THz image recognition of moldy wheat based on multi-scale context and feature pyramid

Wheat is susceptible to mold growth due to storage conditions, which subsequently affects its quality; therefore, timely and rapid identification of moldy wheat is critically important. In order to achieve high-precision recognition and class classification of wheat with different degrees of mold, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuying Jiang, Xinyu Chen, Hongyi Ge, Xixi Wen, Mengdie Jiang, Yuan Zhang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1490384/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850133860289871872
author Yuying Jiang
Yuying Jiang
Yuying Jiang
Xinyu Chen
Xinyu Chen
Xinyu Chen
Hongyi Ge
Hongyi Ge
Hongyi Ge
Xixi Wen
Xixi Wen
Xixi Wen
Mengdie Jiang
Mengdie Jiang
Mengdie Jiang
Yuan Zhang
Yuan Zhang
Yuan Zhang
author_facet Yuying Jiang
Yuying Jiang
Yuying Jiang
Xinyu Chen
Xinyu Chen
Xinyu Chen
Hongyi Ge
Hongyi Ge
Hongyi Ge
Xixi Wen
Xixi Wen
Xixi Wen
Mengdie Jiang
Mengdie Jiang
Mengdie Jiang
Yuan Zhang
Yuan Zhang
Yuan Zhang
author_sort Yuying Jiang
collection DOAJ
description Wheat is susceptible to mold growth due to storage conditions, which subsequently affects its quality; therefore, timely and rapid identification of moldy wheat is critically important. In order to achieve high-precision recognition and class classification of wheat with different degrees of mold, a multi-scale context and feature pyramid based moldy wheat recognition network (MSCFP-Net) is proposed. Firstly, the network uses the residual network ResNeXt as the baseline network, and incorporates a multi-scale contextual feature extraction module, which is more helpful to determine the important discriminative regions in the whole image to extract more image detail features. In addition, a coordinated attention mechanism module is introduced to perform global average pooling from both directions to learn the importance of different regions in the input features in a dynamically weighted manner. Moreover, a bidirectional feature pyramid network is embedded into the baseline model, so that certain coarse-grained features and fine-grained features are retained in the processed output features at the same time to improve the network recognition accuracy. Compared with the baseline network, the four evaluation indexes of Accuracy, Precision, Recall and F1-Score of MSCFP-Net are improved by 1.08%, 1.25%, 0.53% and 0.91%, respectively. In addition, a series of comparison experiments and ablation experiments show that the classification network constructed in this paper has the best fine-grained classification performance for moldy wheat THz images.
format Article
id doaj-art-c5fb41d23f7442cb99e87e8009cd7506
institution OA Journals
issn 1664-462X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-c5fb41d23f7442cb99e87e8009cd75062025-08-20T02:31:51ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-06-011610.3389/fpls.2025.14903841490384THz image recognition of moldy wheat based on multi-scale context and feature pyramidYuying Jiang0Yuying Jiang1Yuying Jiang2Xinyu Chen3Xinyu Chen4Xinyu Chen5Hongyi Ge6Hongyi Ge7Hongyi Ge8Xixi Wen9Xixi Wen10Xixi Wen11Mengdie Jiang12Mengdie Jiang13Mengdie Jiang14Yuan Zhang15Yuan Zhang16Yuan Zhang17Key Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaSchool of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaKey Laboratory of Grain Information Processing & Control, Ministry of Education, Henan University of Technology, Zhengzhou, ChinaHenan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaWheat is susceptible to mold growth due to storage conditions, which subsequently affects its quality; therefore, timely and rapid identification of moldy wheat is critically important. In order to achieve high-precision recognition and class classification of wheat with different degrees of mold, a multi-scale context and feature pyramid based moldy wheat recognition network (MSCFP-Net) is proposed. Firstly, the network uses the residual network ResNeXt as the baseline network, and incorporates a multi-scale contextual feature extraction module, which is more helpful to determine the important discriminative regions in the whole image to extract more image detail features. In addition, a coordinated attention mechanism module is introduced to perform global average pooling from both directions to learn the importance of different regions in the input features in a dynamically weighted manner. Moreover, a bidirectional feature pyramid network is embedded into the baseline model, so that certain coarse-grained features and fine-grained features are retained in the processed output features at the same time to improve the network recognition accuracy. Compared with the baseline network, the four evaluation indexes of Accuracy, Precision, Recall and F1-Score of MSCFP-Net are improved by 1.08%, 1.25%, 0.53% and 0.91%, respectively. In addition, a series of comparison experiments and ablation experiments show that the classification network constructed in this paper has the best fine-grained classification performance for moldy wheat THz images.https://www.frontiersin.org/articles/10.3389/fpls.2025.1490384/fullterahertzidentification of moldy wheatspectral imageimage classificationdeep learning
spellingShingle Yuying Jiang
Yuying Jiang
Yuying Jiang
Xinyu Chen
Xinyu Chen
Xinyu Chen
Hongyi Ge
Hongyi Ge
Hongyi Ge
Xixi Wen
Xixi Wen
Xixi Wen
Mengdie Jiang
Mengdie Jiang
Mengdie Jiang
Yuan Zhang
Yuan Zhang
Yuan Zhang
THz image recognition of moldy wheat based on multi-scale context and feature pyramid
Frontiers in Plant Science
terahertz
identification of moldy wheat
spectral image
image classification
deep learning
title THz image recognition of moldy wheat based on multi-scale context and feature pyramid
title_full THz image recognition of moldy wheat based on multi-scale context and feature pyramid
title_fullStr THz image recognition of moldy wheat based on multi-scale context and feature pyramid
title_full_unstemmed THz image recognition of moldy wheat based on multi-scale context and feature pyramid
title_short THz image recognition of moldy wheat based on multi-scale context and feature pyramid
title_sort thz image recognition of moldy wheat based on multi scale context and feature pyramid
topic terahertz
identification of moldy wheat
spectral image
image classification
deep learning
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1490384/full
work_keys_str_mv AT yuyingjiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT yuyingjiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT yuyingjiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xinyuchen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xinyuchen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xinyuchen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT hongyige thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT hongyige thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT hongyige thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xixiwen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xixiwen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT xixiwen thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT mengdiejiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT mengdiejiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT mengdiejiang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT yuanzhang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT yuanzhang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid
AT yuanzhang thzimagerecognitionofmoldywheatbasedonmultiscalecontextandfeaturepyramid