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. Hyperspect...

ver descrição completa

Detalhes bibliográficos
Autores: Yang, Sicheng, Cao, Yang, Li, Chuanjie, Castagnini, Juan Manuel, Barba, Francisco J., Shan, Changyao, Zhou, Jianjun
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/348502
Acesso em linha:http://hdl.handle.net/10261/348502
https://api.elsevier.com/content/abstract/scopus_id/85184815871
Access Level:acceso abierto
Palavra-chave:Grain drying
Hyperspectral imaging
Partial least squares model
Visualization
Descrição
Resumo: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.