DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks

Rapid, accurate seed classification of soybean varieties is needed for product quality control. We describe a hyperspectral image-based deep-learning model called Dual Attention Feature Fusion Networks (DAFFnet), which sequentially applies 3D Convolutional Neural Network (CNN) and 2D CNN. A fusion a...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingyu Zhang, Laijun Sun, Xiuliang Jin, Xiangguang Zhao, Shujia Li
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-04-01
Series:Crop Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214514125000224
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849732099079143424
author Lingyu Zhang
Laijun Sun
Xiuliang Jin
Xiangguang Zhao
Shujia Li
author_facet Lingyu Zhang
Laijun Sun
Xiuliang Jin
Xiangguang Zhao
Shujia Li
author_sort Lingyu Zhang
collection DOAJ
description Rapid, accurate seed classification of soybean varieties is needed for product quality control. We describe a hyperspectral image-based deep-learning model called Dual Attention Feature Fusion Networks (DAFFnet), which sequentially applies 3D Convolutional Neural Network (CNN) and 2D CNN. A fusion attention mechanism module in 2D CNN permits the model to capture local and global feature information by combining with Convolution Block Attention Module (CBAM) and Mobile Vision Transformer (MViT), outperforming conventional hyperspectral image classification models in seed classification.
format Article
id doaj-art-b02554c4454b4af69937449ea6747e4b
institution DOAJ
issn 2214-5141
language English
publishDate 2025-04-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Crop Journal
spelling doaj-art-b02554c4454b4af69937449ea6747e4b2025-08-20T03:08:20ZengKeAi Communications Co., Ltd.Crop Journal2214-51412025-04-0113261962910.1016/j.cj.2024.12.023DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networksLingyu Zhang0Laijun Sun1Xiuliang Jin2Xiangguang Zhao3Shujia Li4College of Electronics Engineering, Heilongjiang University, Harbin 150006, Heilongjiang, ChinaCollege of Electronics Engineering, Heilongjiang University, Harbin 150006, Heilongjiang, China; Corresponding authors.Key Laboratory of Crop Physiology and Ecology, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, Ministry of Agriculture, Beijing 100081, China; Corresponding authors.State Key Laboratory of Crop Gene Resources and Breeding, Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaCollege of Electronics Engineering, Heilongjiang University, Harbin 150006, Heilongjiang, ChinaRapid, accurate seed classification of soybean varieties is needed for product quality control. We describe a hyperspectral image-based deep-learning model called Dual Attention Feature Fusion Networks (DAFFnet), which sequentially applies 3D Convolutional Neural Network (CNN) and 2D CNN. A fusion attention mechanism module in 2D CNN permits the model to capture local and global feature information by combining with Convolution Block Attention Module (CBAM) and Mobile Vision Transformer (MViT), outperforming conventional hyperspectral image classification models in seed classification.http://www.sciencedirect.com/science/article/pii/S2214514125000224Soybean seedClassificationDeep learningNeural networksAttention mechanisms
spellingShingle Lingyu Zhang
Laijun Sun
Xiuliang Jin
Xiangguang Zhao
Shujia Li
DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
Crop Journal
Soybean seed
Classification
Deep learning
Neural networks
Attention mechanisms
title DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
title_full DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
title_fullStr DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
title_full_unstemmed DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
title_short DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks
title_sort daffnet seed classification of soybean variety based on dual attention feature fusion networks
topic Soybean seed
Classification
Deep learning
Neural networks
Attention mechanisms
url http://www.sciencedirect.com/science/article/pii/S2214514125000224
work_keys_str_mv AT lingyuzhang daffnetseedclassificationofsoybeanvarietybasedondualattentionfeaturefusionnetworks
AT laijunsun daffnetseedclassificationofsoybeanvarietybasedondualattentionfeaturefusionnetworks
AT xiuliangjin daffnetseedclassificationofsoybeanvarietybasedondualattentionfeaturefusionnetworks
AT xiangguangzhao daffnetseedclassificationofsoybeanvarietybasedondualattentionfeaturefusionnetworks
AT shujiali daffnetseedclassificationofsoybeanvarietybasedondualattentionfeaturefusionnetworks