Cargando…

SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure

During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a di...

Descripción completa

Detalles Bibliográficos
Autores principales: Ye, Sheng, Liu, Weihua, Zeng, Shan, Wu, Guiju, Chen, Liangyan, Lai, Huaqing, Yan, Zi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346631/
https://www.ncbi.nlm.nih.gov/pubmed/37448042
http://dx.doi.org/10.3390/s23136194
_version_ 1785073358716534784
author Ye, Sheng
Liu, Weihua
Zeng, Shan
Wu, Guiju
Chen, Liangyan
Lai, Huaqing
Yan, Zi
author_facet Ye, Sheng
Liu, Weihua
Zeng, Shan
Wu, Guiju
Chen, Liangyan
Lai, Huaqing
Yan, Zi
author_sort Ye, Sheng
collection PubMed
description During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a difficult problem in the field of target segmentation. In this paper, a network called SY-net, which consists of a feature extractor module, a feature pyramid fusion module, a prediction head module and a prototype mask generation module, is proposed for rice seed instance segmentation. In the feature extraction module, a transformer backbone is used to improve the ability of the network to learn rice seed features; in the pyramid fusion module and the prediction head module, a six-layer feature fusion network and a parallel prediction head structure are employed to enhance the utilization of feature information; and in the prototype mask generation module, a large feature map is used to generate high-quality masks. Training and testing were performed on two public datasets and one private rice seed dataset. The results showed that SY-net achieved a mean average precision (mAP) of 90.71% for the private rice seed dataset and an average precision (AP) of 16.5% with small targets in COCO2017. The network improved the efficiency of rice seed segmentation and showed excellent application prospects in performing rice seed quality testing.
format Online
Article
Text
id pubmed-10346631
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103466312023-07-15 SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure Ye, Sheng Liu, Weihua Zeng, Shan Wu, Guiju Chen, Liangyan Lai, Huaqing Yan, Zi Sensors (Basel) Article During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a difficult problem in the field of target segmentation. In this paper, a network called SY-net, which consists of a feature extractor module, a feature pyramid fusion module, a prediction head module and a prototype mask generation module, is proposed for rice seed instance segmentation. In the feature extraction module, a transformer backbone is used to improve the ability of the network to learn rice seed features; in the pyramid fusion module and the prediction head module, a six-layer feature fusion network and a parallel prediction head structure are employed to enhance the utilization of feature information; and in the prototype mask generation module, a large feature map is used to generate high-quality masks. Training and testing were performed on two public datasets and one private rice seed dataset. The results showed that SY-net achieved a mean average precision (mAP) of 90.71% for the private rice seed dataset and an average precision (AP) of 16.5% with small targets in COCO2017. The network improved the efficiency of rice seed segmentation and showed excellent application prospects in performing rice seed quality testing. MDPI 2023-07-06 /pmc/articles/PMC10346631/ /pubmed/37448042 http://dx.doi.org/10.3390/s23136194 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ye, Sheng
Liu, Weihua
Zeng, Shan
Wu, Guiju
Chen, Liangyan
Lai, Huaqing
Yan, Zi
SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title_full SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title_fullStr SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title_full_unstemmed SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title_short SY-Net: A Rice Seed Instance Segmentation Method Based on a Six-Layer Feature Fusion Network and a Parallel Prediction Head Structure
title_sort sy-net: a rice seed instance segmentation method based on a six-layer feature fusion network and a parallel prediction head structure
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346631/
https://www.ncbi.nlm.nih.gov/pubmed/37448042
http://dx.doi.org/10.3390/s23136194
work_keys_str_mv AT yesheng synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT liuweihua synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT zengshan synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT wuguiju synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT chenliangyan synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT laihuaqing synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure
AT yanzi synetariceseedinstancesegmentationmethodbasedonasixlayerfeaturefusionnetworkandaparallelpredictionheadstructure