Identification of rapeseed varieties based on hyperspectral imagery

Identification of rapeseed varieties by using hyperspectral imaging technique combined with artificial neural network (ANN) was proposed. Hyperspectral images of several rapeseed varieties in range 400-1 000 nm were acquired, and then the principal component analysis (PCA) was performed to select th...

Full description

Saved in:
Bibliographic Details
Main Authors: ZOU Wei, FANG Hui, ZHOU Kang-yun, BAO Yi-dan, HE Yong, 何勇
Format: Article
Language:English
Published: Zhejiang University Press 2011-03-01
Series:浙江大学学报. 农业与生命科学版
Subjects:
Online Access:https://www.academax.com/doi/10.3785/j.issn.1008-9209.2011.02.009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706557658365952
author ZOU Wei
FANG Hui
ZHOU Kang-yun
BAO Yi-dan
HE Yong
何勇
author_facet ZOU Wei
FANG Hui
ZHOU Kang-yun
BAO Yi-dan
HE Yong
何勇
author_sort ZOU Wei
collection DOAJ
description Identification of rapeseed varieties by using hyperspectral imaging technique combined with artificial neural network (ANN) was proposed. Hyperspectral images of several rapeseed varieties in range 400-1 000 nm were acquired, and then the principal component analysis (PCA) was performed to select three optimal band images. The texture parameters were extracted from the optimal band images based on gray level histogram and gray level co-occurrence matrix (GLCM) statistical methods. The ANN model was used for the identification of rapeseed varieties. Detection results of ANN model showed that the discriminating rates of rapeseed varieties in the training and prediction sets were 93.75% and 91.67%, respectively. It is indicated that the hyperspectral imaging technology has a good classification and identification effects on rapeseed varieties.
format Article
id doaj-art-e9818bd7654c478988d4ecf53f4f471e
institution DOAJ
issn 1008-9209
2097-5155
language English
publishDate 2011-03-01
publisher Zhejiang University Press
record_format Article
series 浙江大学学报. 农业与生命科学版
spelling doaj-art-e9818bd7654c478988d4ecf53f4f471e2025-08-20T03:16:10ZengZhejiang University Press浙江大学学报. 农业与生命科学版1008-92092097-51552011-03-013717518010.3785/j.issn.1008-9209.2011.02.00910089209Identification of rapeseed varieties based on hyperspectral imageryZOU WeiFANG HuiZHOU Kang-yunBAO Yi-danHE Yong何勇Identification of rapeseed varieties by using hyperspectral imaging technique combined with artificial neural network (ANN) was proposed. Hyperspectral images of several rapeseed varieties in range 400-1 000 nm were acquired, and then the principal component analysis (PCA) was performed to select three optimal band images. The texture parameters were extracted from the optimal band images based on gray level histogram and gray level co-occurrence matrix (GLCM) statistical methods. The ANN model was used for the identification of rapeseed varieties. Detection results of ANN model showed that the discriminating rates of rapeseed varieties in the training and prediction sets were 93.75% and 91.67%, respectively. It is indicated that the hyperspectral imaging technology has a good classification and identification effects on rapeseed varieties.https://www.academax.com/doi/10.3785/j.issn.1008-9209.2011.02.009image processinghyperspectral imageryvariety identificationprincipal component analysisrapeseed
spellingShingle ZOU Wei
FANG Hui
ZHOU Kang-yun
BAO Yi-dan
HE Yong
何勇
Identification of rapeseed varieties based on hyperspectral imagery
浙江大学学报. 农业与生命科学版
image processing
hyperspectral imagery
variety identification
principal component analysis
rapeseed
title Identification of rapeseed varieties based on hyperspectral imagery
title_full Identification of rapeseed varieties based on hyperspectral imagery
title_fullStr Identification of rapeseed varieties based on hyperspectral imagery
title_full_unstemmed Identification of rapeseed varieties based on hyperspectral imagery
title_short Identification of rapeseed varieties based on hyperspectral imagery
title_sort identification of rapeseed varieties based on hyperspectral imagery
topic image processing
hyperspectral imagery
variety identification
principal component analysis
rapeseed
url https://www.academax.com/doi/10.3785/j.issn.1008-9209.2011.02.009
work_keys_str_mv AT zouwei identificationofrapeseedvarietiesbasedonhyperspectralimagery
AT fanghui identificationofrapeseedvarietiesbasedonhyperspectralimagery
AT zhoukangyun identificationofrapeseedvarietiesbasedonhyperspectralimagery
AT baoyidan identificationofrapeseedvarietiesbasedonhyperspectralimagery
AT heyong identificationofrapeseedvarietiesbasedonhyperspectralimagery
AT héyǒng identificationofrapeseedvarietiesbasedonhyperspectralimagery