Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.

Accurately recognizing rice seed varieties poses significant challenges due to their diverse morphological characteristics and complex classification requirements. Traditional image recognition methods often struggle with both accuracy and efficiency in this context. To address these limitations, th...

Full description

Saved in:
Bibliographic Details
Main Authors: Tingyuan Zhang, Changsheng Zhang, Zhongyi Yang, Meng Wang, Fujie Zhang, Dekai Li, Sen Yang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0322699
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261224309129216
author Tingyuan Zhang
Changsheng Zhang
Zhongyi Yang
Meng Wang
Fujie Zhang
Dekai Li
Sen Yang
author_facet Tingyuan Zhang
Changsheng Zhang
Zhongyi Yang
Meng Wang
Fujie Zhang
Dekai Li
Sen Yang
author_sort Tingyuan Zhang
collection DOAJ
description Accurately recognizing rice seed varieties poses significant challenges due to their diverse morphological characteristics and complex classification requirements. Traditional image recognition methods often struggle with both accuracy and efficiency in this context. To address these limitations, this study proposes the Deep Space and Channel Residual Network with Double Attention Mechanism (RSCD-Net) to enhance the recognition accuracy of 36 rice seed varieties. The core innovation of RSCD-Net is the introduction of the Space and Channel Feature Extraction Residual Block (SCR-Block), which improves inter-class differentiation while minimizing redundant features, thereby optimizing computational efficiency. The RSCD-Net architecture consists of 16 layers of SCR-Blocks, structured into four convolutional stages with 3, 4, 6, and 3 units, respectively. Additionally, a Double Attention Mechanism (A2Net) is incorporated to enhance the network's global receptive field, improving its capacity to distinguish subtle variations among seed types. Experimental results on a self-collected dataset demonstrate that RSCD-Net achieves an average accuracy of 81.94%, surpassing the baseline model by 4.16%. Compared with state-of-the-art models such as InceptionResNetV2, ConvNeXt, MobileNetV3, and Swin Transformer, RSCD Net has improved by 1.17%, 3%, 24.72%, and 13.22%, respectively, showcasing its superior performance. These findings confirm that RSCD-Net provides an effective and efficient solution for rice seed classification, offering a promising reference for addressing similar fine-grained recognition challenges in agricultural applications.
format Article
id doaj-art-7e9aa800380749d5a54b4ddb8d16a69e
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-7e9aa800380749d5a54b4ddb8d16a69e2025-08-20T01:55:28ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032269910.1371/journal.pone.0322699Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.Tingyuan ZhangChangsheng ZhangZhongyi YangMeng WangFujie ZhangDekai LiSen YangAccurately recognizing rice seed varieties poses significant challenges due to their diverse morphological characteristics and complex classification requirements. Traditional image recognition methods often struggle with both accuracy and efficiency in this context. To address these limitations, this study proposes the Deep Space and Channel Residual Network with Double Attention Mechanism (RSCD-Net) to enhance the recognition accuracy of 36 rice seed varieties. The core innovation of RSCD-Net is the introduction of the Space and Channel Feature Extraction Residual Block (SCR-Block), which improves inter-class differentiation while minimizing redundant features, thereby optimizing computational efficiency. The RSCD-Net architecture consists of 16 layers of SCR-Blocks, structured into four convolutional stages with 3, 4, 6, and 3 units, respectively. Additionally, a Double Attention Mechanism (A2Net) is incorporated to enhance the network's global receptive field, improving its capacity to distinguish subtle variations among seed types. Experimental results on a self-collected dataset demonstrate that RSCD-Net achieves an average accuracy of 81.94%, surpassing the baseline model by 4.16%. Compared with state-of-the-art models such as InceptionResNetV2, ConvNeXt, MobileNetV3, and Swin Transformer, RSCD Net has improved by 1.17%, 3%, 24.72%, and 13.22%, respectively, showcasing its superior performance. These findings confirm that RSCD-Net provides an effective and efficient solution for rice seed classification, offering a promising reference for addressing similar fine-grained recognition challenges in agricultural applications.https://doi.org/10.1371/journal.pone.0322699
spellingShingle Tingyuan Zhang
Changsheng Zhang
Zhongyi Yang
Meng Wang
Fujie Zhang
Dekai Li
Sen Yang
Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
PLoS ONE
title Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
title_full Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
title_fullStr Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
title_full_unstemmed Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
title_short Multi-class rice seed recognition based on deep space and channel residual network combined with double attention mechanism.
title_sort multi class rice seed recognition based on deep space and channel residual network combined with double attention mechanism
url https://doi.org/10.1371/journal.pone.0322699
work_keys_str_mv AT tingyuanzhang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT changshengzhang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT zhongyiyang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT mengwang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT fujiezhang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT dekaili multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism
AT senyang multiclassriceseedrecognitionbasedondeepspaceandchannelresidualnetworkcombinedwithdoubleattentionmechanism