可见-近红外高光谱图像技术快速鉴别激光打印墨粉

刘猛; 申思; 王楠

doi:10.3788/fgxb20173805.0662

您当前的位置：

首页 >

文章列表页 >

可见-近红外高光谱图像技术快速鉴别激光打印墨粉

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 可见-近红外高光谱图像技术快速鉴别激光打印墨粉
- Rapid Identification of Black Toner Variety by Visible and Near Infrared Hyperspectral Imaging Technology
- 发光学报 2017年38卷第5期页码：662-668
- 作者机构：
  
  1. 文件检验鉴定公安部重点实验室(中国刑警学院), 辽宁沈阳 100035
  2. 浙江警察学院刑事科学技术系, 浙江杭州 310053
  3. 司法部司法鉴定科学技术研究所上海,200063
- 作者简介：
  
  [ "刘猛(1988-),男,山东东平人,硕士,助教,2014年于中国公安大学获得硕士学位,主要从事物证鉴定方面的研究。E-mail:liumeng@zjjcxy.cn" ]
  [ "王楠(1988-),女,福建福州人,硕士,工程师,2013年于华东政法大学获得硕士学位,主要从事文件检验和痕迹检验方面的研究。E-mail:wangn@ssfjd.cn" ]
  [ "申思(1989-),女,河南开封人,硕士,助教,2011年于中国刑事警察学院获得硕士学位,主要从事文件检验鉴定方面的研究。E-mail:shengsi@zjjcxy.cn" ]
- 基金信息：
  
  文件检验鉴定公安部重点实验室（中国刑事警察学院）课题（2015KFKT09）;浙江警察学院校局合作项目（2016XJY014）资助
- DOI：10.3788/fgxb20173805.0662
  中图分类号： DF794.2;O433.4
- 纸质出版日期：2017-5-5，
  
  收稿日期：2016-11-9，
  
  修回日期：2016-12-15，
扫描看全文
刘猛, 申思, 王楠. 可见-近红外高光谱图像技术快速鉴别激光打印墨粉[J]. 发光学报, 2017,38(5): 662-668

LIU Meng, SHEN Si, WANG Nan. Rapid Identification of Black Toner Variety by Visible and Near Infrared Hyperspectral Imaging Technology[J]. Chinese Journal of Luminescence, 2017,38(5): 662-668
刘猛, 申思, 王楠. 可见-近红外高光谱图像技术快速鉴别激光打印墨粉[J]. 发光学报, 2017,38(5): 662-668 DOI： 10.3788/fgxb20173805.0662.

LIU Meng, SHEN Si, WANG Nan. Rapid Identification of Black Toner Variety by Visible and Near Infrared Hyperspectral Imaging Technology[J]. Chinese Journal of Luminescence, 2017,38(5): 662-668 DOI： 10.3788/fgxb20173805.0662.

摘要

为了使用快速、无损的方法区分激光打印文件使用的墨粉种类，利用高光谱成像技术结合化学计量法对6种激光打印墨粉的光谱数据进行建模和种类鉴别的研究。利用可见-近红外高光谱成像仪采集400~1 000 nm波段内的光谱数据，采用Savitzky Golay 平滑、标准化、多元散射校正和标准正态变量变换4种方法分别对光谱数据进行预处理，而后分别建立随机森林（RF）、K最近邻（KNN）、支持向量机（SVM）、偏最小二乘判别分析（PLS-DA）和簇类独立软模式（SIMCA）模型，进而实现激光打印墨粉的种类鉴别。利用准确率、拒识率和误识率3个指标作为模型评价标准。实验结果显示，SVM和PLS-DA模型的效果最佳，准确率为100%，拒识率和误识率为0。基于可见-近红外高光谱成像技术可以实现激光打印墨粉的快速种类鉴别。

Abstract

In order to develop rapid and non-destructive method for identification of laser printer toner

six kinds of black toner were identified rapidly by combining hyperspectral imaging technique and five kinds of statistical learning method. Method: a visible and near-infrared hyperspectral imaging system covering the spectral range of 400-1 000 nm was set up to capture hyperspectral images of toner samples. Savitzky Golay smooth

normalize

multiple scatter correction and standard normal varite were applied as preprocessing method. After that

five statistical learning methods

including Random Forest (RF)

K-nearest Neighbor (KNN)

Support Vector Machine (SVM)

Partial Least Square-discriminant analysis (PLS-DA) and Soft Independent Modeling of Class Analogy (SIMCA) were applied to establishment of discriminant models based on the full spectra. The properties of discriminant models were compared and valued by three parameters

precision

false reject rate (FRR) and false accept rate (FAR). Result: Among all discriminant models

the SVM and PLS-DA model show the best identification result

the precision is 100%

FRR and FAR are both 0. Conclusion: black toner could be identified by visible and near-infrared hyperspectral imaging technique combined with statistical learning method rapidly.

关键词

高光谱图像墨粉种类鉴别化学计量法支持向量机偏最小二乘判别分析

Keywords

hyperspectral imagingtoner identificationstatistical learning methodSVMPLS-DA

references

许可, 梁鲁宁, 连园园. 线聚焦显微激光拉曼光谱技术区分激光打印墨粉 [J]. 中国司法鉴定, 2011(2):27-30. XU K, LIANG L N, LIAN Y Y. Classification toners of laser printers with micro Raman spectroscopy [J]. Chin. J. Forensic Sci., 2011(2):27-30. (in Chinese)

张清华, 杨旭, 罗仪文, 等. 红外光谱结合化学计量学方法在激光打印原装黑色墨粉分析中的应用研究 [J]. 中国司法鉴定, 2014(5):28-33. ZHANG Q H, YANG X, LUO Y W, et al.. Analysis of original black toner of laser printers by infrared spectroscopy coupled with chemometrics [J]. Chin. J. Forensic Sci., 2014(5):28-33. (in Chinese)

罗仪文, 徐彻, 张清华, 等. LA-ICP-MS对激光打印原装黑色墨粉元素成分的分析 [J]. 中国司法鉴定, 2015(1):27-32. LUO Y W, XU C, ZHANG Q H, et al.. Discrimination of original black toner by laser ablation inductively coupled plasma mass spectrometry [J]. Chin. J. Forensic Sci., 2015(1):27-32. (in Chinese)

冯愈钦, 吴龙国, 何建国, 等. 基于高光谱成像技术的长枣不同保藏温度的可溶性固形物含量检测方法 [J]. 发光学报, 2016, 37(8):1014-1022. FENG Y Q, WU L G, HE J G, et al.. Detection method of soluble solid of jujube at different preservative temperature based on hyper-spectral imaging technology [J]. Chin. J. Lumin., 2016, 37(8):1014-1022. (in Chinese)

刘燕德, 邓清. 基于高光谱成像技术的脐橙叶片的叶绿素含量及其分布测量 [J]. 发光学报, 2015, 36(8):957-961. LIU Y D, DENG Q. Measurement of chlorophyll distribution in navel orange leaves based on hyper-spectral imaging technique [J]. Chin. J. Lumin., 2015, 36(8):957-961. (in Chinese)

吴龙国, 何建国, 刘贵珊, 等. 基于NIR高光谱成像技术的长枣虫眼无损检测 [J]. 发光学报, 2013, 34(11):1527-1532. WU L G, HE J G, LIU G S, et al.. Non-destructive detection of insect hole in jujube based on near-infrared hyperspectral imaging [J]. Chin. J. Lumin., 2013, 34(11):1527-1532. (in Chinese)

鲍一丹, 陈纳, 何勇, 等. 近红外高光谱成像技术快速鉴别国产咖啡豆品种 [J]. 光学精密工程, 2015, 23(2):349-355. BAO Y D, CHEN N, HE Y, et al.. Rapid identification of coffee bean variety by near infrared hyperspectral imaging technology [J]. Opt. Precision Eng., 2015, 23(2):349-355. (in Chinese)

BRAUNS E B, DYER R B. Fourier transform hyperspectral visible imaging and the nondestructive analysis of potentially fraudulent documents [J]. Appl. Spect., 2006, 60(8):833-840.

GL L, ORAVEC M, GEMEINER P, et al.. Principal component analysis for the forensic discrimination of black inkjet inks based on the Vis-NIR fibre optics reflection spectra [J]. Forensic Sci. Int., 2015, 257:285-292.

KHAN Z, SHAFAIT F, MIAN A. Automatic ink mismatch detection for forensic document analysis [J]. Pattern Recognit., 2015, 48(11):3615-3626.

EDELMAN G J, GASTON E, VAN LEEUWEN T G, et al.. Hyperspectral imaging for non-contact analysis of forensic traces [J]. Forensic Sci. Int., 2012, 223(1-3):28-39.

RINNAN , VAN DEN BERG F, ENGELSEN S B. Review of the most common pre-processing techniques for near-infrared spectra [J]. TrAC Trends Analyt. Chem., 2009, 28(10):1201-1222.

BREIMAN L. Random forests [J]. Mach. Learn., 2001, 45(1):5-32.

BREIMAN L, CUTLER A. Random forests [EB/OL]. (2004-06-06) [2016-04-15]. http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm.

LIAW A, WIENER M. Classification and regression by random forest [J]. R News, 2002, 2-3:18-22.

GUO G D, WANG H, BELL D, et al.. KNN Model-based Approach in Classification [M]. Berlin Heidelberg: Springer, 2003:986-996.

DEVOS O, RUCKEBUSCH C, DURAND A, et al.. Support vector machines (SVM) in near infrared (NIR) spectroscopy: focus on parameters optimization and model interpretation [J]. Chemom. Intell. Labor. Syst., 2009, 96(1):27-33.

BELOUSOV A I, VERZAKOV S A, VON FRESE S J. A flexible classification approach with optimal generalisation performance: support vector machines [J]. Chemom. Intell. Labor. Syst., 2002, 64(1):15-25.

SANTOS F, GUYOMARC'H P, BRUZEK J. Statistical sex determination from craniometrics: comparison of linear discriminant analysis, logistic regression, and support vector machines [J]. Forensic Sci. Int., 2014, 245:204.e1-e8.

BARKER M, RAYENS W. Partial least squares for discrimination [J]. J. Chemom., 2003, 17(3):166-173.

WOLD S. Pattern recognition by means of disjoint principal components models [J]. Pattern Recognit., 1976, 8(3):127-139.

MUEHLETHALER C, MASSONNET G, ESSEIVA P. Discrimination and classification of FTIR spectra of red, blue and green spray paints using a multivariate statistical approach [J]. Forensic Sci. Int., 2014, 244:170-178.

李航. 统计学习方法 [M]. 北京: 清华大学出版社, 2012:116. LI H. Statistical Learning Method [M]. Beijing: Tsinghua University Press, 2012:116. (in Chinese)

HSU C W, CHANG C C, LIN C J. A practical guide to support vector classification [EB/OL].(2016-05-19) [2016-06-26]. http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据