Recognition of Fingernail Region Based on Filter－Spectral Feature Extraction

GU Kun-shan; WANG Ji-fen; ZENG Xiao-hu

doi:10.19969/j.fxcsxb.21072903

您当前的位置：

首页 >

文章列表页 >

Recognition of Fingernail Region Based on Filter－Spectral Feature Extraction

Scientific Paper | 更新时间：2022-06-22

- Recognition of Fingernail Region Based on Filter－Spectral Feature Extraction
- Journal of Instrumental Analysis Vol. 41, Issue 5, Pages: 746-753(2022)
- 作者机构：
  
  1.中国人民公安大学侦查学院，北京 100038
  2.酒泉卫星发射中心，甘肃酒泉 735000
- 作者简介：
- 基金信息：
- DOI：10.19969/j.fxcsxb.21072903
  CLC：
扫描看全文
古锟山,王继芬,曾啸虎.基于滤波器－光谱数据降维的指甲地区识别[J].分析测试学报,2022,41(05):746-753.

GU Kun-shan,WANG Ji-fen,ZENG Xiao-hu.Recognition of Fingernail Region Based on Filter－Spectral Feature Extraction[J].Journal of Instrumental Analysis,2022,41(05):746-753.
古锟山,王继芬,曾啸虎.基于滤波器－光谱数据降维的指甲地区识别[J].分析测试学报,2022,41(05):746-753. DOI： 10.19969/j.fxcsxb.21072903.

GU Kun-shan,WANG Ji-fen,ZENG Xiao-hu.Recognition of Fingernail Region Based on Filter－Spectral Feature Extraction[J].Journal of Instrumental Analysis,2022,41(05):746-753. DOI： 10.19969/j.fxcsxb.21072903.

摘要

该文从实际案件中收集了5个地区共计204份指甲样本，运用希尔伯特变换滤波器对原始谱图进行降噪处理，然后采用主成分分析进行数据降维，借助朴素贝叶斯、随机森林以及偏最小二乘判别分析模型开展指甲地区的识别工作，并根据模型的识别率和相关指标筛选出最佳预处理方法和最优识别模型。结果表明，经预处理后的原始谱图识别率得到显著提升，希尔伯特变换滤波器结合主成分分析是最佳预处理方法，随机森林模型的稳定性和识别率均高于朴素贝叶斯和偏最小二乘判别分析模型，对最佳预处理方法的训练集识别率为94.88%，测试集识别率为93.47%。该方法能有效降低谱图的噪声，减少数据的冗余，提高模型的识别效果，为法庭科学中指甲地区的快速鉴定提供了参考。

Abstract

Fingernail is one of the common biological evidences on the scene of the case．The rapid inspection of fingernails found in the scene could provide direction and clues for case investigation．Meanwhile，application of machine learning for quick and nondestructive detection of the testing material is an important branch of court science．Filter could effectively remove the noise and background interference of the spectra．The dimension reduction of the spectral data could effectively reduce the dimension of the data，and improve the recognition effect of the model．In this paper，a total of 204 nail samples from the actual cases of five regions were collected．The original spectra were denoised by Hilbert transform filter（HTF），and then the principal component analysis（PCA）was used to reduce the dimension of the original data and the denoised data．Naive Bayes（NB），random forest（RF） and partial least squares discriminant analysis（PLS－DA） model were used to carry out the identification of nail area．According to the recognition rate and related indicators of the model，the optimal preprocessing method and optimal recognition model for nail area identification were selected．The results demonstrated that the recognition rate of the original spectra is significantly improved after preprocessing．HTF combined with PCA is the best preprocessing method．The recognition rate of RF for the training set of the best pretreatment method is 94.88%，while that for the test set is 93.47%．This method could effectively reduce the noise of spectra，reduce the redundancy of data，improve the recognition effect of the model，and provide some reference for the rapid identification of nail areas in forensic science．

关键词

光谱学指甲希尔伯特变换滤波器主成分分析机器学习

Keywords

spectroscopyfingernailHilbert transform filterprincipal component analysis（PCA）machine learning

references

Katarzyna A M．Trends Anal. Chem.，2010，29（3）：246－259.

Medana C，Santoro V，Bello F D，Sala C，Pazzi M，Sarro M，Calza P．Rapid Commun. Mass Sp.，2016，30（24）：2617－2627.

Franziska K，Martin H，Lena W，André N，Maximilian M，Maria K P，Michael T．Forensic Sci. Med. Pathol.，2016，12（4）：416－434.

Delphine C，Michel Y，Hugo N，Alexander L N N，Mireille D，Kristof M，Adrian C，Cleo L．Forensic Toxicol.，2015，33（1）：12－36.

Inkret J，Podovšovnik E，Zupanc T，Pajnič I Z．Int. J. Legal Med.，2020，134（5）：1629－1638.

Kintz P，Gheddar L，Ameline A，Raul J S．Drug Test. Anal.，2020，12（10）：1508－1513.

Rosalie S，Anne S H，Laurence S，Marie E，Rajae D，Caroline A，Marjorie S，Ludwig M，Cécile M，Jorge A，Marie P H．Mycoses，2020，63（10）：1115－1127.

Meier A W，Fraser I．Sci. Justice：J. Forensic Sci. Soc.，2008，48（3）：153－159.

Christy J M，James R E．J. Forensic Sci.，2019，64（1）：69－76.

Fraser I，Meier A W，Kalin R M．J. Forensic Sci.，2008，53（1）：95－99.

Farmer N L，Meier－Augenstein W，Kalin R M．Rapid Commun. Mass Spectrom.，2005，19（22）：3182－3186.

He X L，Mei H C，Wang J F，Zhu J，Guo P R，Hu C，He Y，Dou X X，Hu Z L．Acta Anthropologica Sin. 何欣龙，梅宏成，王继芬，朱军，郭鹏然，胡灿，何亚，龚晓晓，胡展纶．人类学学报），2021，40（5）：888－894.

Hou W，Wang J F，He X L．Laser Optoelectron. Prog. （侯伟，王继芬，何欣龙．激光与光电子学进展），2021，58（3）：333－340.

Dittmar M，Dindorf W，Banerjee A．Gerontology，2008，54（2）：100－105.

Brzózka P，Kolodziejski W．RSC Adv.，2017，7（45）：28213－28223.

Sharma A，Verma R，Kumar R，Chauhana R，Sharma V．Microchem. J.，2020，159（1）：105504.

Zhang R Q，Du Y P．J. Instrum. Anal. （张若秋，杜一平．分析测试学报），2020，39（10）：1282－1287.

Rong S H， Zhou H X，Zhao D，Cheng K H，Qian K，Qin H L．Infrared Phys. Technol.，2018，9（1）：243－249.

Ju W，Lu C H，Zhang Y J．Spectrosc. Spectral Anal. （鞠薇，鲁昌华，张玉钧．光谱学与光谱分析），2018，38（6）：1684－1690.

Li D，Kong F Q，Zhu D Y．Acta Opt. Sin. （李丹，孔繁锵，朱德燕．光学学报），2021，41（6）：78－89.

Vaishali A，Ramakrishnan R，Subasini A．Procedia Comput. Sci.，2019，16（5）：449－455.

He X L，Wang J F．Anal. Lett.，2020，53（5）：714－734.

He X L，Wang J F，Zhao B，Mu Y L，Liu Y M，Hou W，Ma T．Anal. Lett.，2020，53（17）：2761－2774.

Botin D，Carrique F，Ruiz R E，Palberg T．J. Chem. Phys.，2020，152（24）：244902.

Dankan G V，Naveena P G，Sridhara S B，Shashidhara K S，Gangadhara P A．J. Phys.，2020，1706（1）：65－77.

Ronei M M，Jodavid A F，Liliane S M．Int. J. Fuzzy Syst.，2020，42（12）：1－13.

Wang F，Zhang C H，Zhao J F，Sibateer H，Zhang Y．Laser Optoelectron. Prog. （王芳，张春红，赵景峰，哈斯巴特尔，张玉．激光与光电子学进展），2021，58（3）：318－324.

Li Y Q，Hong S J，Huang W，Zhang L G，Ge J，Luan S R，Ni L J．J. Instrum Anal. 李永琪，洪士军，黄雯，张立国，葛炯，栾绍嵘，倪力军．分析测试学报），2020，39（10）：1231-1238.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Screening Methods of Pesticides and Their Transformation Products Based on Omics，Machine Learning and Biotransformation Technology

Research on Identification Model for Car Paint Material Evidence Based on Hyperspectral Technology

Rapid Detection and Traceability of Counterfeit Banknote Paper Based on Ion Mobility Spectrometry

Detection of Explosives by Direct Ionization Mass Spectrometry Based on Machine Learning Algorithm

Related Author

No data

Related Institution

Shanghai Municipal Center for Disease Control and Prevention，State Key Laboratory of Environmental Health Impact Assessment of Emerging Pollutants for Environmental Protection

Institute of Forensic Science，Ministry of Public Security

College of Chemistry，Beijing University of Chemical Technology

Suzhou Weimu Intelligent System Co.Ltd

College of Pharmacy， Xinxiang Medical University

Address：100 Xianlie Middle Road, Guangzhou Postal code：510070
Tel：020-87684776,37656606 Fax：020-87684776 Email：fxcsxb@china.com
Technical support is provided by Beijing Founder electronics co., LTD 粤ICP备12017312号-3 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰