GrotUNet: a novel leaf segmentation method

In the field of biology, the current leaf segmentation method still has problems such as missed inspections and duplication in the number of large, dense, mutual obstruction and vague division tasks. The reason for the above is that image semantic extraction is not satisfactory and semantic parsing...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongfei Deng, Bin Wen, Cheng Gu, Yingjie Fan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1378958/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713049634603008
author Hongfei Deng
Hongfei Deng
Bin Wen
Bin Wen
Cheng Gu
Yingjie Fan
author_facet Hongfei Deng
Hongfei Deng
Bin Wen
Bin Wen
Cheng Gu
Yingjie Fan
author_sort Hongfei Deng
collection DOAJ
description In the field of biology, the current leaf segmentation method still has problems such as missed inspections and duplication in the number of large, dense, mutual obstruction and vague division tasks. The reason for the above is that image semantic extraction is not satisfactory and semantic parsing is still insufficient. To address the above problems, this paper proposes GrotUNet, a novel leaf segmentation method that can be trained end-to-end. The algorithm is reconstructed in three aspects: semantic feature coding, hopping connectivity, and multiscale upsampling fusion. The semantic coding structure consists of GRblock, WGRblock, and OTblock modules. The former two make full use of the design ideas of GoogLeNet parallel branching and Resnet residual connectivity, while the latter further mines the fine-grained semantic information distributed in the feature space on the feature map after extraction by the WGRblock module to make the feature expression richer. Unlike UNet++ dense connectivity, jump connection reconstruction only uses 1×1  convolution for feature fusion of feature maps from different network hierarchies to enrich the semantic information at each location in the space. The multi-scale upsampling fusion design mechanism incorporates higher-order feature maps into each shallow decoding sub-network, effectively mitigating the loss of semantic parsing information of feature maps. In this paper, the method is fully demonstrated on CVPPP, KOMATSUNA and MSU-PID datasets. The experimental results show that GrotUNet segmentation outperforms existential UNet, ResUNet, UNet++, Perspective + UNet and other methods. Compared with UNet++, GrotUNet improves the key evaluation metrics (SBD) by 0.57%, 0.30%, and 0.27%, respectively.
format Article
id doaj-art-b73fb2707e9646389b602c79a0dfd2b7
institution DOAJ
issn 1664-462X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-b73fb2707e9646389b602c79a0dfd2b72025-08-20T03:14:05ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-07-011610.3389/fpls.2025.13789581378958GrotUNet: a novel leaf segmentation methodHongfei Deng0Hongfei Deng1Bin Wen2Bin Wen3Cheng Gu4Yingjie Fan5Key Laboratory of Ethnic Education Informatization, Yunnan Normal University, Kunming, ChinaSchool of Information Technology Industry, Yunnan Vocational Institute of Energy Technology, Qujing, ChinaKey Laboratory of Ethnic Education Informatization, Yunnan Normal University, Kunming, ChinaSchool of Information Science, Yunnan Normal University, Kunming, ChinaSchool of Information Science, Yunnan Normal University, Kunming, ChinaSchool of Information Science, Yunnan Normal University, Kunming, ChinaIn the field of biology, the current leaf segmentation method still has problems such as missed inspections and duplication in the number of large, dense, mutual obstruction and vague division tasks. The reason for the above is that image semantic extraction is not satisfactory and semantic parsing is still insufficient. To address the above problems, this paper proposes GrotUNet, a novel leaf segmentation method that can be trained end-to-end. The algorithm is reconstructed in three aspects: semantic feature coding, hopping connectivity, and multiscale upsampling fusion. The semantic coding structure consists of GRblock, WGRblock, and OTblock modules. The former two make full use of the design ideas of GoogLeNet parallel branching and Resnet residual connectivity, while the latter further mines the fine-grained semantic information distributed in the feature space on the feature map after extraction by the WGRblock module to make the feature expression richer. Unlike UNet++ dense connectivity, jump connection reconstruction only uses 1×1  convolution for feature fusion of feature maps from different network hierarchies to enrich the semantic information at each location in the space. The multi-scale upsampling fusion design mechanism incorporates higher-order feature maps into each shallow decoding sub-network, effectively mitigating the loss of semantic parsing information of feature maps. In this paper, the method is fully demonstrated on CVPPP, KOMATSUNA and MSU-PID datasets. The experimental results show that GrotUNet segmentation outperforms existential UNet, ResUNet, UNet++, Perspective + UNet and other methods. Compared with UNet++, GrotUNet improves the key evaluation metrics (SBD) by 0.57%, 0.30%, and 0.27%, respectively.https://www.frontiersin.org/articles/10.3389/fpls.2025.1378958/fullinstance segmentationfeature codingjump connectionmulti-scale fusionGoogLeNet
spellingShingle Hongfei Deng
Hongfei Deng
Bin Wen
Bin Wen
Cheng Gu
Yingjie Fan
GrotUNet: a novel leaf segmentation method
Frontiers in Plant Science
instance segmentation
feature coding
jump connection
multi-scale fusion
GoogLeNet
title GrotUNet: a novel leaf segmentation method
title_full GrotUNet: a novel leaf segmentation method
title_fullStr GrotUNet: a novel leaf segmentation method
title_full_unstemmed GrotUNet: a novel leaf segmentation method
title_short GrotUNet: a novel leaf segmentation method
title_sort grotunet a novel leaf segmentation method
topic instance segmentation
feature coding
jump connection
multi-scale fusion
GoogLeNet
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1378958/full
work_keys_str_mv AT hongfeideng grotunetanovelleafsegmentationmethod
AT hongfeideng grotunetanovelleafsegmentationmethod
AT binwen grotunetanovelleafsegmentationmethod
AT binwen grotunetanovelleafsegmentationmethod
AT chenggu grotunetanovelleafsegmentationmethod
AT yingjiefan grotunetanovelleafsegmentationmethod