Pepper seed variety identification based on visible/near-infrared spectral technology

Cuiling Li; Xiu Wang; Zhijun Meng; Pengfei Fan; Jichen Cai

doi:10.1117/12.2247569

3 November 2016 Pepper seed variety identification based on visible/near-infrared spectral technology

Cuiling Li, Xiu Wang, Zhijun Meng, Pengfei Fan, Jichen Cai

Proceedings Volume 10030, Infrared, Millimeter-Wave, and Terahertz Technologies IV; 100302N (2016) https://doi.org/10.1117/12.2247569
Event: SPIE/COS Photonics Asia, 2016, Beijing, China

Abstract

Pepper is a kind of important fruit vegetable, with the expansion of pepper hybrid planting area, detection of pepper seed purity is especially important. This research used visible/near infrared (VIS/NIR) spectral technology to detect the variety of single pepper seed, and chose hybrid pepper seeds "Zhuo Jiao NO.3", "Zhuo Jiao NO.4" and "Zhuo Jiao NO.5" as research sample. VIS/NIR spectral data of 80 "Zhuo Jiao NO.3", 80 "Zhuo Jiao NO.4" and 80 "Zhuo Jiao NO.5” pepper seeds were collected, and the original spectral data was pretreated with standard normal variable (SNV) transform, first derivative (FD), and Savitzky-Golay (SG) convolution smoothing methods. Principal component analysis (PCA) method was adopted to reduce the dimension of the spectral data and extract principal components, according to the distribution of the first principal component (PC1) along with the second principal component(PC2) in the twodimensional plane, similarly, the distribution of PC1 coupled with the third principal component(PC3), and the distribution of PC2 combined with PC3, distribution areas of three varieties of pepper seeds were divided in each twodimensional plane, and the discriminant accuracy of PCA was tested through observing the distribution area of samples’ principal components in validation set. This study combined PCA and linear discriminant analysis (LDA) to identify single pepper seed varieties, results showed that with the FD preprocessing method, the discriminant accuracy of pepper seed varieties was 98% for validation set, it concludes that using VIS/NIR spectral technology is feasible for identification of single pepper seed varieties.

Citation Download Citation

Cuiling Li, Xiu Wang, Zhijun Meng, Pengfei Fan, and Jichen Cai "Pepper seed variety identification based on visible/near-infrared spectral technology", Proc. SPIE 10030, Infrared, Millimeter-Wave, and Terahertz Technologies IV, 100302N (3 November 2016); https://doi.org/10.1117/12.2247569

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available