Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer
Turtle shell (<i>Chinemys reecesii</i>) is a prized traditional Chinese dietary therapy, and the growth year of turtle shell has a significant impact on its quality attributes. In this study, a hyperspectral imaging (HSI) technique combined with a proposed deep learning (DL) network algo...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Molecules |
Subjects: | |
Online Access: | https://www.mdpi.com/1420-3049/28/17/6427 |
_version_ | 1797582104035328000 |
---|---|
author | Tingting Wang Zhenyu Xu Huiqiang Hu Huaxing Xu Yuping Zhao Xiaobo Mao |
author_facet | Tingting Wang Zhenyu Xu Huiqiang Hu Huaxing Xu Yuping Zhao Xiaobo Mao |
author_sort | Tingting Wang |
collection | DOAJ |
description | Turtle shell (<i>Chinemys reecesii</i>) is a prized traditional Chinese dietary therapy, and the growth year of turtle shell has a significant impact on its quality attributes. In this study, a hyperspectral imaging (HSI) technique combined with a proposed deep learning (DL) network algorithm was investigated for the objective determination of the growth year of turtle shells. The acquisition of hyperspectral images was carried out in the near-infrared range (948.72–2512.97 nm) from samples spanning five different growth years. To fully exploit the spatial and spectral information while reducing redundancy in hyperspectral data simultaneously, three modules were developed. First, the spectral–spatial attention (SSA) module was developed to better protect the spectral correlation among spectral bands and capture fine-grained spatial information of hyperspectral images. Second, the 3D convolutional neural network (CNN), more suitable for the extracted 3D feature map, was employed to facilitate the joint spatial–spectral feature representation. Thirdly, to overcome the constraints of convolution kernels as well as better capture long-range correlation between spectral bands, the transformer encoder (TE) module was further designed. These modules were harmoniously orchestrated, driven by the need to effectively leverage both spatial and spectral information within hyperspectral data. They collectively enhance the model’s capacity to extract joint spatial and spectral features to discern growth years accurately. Experimental studies demonstrated that the proposed model (named SSA–3DTE) achieved superior classification accuracy, with 98.94% on average for five-category classification, outperforming traditional machine learning methods using only spectral information and representative deep learning methods. Also, ablation experiments confirmed the effectiveness of each module to improve performance. The encouraging results of this study revealed the potentiality of HSI combined with the DL algorithm as an efficient and non-destructive method for the quality control of turtle shells. |
first_indexed | 2024-03-10T23:16:07Z |
format | Article |
id | doaj.art-26115cca872f4075b71a17c35f62a079 |
institution | Directory Open Access Journal |
issn | 1420-3049 |
language | English |
last_indexed | 2024-03-10T23:16:07Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Molecules |
spelling | doaj.art-26115cca872f4075b71a17c35f62a0792023-11-19T08:35:51ZengMDPI AGMolecules1420-30492023-09-012817642710.3390/molecules28176427Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a TransformerTingting Wang0Zhenyu Xu1Huiqiang Hu2Huaxing Xu3Yuping Zhao4Xiaobo Mao5School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaChina Academy of Chinese Medical Sciences, Beijing 100700, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaTurtle shell (<i>Chinemys reecesii</i>) is a prized traditional Chinese dietary therapy, and the growth year of turtle shell has a significant impact on its quality attributes. In this study, a hyperspectral imaging (HSI) technique combined with a proposed deep learning (DL) network algorithm was investigated for the objective determination of the growth year of turtle shells. The acquisition of hyperspectral images was carried out in the near-infrared range (948.72–2512.97 nm) from samples spanning five different growth years. To fully exploit the spatial and spectral information while reducing redundancy in hyperspectral data simultaneously, three modules were developed. First, the spectral–spatial attention (SSA) module was developed to better protect the spectral correlation among spectral bands and capture fine-grained spatial information of hyperspectral images. Second, the 3D convolutional neural network (CNN), more suitable for the extracted 3D feature map, was employed to facilitate the joint spatial–spectral feature representation. Thirdly, to overcome the constraints of convolution kernels as well as better capture long-range correlation between spectral bands, the transformer encoder (TE) module was further designed. These modules were harmoniously orchestrated, driven by the need to effectively leverage both spatial and spectral information within hyperspectral data. They collectively enhance the model’s capacity to extract joint spatial and spectral features to discern growth years accurately. Experimental studies demonstrated that the proposed model (named SSA–3DTE) achieved superior classification accuracy, with 98.94% on average for five-category classification, outperforming traditional machine learning methods using only spectral information and representative deep learning methods. Also, ablation experiments confirmed the effectiveness of each module to improve performance. The encouraging results of this study revealed the potentiality of HSI combined with the DL algorithm as an efficient and non-destructive method for the quality control of turtle shells.https://www.mdpi.com/1420-3049/28/17/6427hyperspectral imagingturtle shellgrowth-year identificationspatial–spectral attention3D convolutional neural networktransformer |
spellingShingle | Tingting Wang Zhenyu Xu Huiqiang Hu Huaxing Xu Yuping Zhao Xiaobo Mao Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer Molecules hyperspectral imaging turtle shell growth-year identification spatial–spectral attention 3D convolutional neural network transformer |
title | Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer |
title_full | Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer |
title_fullStr | Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer |
title_full_unstemmed | Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer |
title_short | Identification of Turtle-Shell Growth Year Using Hyperspectral Imaging Combined with an Enhanced Spatial–Spectral Attention 3DCNN and a Transformer |
title_sort | identification of turtle shell growth year using hyperspectral imaging combined with an enhanced spatial spectral attention 3dcnn and a transformer |
topic | hyperspectral imaging turtle shell growth-year identification spatial–spectral attention 3D convolutional neural network transformer |
url | https://www.mdpi.com/1420-3049/28/17/6427 |
work_keys_str_mv | AT tingtingwang identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer AT zhenyuxu identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer AT huiqianghu identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer AT huaxingxu identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer AT yupingzhao identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer AT xiaobomao identificationofturtleshellgrowthyearusinghyperspectralimagingcombinedwithanenhancedspatialspectralattention3dcnnandatransformer |