Classification accuracy improvement of laser-induced breakdown spectroscopy based on histogram of oriented gradients features of spectral images

Jiujiang Yan, Ping Yang, Zhongqi Hao, Ran Zhou, Xiangyou Li, Shisong Tang, Yun Tang, Xiaoyan Zeng, Yongfeng Lu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

To improve the classification accuracy of laser-induced breakdown spectroscopy (LIBS), image histogram of oriented gradients (HOG) features method (IHFM) for materials analysis was proposed in this work. 24 rice (Oryza sativa L.) samples were carried out to verify the proposed method. The results showed that the classification accuracy of rice samples by the full-spectra intensities method (FSIM) and IHFM were 60.25% and 81.00% respectively. The classification accuracy was obviously improved by 20.75%. Universality test results showed that this method also achieved good results in the plastics, steel, rock and minerals classification. This study provides an effective method to improve the classification performance of LIBS.

Original languageEnglish (US)
Pages (from-to)28996-29004
Number of pages9
JournalOptics Express
Volume26
Issue number22
DOIs
StatePublished - Oct 29 2018

Fingerprint

laser-induced breakdown spectroscopy
histograms
gradients
rice
plastics
minerals
steels
rocks

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Classification accuracy improvement of laser-induced breakdown spectroscopy based on histogram of oriented gradients features of spectral images. / Yan, Jiujiang; Yang, Ping; Hao, Zhongqi; Zhou, Ran; Li, Xiangyou; Tang, Shisong; Tang, Yun; Zeng, Xiaoyan; Lu, Yongfeng.

In: Optics Express, Vol. 26, No. 22, 29.10.2018, p. 28996-29004.

Research output: Contribution to journalArticle

Yan, Jiujiang ; Yang, Ping ; Hao, Zhongqi ; Zhou, Ran ; Li, Xiangyou ; Tang, Shisong ; Tang, Yun ; Zeng, Xiaoyan ; Lu, Yongfeng. / Classification accuracy improvement of laser-induced breakdown spectroscopy based on histogram of oriented gradients features of spectral images. In: Optics Express. 2018 ; Vol. 26, No. 22. pp. 28996-29004.
@article{29a169a5d55d46a48088ae9db352b232,
title = "Classification accuracy improvement of laser-induced breakdown spectroscopy based on histogram of oriented gradients features of spectral images",
abstract = "To improve the classification accuracy of laser-induced breakdown spectroscopy (LIBS), image histogram of oriented gradients (HOG) features method (IHFM) for materials analysis was proposed in this work. 24 rice (Oryza sativa L.) samples were carried out to verify the proposed method. The results showed that the classification accuracy of rice samples by the full-spectra intensities method (FSIM) and IHFM were 60.25{\%} and 81.00{\%} respectively. The classification accuracy was obviously improved by 20.75{\%}. Universality test results showed that this method also achieved good results in the plastics, steel, rock and minerals classification. This study provides an effective method to improve the classification performance of LIBS.",
author = "Jiujiang Yan and Ping Yang and Zhongqi Hao and Ran Zhou and Xiangyou Li and Shisong Tang and Yun Tang and Xiaoyan Zeng and Yongfeng Lu",
year = "2018",
month = "10",
day = "29",
doi = "10.1364/OE.26.028996",
language = "English (US)",
volume = "26",
pages = "28996--29004",
journal = "Optics Express",
issn = "1094-4087",
publisher = "The Optical Society",
number = "22",

}

TY - JOUR

T1 - Classification accuracy improvement of laser-induced breakdown spectroscopy based on histogram of oriented gradients features of spectral images

AU - Yan, Jiujiang

AU - Yang, Ping

AU - Hao, Zhongqi

AU - Zhou, Ran

AU - Li, Xiangyou

AU - Tang, Shisong

AU - Tang, Yun

AU - Zeng, Xiaoyan

AU - Lu, Yongfeng

PY - 2018/10/29

Y1 - 2018/10/29

N2 - To improve the classification accuracy of laser-induced breakdown spectroscopy (LIBS), image histogram of oriented gradients (HOG) features method (IHFM) for materials analysis was proposed in this work. 24 rice (Oryza sativa L.) samples were carried out to verify the proposed method. The results showed that the classification accuracy of rice samples by the full-spectra intensities method (FSIM) and IHFM were 60.25% and 81.00% respectively. The classification accuracy was obviously improved by 20.75%. Universality test results showed that this method also achieved good results in the plastics, steel, rock and minerals classification. This study provides an effective method to improve the classification performance of LIBS.

AB - To improve the classification accuracy of laser-induced breakdown spectroscopy (LIBS), image histogram of oriented gradients (HOG) features method (IHFM) for materials analysis was proposed in this work. 24 rice (Oryza sativa L.) samples were carried out to verify the proposed method. The results showed that the classification accuracy of rice samples by the full-spectra intensities method (FSIM) and IHFM were 60.25% and 81.00% respectively. The classification accuracy was obviously improved by 20.75%. Universality test results showed that this method also achieved good results in the plastics, steel, rock and minerals classification. This study provides an effective method to improve the classification performance of LIBS.

UR - http://www.scopus.com/inward/record.url?scp=85055775336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055775336&partnerID=8YFLogxK

U2 - 10.1364/OE.26.028996

DO - 10.1364/OE.26.028996

M3 - Article

C2 - 30470068

AN - SCOPUS:85055775336

VL - 26

SP - 28996

EP - 29004

JO - Optics Express

JF - Optics Express

SN - 1094-4087

IS - 22

ER -