首页 > 论文 > 太赫兹科学与电子信息学报 > 17卷 > 3期(pp:489-494)

高光谱技术在血迹分类识别中的应用

Application of hyperspectral technology in classification and recognition of bloodstains

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

利用高光谱技术对血迹种类进行无损识别研究。采用小波变换技术对 400~950 nm之间的原始光谱进行去噪处理,并对处理后的光谱进行特征波段选择,建立全波段和特征波长下的血迹种类识别模型。结果表明,利用特征波长与支持向量机 (SVM)结合建立的血迹种类识别模型的识别准确率及识别时间分别为 98%和 0.2 s,优于全波段建立的模型。研究表明,采用高光谱技术对血迹种类识别是可行的。

Abstract

Nondestructive identification of blood type is studied by hyperspectral technology in this paper. The original spectrum between 400-950 nm is denoised by wavelet transform, and then the characteristic spectrum of the processed spectrum is selected, finally the bloodstain type recognition models in the whole band and characteristic wavelengths are established. The results show that the model established in the characteristic wavelength combined with Support Vector Machine(SVM) can realize recognition accuracy of 98% and recognition time of 0.2 s, which is better than that of the model in full band. Research indicates that the hyperspectral technology is feasible for identifying the bloodstain types.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TN911.74

DOI:10.11805/tkyda201903.0489

所属栏目:信号与信息处理、计算机与控制

基金项目:国家自然科学基金资助项目 (51276209);重庆市科委基础与前沿研究资助项目 (cstc2014jcyjA0081)

收稿日期:2017-11-21

修改稿日期:2018-01-31

网络出版日期:--

作者单位    点击查看

李成成:重庆理工大学电气与电子工程学院,重庆 400054光纤传感与光电检测重庆市重点实验室,重庆 400054重庆市现代光电检测技术与仪器重点实验室,重庆 400054中国电子科技集团公司第八研究所,安徽合肥 230000
赵明富:重庆理工大学电气与电子工程学院,重庆 400054光纤传感与光电检测重庆市重点实验室,重庆 400054重庆市现代光电检测技术与仪器重点实验室,重庆 400054
汤斌:重庆理工大学电气与电子工程学院,重庆 400054光纤传感与光电检测重庆市重点实验室,重庆 400054重庆市现代光电检测技术与仪器重点实验室,重庆 400054
罗彬彬:重庆理工大学电气与电子工程学院,重庆 400054光纤传感与光电检测重庆市重点实验室,重庆 400054重庆市现代光电检测技术与仪器重点实验室,重庆 400054
邹雪:重庆理工大学电气与电子工程学院,重庆 400054光纤传感与光电检测重庆市重点实验室,重庆 400054重庆市现代光电检测技术与仪器重点实验室,重庆 400054王博思招商局重庆交通科研设计院有限公司,重庆 400067

联系人作者:赵明富(zmf@cqut.edu.cn)

备注:李成成(1992-),男,安徽省阜阳市人,硕士,工程师,主要研究方向为信息获取技术与处理.email:932015647@qq.com.

【1】樊学勇,杨涛.刑事诉讼视野下的法医物证应用研究[J].证据科学, 2012,20(1):60-67. (FAN Xueyong,YANG Tao. Research of forensic application from criminal procedure perspective[J]. Journal of Law & Medicine, 2012,20(1):60-67.) DOI:10.3969/j.issn.1674-1226.2012.01.007.

【2】ZHANG X,LIU F,HE Y,et al. Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging[J]. Biosystems Engineering, 2013,115(1):56-65. DOI:10.1016/j.biosystemseng.2013.02.007.

【3】李岚涛,汪善勤,任涛,等.基于高光谱的冬油菜叶片磷含量诊断模型[J].农业工程学报, 2016,32(14):209-218. (LI Lantao,WANG Shanqin,REN Tao,et al. Evaluating models of leaf phosphorus content of winter oilseed rape based on hyperspectral data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016,32(14):209-218.) DOI:10.11975/ j.issn.1002-6819.2016.14.028.

【4】赵明富,刘自迪,邹雪,等.基于高光谱成像技术对马铃薯外部缺陷的识别[J].激光杂志, 2016(3):20-24. (ZHAO Mingfu, LIU Zidi,ZOU Xue,et al. Detection of defects on potatoes by hyperspectral imaging technology[J]. Laser Journal, 2016(3): 20-24.) DOI:10.14016/j.cnki.jgzz.2016.03.020.

【5】余伟,彭宽宽,陈伟,等.基于高光谱技术的培养基上细菌菌落分类方法研究[J].分析化学, 2016(8):1221-1226. (YU Wei,PENG Kuankuan,CHEN Wei,et al. Classification of bacterial colonies on agar plates using hyperspectral imaging technology[J]. Chinese Journal of Analytical Chemistry, 2016(8):1221-1226.) DOI:10.11895/j.issn.0253-3820.160053.

【6】赵明富,冯小平,张政委,等.基于光谱分析技术的不同介质血迹陈旧度研究[J].压电与声光, 2013,35(6):806-809. (ZHAO Mingfu,FENG Xiaoping,ZHANG Zhengwei,et al. Study on detection of bloodstain age in different objects based on spectroscopy technology[J]. Piezoelectrics & Acoustooptics, 2013,35(6):806-809.) DOI:10.3969/j.issn.1004-2474. 2013. 06.010.

【7】董永芳,孟耀勇,张平丽,等.基于可见反射光谱和遗传区间偏昀小二乘法的血迹年龄预测研究[J].光学学报, 2015, 35(8):369-374. (DONG Yongfang,MENG Yaoyong,ZHANG Pingli,et al. Accurate age estimation of bloodstains based on visible reflectance and genetic algorithm interval partial Least Squares[J]. Acta Optica Sinica, 2015,35(8):369-374.) DOI:10.3788/aos201535.0830001.

【8】万雄,王建,刘鹏希,等.近红外透射光谱的动物全血鉴别[J].光谱学与光谱分析, 2016,36(1):80-83. (WAN Xiong,WANG Jian,LIU Pengxi,et al. Identification of animal whole blood based on near infrared transmission spectroscopy[J]. Spectroscopy and Spectral Analysis, 2016,36(1):80-83.) DOI:10.3964/j.issn.1000-0593(2016)01-0080-04.

【9】赵明富,夏曦,张政委,等. 基于高光谱图像技术的指纹识别研究[J]. 激光杂志, 2013,34(1):45-47. (ZHAO Mingfu,XIA Xi,ZHANG Zhengwei,et al. Study on detection of fingerprint recognition based on hyperspectral imaging technology[J]. Laser Journal, 2013,34(1):45-47.) DOI:10.3969/j.issn.0253-2743.2013.01.022.

【10】张胤鸣.基于 FTIR光谱技术鉴别血痕种属及形成时间的实验研究[D].西安:西安交通大学, 2017. (ZHANG Yinming. The estimation of time since deposition and species of bloodstains based on FTIR spectroscopy[D]. Xi’an,China:Xi’an Jiaotong University, 2017.)

【11】毛国庆,滕奇志,吴拥,等.基于 BP神经网络的剩余油形态识别[J].太赫兹科学与电子信息学报, 2014,12(6):858-864. (MAO Guoqing,TENG Qizhi,WU Yong,et al. Shape recognition of remained oil based on BP neural network[J]. Journal of Terahertz Science and Electronic Information Technology, 2014,12(6):858-864.) DOI:10.11805/TKYDA201406.0858.

【12】LIU Yufei,PI Dechang,CHENG Qiyou,et al. Ensemble kernel method:SVM classification based on game theory[J]. Journal of Systems Engineering and Electronics, 2016,27(1):251-259. DOI:10.1109/JSEE.2016.00025.

引用该论文

LI Chengcheng,ZHAO Mingfu,TANG Bin,LUO Binbin,ZOU Xue,WANG Bosi. Application of hyperspectral technology in classification and recognition of bloodstains[J]. Thz, 2019, 17(3): 489-494

李成成,赵明富,汤斌,罗彬彬,邹雪. 高光谱技术在血迹分类识别中的应用[J]. 太赫兹科学与电子信息学报, 2019, 17(3): 489-494

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF