Share Email Print

Proceedings Paper

Classification of tea based on terahertz time domain spectroscopy
Author(s): Binghua Cao; Guangxin Zhang; Zekui Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Terahertz time-domain spectroscopy (THz-TDS) is a newly developed technique in the last decade. A new method to classify tea is proposed based on THz-TDS and pattern recognition method. Four kinds of tea are investigated to study its feasibility. Their absorption spectra are measured using the THz-TDS system. Then a pattern recognition method, support vector machine (SVM), is employed to differentiate the investigated tea based on their terahertz data. The absorption spectra between 0.2 and 2.0 THz of the investigated tea samples are selected as the feature to classify them. The correct rate of recognition for the SVM classifier is 96.88%. The results give evidence that different tea varieties can be distinguished based on their terahertz spectra. In this respect, the spectral method provides enough information to differentiate different kinds of tea.

Paper Details

Date Published: 16 February 2009
PDF: 7 pages
Proc. SPIE 7277, Photonics and Optoelectronics Meetings (POEM) 2008: Terahertz Science and Technology, 727701 (16 February 2009); doi: 10.1117/12.817704
Show Author Affiliations
Binghua Cao, Zhejiang Univ. (China)
Guangxin Zhang, Zhejiang Univ. (China)
Zekui Zhou, Zhejiang Univ. (China)

Published in SPIE Proceedings Vol. 7277:
Photonics and Optoelectronics Meetings (POEM) 2008: Terahertz Science and Technology
Jianquan Yao; Shenggang Liu; Xi-Cheng Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top