基于贝叶斯决策理论的爆炸物识别方法

doi:-

东北大学学报:自然科学版 ›› 2013, Vol. 34 ›› Issue (1): 123-126.DOI: -

基于贝叶斯决策理论的爆炸物识别方法

孙丽娜，杨斌

(东北大学机械工程与自动化学院，辽宁沈阳110819)

收稿日期:2012-06-28 修回日期:2012-06-28 出版日期:2013-01-15 发布日期:2013-01-26
通讯作者: 孙丽娜
作者简介:孙丽娜(1977-)，女，辽宁沈阳人，东北大学讲师，博士.
基金资助:
中央高校基本科研业务费专项资金资助项目(N100303005)；沈阳市科技攻关项目(F11-174-9-00)；辽宁省科技攻关计划项目(2012216033).

An Explosives Identification Method Based on the Bayesian Decision Theory

SUN Li-na， YANG Bin

School of Mechanical Engineering ＆ Automation， Northeastern University， Shenyang 110819， China.

Received:2012-06-28 Revised:2012-06-28 Online:2013-01-15 Published:2013-01-26
Contact: SUN Li-na
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对安全检查领域爆炸物识别问题，以辐射数据的特征提取和识别为核心，将双能量X射线透射技术与低能前散射和背散射技术相结合，实验得到双能量透射、低能前散射及低能背散射图像灰度级并计算与物质有效原子序数相关的特征值R和与密度相关的特征值L，给出基于最小错误概率的贝叶斯决策理论的判别函数、决策面方程以及分类判别规则.实验验证贝叶斯决策理论的分类判别规则的识别正确率达到90%，将双能量X射线透射技术与低能散射技术相结合找到物质识别更有效的方法，进而全面提高X射线探测能力，这是对固体爆炸品识别的重要贡献.

关键词: 双能量透射, 低能散射, 爆炸物探测, 贝叶斯决策, 模式识别

Abstract: For explosives recognition problem in safety inspection field， dual-energy X-ray transmission technology， low-energy forward scattering and back scattering technology were combined to get the gray-levels of dual-energy transmission， low-energy forward scattering and back scattering images taking the feature extraction and recognition of the radiation data as the core. The eigenvalue R associated with effective atomic number and the eigenvalue L associated with density were obtained. Based on the least mistake probability， the eigenvalue R and L were synthesized to get the discriminate， decision-making plane and distinguish rule. The experiments validated that the correct rate of the discrimination rules by the Bayesian decision theory is up to 90%， and it is a more effective method for solid explosives identification that improves the detection capability of X-ray comprehensively. This may significantly contribute to recognition of solid explosives.

Key words: dual-energy transmission, low-energy scattering, explosives detection, Bayesian decision, pattern recognition

中图分类号:

O434.14

孙丽娜，杨斌. 基于贝叶斯决策理论的爆炸物识别方法[J]. 东北大学学报:自然科学版, 2013, 34(1): 123-126.

SUN Li-na， YANG Bin. An Explosives Identification Method Based on the Bayesian Decision Theory[J]. Journal of Northeastern University:Natural Science, 2013, 34(1): 123-126.

参考文献

[1]Shi X H.Improving object classification in X-ray luggage inspection［D］.Blacksburg:Virginia Polytechnic Institute and State University，2000.
[2]赵崑，李荐民.一种基于双能X射线与向前散射的爆炸物检测方法［J］.核技术，2004，27(10):783-786.(Zhao Kun，Li Jian-min.A new method of explosive detection based on dual-energy X-ray technology and forward-scattering［J］.Nuclear Techniques，2004，27(10):783-786.)
[3]杨斌.通用型安检设备物质重叠识别及R-L物质分类算法研究［D］.沈阳:东北大学，2008.(Yang Bin.Research on overlapped material recognition of universal security inspection equipment and R-L object classification［D］.Shenyang:Northeastern University，2008.)
[4]Macdonald D R.Design and implementation of a dual-energy X-ray imaging system for organic material detection in an airport security application［J］.Machine Vision Application in Industrial Inspection，2001，43(1):31-41.
[5]Panagiotis J A.Developing an automated explosives detection prototype based on the AS＆E 101ZZ system［D］.Blacksburg:Virginia Polytechnic Institute and State University，1997.
[6]Zou S.A sensor-fusion technique for explosive detection［D］.Blacksburg:Virginia Polytechnic Institute and State University，1998.
[7]Krug K D，Stein J A.Advanced dual energy X-ray for explosives detection［C］//Proceeding of the First International Symposium on Explosives Detection Technology.Atlantic City，1991:282-284.
[8]Xie W.Simulation of X-ray imaging systems for luggage inspection［D］.Blacksburg:Virginia Polytechnic Institute and State University，1995.
[9]Smith R C，Krall P R.Full volume dual-energy high speed computed tomography explosives detection system［C］//Proceeding of the Second Explosive Detection Symposium ＆ Aviation Security Conference.Atlantic City，1996:260-263.
[10]Liu W Y.Automatic detection of elongated objects in X-ray images of luggage［D］.Blacksburg:Virginia Polytechnic Institute and State University，1997.

[1]	印明昂，王钰烁，孙志礼，于云飞. 一种自适应步长的复合梯度加速优化算法[J]. 东北大学学报:自然科学版, 2020, 41(9): 1274-1279.
[2]	张尧;刘伟嵬;邢芝涛;颜云辉;. 采用多分类器集成方法的带钢表面缺陷图像识别[J]. 东北大学学报(自然科学版), 2012, 33(2): 267-270.
[3]	李景奎;张义民;. 正态分布连续体结构可靠性拓扑优化设计[J]. 东北大学学报(自然科学版), 2011, 32(9): 1304-1307.
[4]	姜慧研;景世磊;柴天佑;周晓杰;. 基于SVM和PSO的烧结工况预报方法[J]. 东北大学学报(自然科学版), 2010, 31(4): 494-497.
[5]	赵兴东;李元辉;刘建坡;田军;. 红透山矿深部开采岩爆潜在区微震活动性研究[J]. 东北大学学报(自然科学版), 2009, 30(9): 1330-1333.
[6]	孙红春;谢里阳;邢海涛;. 基于混合特征和支持向量机的抽油杆缺陷识别[J]. 东北大学学报(自然科学版), 2009, 30(2): 266-269.
[7]	姜慧研;周晓杰;柴天佑;. 基于多级SVM的回转窑烧结状态识别方法[J]. 东北大学学报(自然科学版), 2009, 30(1): 54-57.
[8]	姜慧研;赵越;杨新风;. 基于MRI的肝硬化程度的计算机辅助诊断[J]. 东北大学学报(自然科学版), 2007, 28(1): 31-34.
[9]	贾雪琴;王旭;李景宏;杨丹;. 基于小波变换和K-L展开的单通道表面肌电信号识别[J]. 东北大学学报(自然科学版), 2006, 27(8): 859-862.
[10]	曾鹏鑫;么健石;朱琳琳;徐心和;. 基于分形的人造目标与自然物体区别[J]. 东北大学学报(自然科学版), 2006, 27(3): 260-263.
[11]	刘建昌;王柱. 基于神经网络模式识别的板形模糊控制器[J]. 东北大学学报(自然科学版), 2005, 26(8): 718-721.
[12]	南存全;冯夏庭. 基于模式识别的煤与瓦斯突出区域预测[J]. 东北大学学报(自然科学版), 2004, 25(9): 903-906.
[13]	颜云辉;杨会林;王成明. 金属断口图像的非线性模式识别方法[J]. 东北大学学报(自然科学版), 2004, 25(9): 884-886.
[14]	范立南;徐心和. 基于不变矩特征和神经网络的图像模式模糊分类[J]. 东北大学学报(自然科学版), 2004, 25(8): 738-741.
[15]	张祥德;唐青松. 确定性退火技术及其在点匹配中的应用[J]. 东北大学学报(自然科学版), 2003, 24(11): 1119-1122.

基于贝叶斯决策理论的爆炸物识别方法

An Explosives Identification Method Based on the Bayesian Decision Theory

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价