Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis
This study proposes a recognition model for different drying methods of grain using hyperspectral imaging technology (HSI) and multivariate analysis. Fresh harvested grain samples were dried using three different methods: rotating ventilation drying, mechanical drying, and natural drying. Hyperspectral images of the samples were collected within the 388-1065 nm band range. The spectral features of the samples were extracted using principal component analysis (PCA), while the texture features were extracted using second-order probability statistical filtering. Partial least squares regression (PLSR) drying models with different characteristics were established. At the same time, a BPNN (Back-propagation neural network, BPNN) based on spectral texture fusion features was established to compare the recognition effects of different models. Texture analysis indicated that the mean-image had the clearest contour, and the texture characteristics of mechanical drying were smaller than those of rotating ventilation drying and natural drying. The BPNN model established using spectral-texture feature variables showed the best performance in distinguishing grain in different drying modes, with a prediction model obtained based on the correlation coefficients of special variables. The spectral and texture feature values were fused for pseudo-color visualization expression, and the three drying methods of grain showed different colors. This study provides a reference for non-destructive and rapid detection of grain with different drying methods.
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | artículo biblioteca |
Language: | English |
Published: |
Elsevier
2024-02-08
|
Subjects: | Grain drying, Hyperspectral imaging, Partial least squares model, Visualization, |
Online Access: | http://hdl.handle.net/10261/348502 https://api.elsevier.com/content/abstract/scopus_id/85184815871 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-iata-es-10261-348502 |
---|---|
record_format |
koha |
spelling |
dig-iata-es-10261-3485022024-05-19T20:37:07Z Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis Yang, Sicheng Cao, Yang Li, Chuanjie Castagnini, Juan Manuel Barba, Francisco Jose Shan, Changyao Zhou, Jianjun #NODATA# #NODATA# #NODATA# 0000-0002-3659-3640 0000-0002-5630-3989 #NODATA# 0000-0001-9122-2933 Grain drying Hyperspectral imaging Partial least squares model Visualization This study proposes a recognition model for different drying methods of grain using hyperspectral imaging technology (HSI) and multivariate analysis. Fresh harvested grain samples were dried using three different methods: rotating ventilation drying, mechanical drying, and natural drying. Hyperspectral images of the samples were collected within the 388-1065 nm band range. The spectral features of the samples were extracted using principal component analysis (PCA), while the texture features were extracted using second-order probability statistical filtering. Partial least squares regression (PLSR) drying models with different characteristics were established. At the same time, a BPNN (Back-propagation neural network, BPNN) based on spectral texture fusion features was established to compare the recognition effects of different models. Texture analysis indicated that the mean-image had the clearest contour, and the texture characteristics of mechanical drying were smaller than those of rotating ventilation drying and natural drying. The BPNN model established using spectral-texture feature variables showed the best performance in distinguishing grain in different drying modes, with a prediction model obtained based on the correlation coefficients of special variables. The spectral and texture feature values were fused for pseudo-color visualization expression, and the three drying methods of grain showed different colors. This study provides a reference for non-destructive and rapid detection of grain with different drying methods. We would like to thank the funding support and collaborative partner institutions of the ‘Key Technology Research and Equipment Development for Grain Collection, Storage, Quality Assurance and Reduction of Losses (2016YFD0401000)’, which have provided guarantee and support for our research work. Peer reviewed 2024-02-27T11:55:29Z 2024-02-27T11:55:29Z 2024-02-08 artículo http://purl.org/coar/resource_type/c_6501 http://hdl.handle.net/10261/348502 10.1016/j.crfs.2024.100695 2665-9271 38362161 2-s2.0-85184815871 https://api.elsevier.com/content/abstract/scopus_id/85184815871 en Current research in food science Publisher's version https://doi.org/10.1016/j.crfs.2024.100695 Sí open Elsevier |
institution |
IATA ES |
collection |
DSpace |
country |
España |
countrycode |
ES |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-iata-es |
tag |
biblioteca |
region |
Europa del Sur |
libraryname |
Biblioteca del IATA España |
language |
English |
topic |
Grain drying Hyperspectral imaging Partial least squares model Visualization Grain drying Hyperspectral imaging Partial least squares model Visualization |
spellingShingle |
Grain drying Hyperspectral imaging Partial least squares model Visualization Grain drying Hyperspectral imaging Partial least squares model Visualization Yang, Sicheng Cao, Yang Li, Chuanjie Castagnini, Juan Manuel Barba, Francisco Jose Shan, Changyao Zhou, Jianjun Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
description |
This study proposes a recognition model for different drying methods of grain using hyperspectral imaging technology (HSI) and multivariate analysis. Fresh harvested grain samples were dried using three different methods: rotating ventilation drying, mechanical drying, and natural drying. Hyperspectral images of the samples were collected within the 388-1065 nm band range. The spectral features of the samples were extracted using principal component analysis (PCA), while the texture features were extracted using second-order probability statistical filtering. Partial least squares regression (PLSR) drying models with different characteristics were established. At the same time, a BPNN (Back-propagation neural network, BPNN) based on spectral texture fusion features was established to compare the recognition effects of different models. Texture analysis indicated that the mean-image had the clearest contour, and the texture characteristics of mechanical drying were smaller than those of rotating ventilation drying and natural drying. The BPNN model established using spectral-texture feature variables showed the best performance in distinguishing grain in different drying modes, with a prediction model obtained based on the correlation coefficients of special variables. The spectral and texture feature values were fused for pseudo-color visualization expression, and the three drying methods of grain showed different colors. This study provides a reference for non-destructive and rapid detection of grain with different drying methods. |
author2 |
#NODATA# |
author_facet |
#NODATA# Yang, Sicheng Cao, Yang Li, Chuanjie Castagnini, Juan Manuel Barba, Francisco Jose Shan, Changyao Zhou, Jianjun |
format |
artículo |
topic_facet |
Grain drying Hyperspectral imaging Partial least squares model Visualization |
author |
Yang, Sicheng Cao, Yang Li, Chuanjie Castagnini, Juan Manuel Barba, Francisco Jose Shan, Changyao Zhou, Jianjun |
author_sort |
Yang, Sicheng |
title |
Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
title_short |
Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
title_full |
Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
title_fullStr |
Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
title_full_unstemmed |
Enhancing grain drying methods with hyperspectral imaging technology: A visual analysis |
title_sort |
enhancing grain drying methods with hyperspectral imaging technology: a visual analysis |
publisher |
Elsevier |
publishDate |
2024-02-08 |
url |
http://hdl.handle.net/10261/348502 https://api.elsevier.com/content/abstract/scopus_id/85184815871 |
work_keys_str_mv |
AT yangsicheng enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT caoyang enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT lichuanjie enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT castagninijuanmanuel enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT barbafranciscojose enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT shanchangyao enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis AT zhoujianjun enhancinggraindryingmethodswithhyperspectralimagingtechnologyavisualanalysis |
_version_ |
1802820555353620480 |