65
页数:9
相关论文
共 22 条
[1]   GEOMETRIC TAMPERING ESTIMATION BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS [J].
Amerini, Irene ;
Ballan, Lamberto ;
Caldelli, Roberto ;
Del Bimbo, Alberto ;
Serra, Giuseppe .
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, :1702-1705
[2]  
[Anonymous], 2004, P 20 C UNC ART INT
[3]  
Basu G., 2014, WORLD CUSTOMS J, V8, P15
[4]   Image texture analysis: methods and comparisons [J].
Bharati, MH ;
Liu, JJ ;
MacGregor, JF .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2004, 72 (01) :57-71
[5]  
Dagher I., 2014, Intl. J. Signal Processing, V7, P225
[6]  
Dejian Meng, 2013, 2013 International Conference on Optoelectronics and Microelectronics (ICOM), P112, DOI 10.1109/ICoOM.2013.6626504
[7]   Visual detection of knives in security applications using Active Appearance Models [J].
Glowacz, Andrzej ;
Kmiec, Marcin ;
Dziech, Andrzej .
MULTIMEDIA TOOLS AND APPLICATIONS, 2015, 74 (12) :4253-4267
[8]  
Horster E., 2007, IEEE C COMP VIS PATT, P1
[9]  
Jaccard N, 2014, 2014 11TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), P387, DOI 10.1109/AVSS.2014.6918699
[10]  
Koller D, 2009, Probabilistic graphical models: principles and techniques