Sensors 2013, 13(7), 8916-8927; doi:10.3390/s130708916
Article

Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis

1 College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China 2 Cyrus Tang Center for Sensor Materials and Applications, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China
* Authors to whom correspondence should be addressed.
Received: 21 May 2013; in revised form: 26 June 2013 / Accepted: 4 July 2013 / Published: 12 July 2013
(This article belongs to the Special Issue Spectral Imaging at the Microscale and Beyond)
PDF Full-text Download PDF Full-Text [530 KB, Updated Version, uploaded 15 July 2013 10:41 CEST]
The original version is still available [514 KB, uploaded 12 July 2013 09:52 CEST]
Abstract: A near-infrared (NIR) hyperspectral imaging system was developed in this study. NIR hyperspectral imaging combined with multivariate data analysis was applied to identify rice seed cultivars. Spectral data was exacted from hyperspectral images. Along with Partial Least Squares Discriminant Analysis (PLS-DA), Soft Independent Modeling of Class Analogy (SIMCA), K-Nearest Neighbor Algorithm (KNN) and Support Vector Machine (SVM), a novel machine learning algorithm called Random Forest (RF) was applied in this study. Spectra from 1,039 nm to 1,612 nm were used as full spectra to build classification models. PLS-DA and KNN models obtained over 80% classification accuracy, and SIMCA, SVM and RF models obtained 100% classification accuracy in both the calibration and prediction set. Twelve optimal wavelengths were selected by weighted regression coefficients of the PLS-DA model. Based on optimal wavelengths, PLS-DA, KNN, SVM and RF models were built. All optimal wavelengths-based models (except PLS-DA) produced classification rates over 80%. The performances of full spectra-based models were better than optimal wavelengths-based models. The overall results indicated that hyperspectral imaging could be used for rice seed cultivar identification, and RF is an effective classification technique.
Keywords: rice seed cultivar; hyperspectral imaging; random forest (RF); weighted regression coefficients (BW)

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Kong, W.; Zhang, C.; Liu, F.; Nie, P.; He, Y. Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis. Sensors 2013, 13, 8916-8927.

AMA Style

Kong W, Zhang C, Liu F, Nie P, He Y. Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis. Sensors. 2013; 13(7):8916-8927.

Chicago/Turabian Style

Kong, Wenwen; Zhang, Chu; Liu, Fei; Nie, Pengcheng; He, Yong. 2013. "Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis." Sensors 13, no. 7: 8916-8927.

Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert