Research on YOLOv5 Oracle Recognition Algorithm Based on Multi-Module Fusion

The recognition of oracle bone script is of significant importance for understanding the evolution of Chinese characters, their morphological features, and semantic changes. However, traditional methods and some deep learning models have limited ability to capture the complex forms and fine details...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE access Vol. 13; pp. 24358 - 24367
Main Authors:	Zhang, Xinhang, Ma, Zhenhua, Zhang, Yaru, Ru, Huiying
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial neural networks Attention mechanisms BiFPN_SDI Bones C3_DAttention Character recognition Convolution detect_efficient Evolutionary algorithms Feature extraction Machine learning Neck Object recognition Optimization oracle recognition Target detection Text recognition Transforms YOLO YOLOv5
ISSN:	2169-3536, 2169-3536
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The recognition of oracle bone script is of significant importance for understanding the evolution of Chinese characters, their morphological features, and semantic changes. However, traditional methods and some deep learning models have limited ability to capture the complex forms and fine details of oracle bone script, which makes it difficult to fully detect subtle differences between characters. Additionally, models trained on such data tend to struggle with recognizing rare or unseen characters, often leading to recognition errors. Therefore, improving the robustness of these models is essential. This paper presents a novel recognition algorithm based on YOLOv5, incorporating BiFPN-SDI, C3-DAttention, and Detect_Efficient to significantly enhance detection performance. BiFPN-SDI enables more precise feature fusion and attention mechanisms, improving the detection of small targets. C3-DAttention combines channel and spatial attention mechanisms to enhance feature extraction in deep convolutional neural networks. Detect_Efficient further improves the model's detection and recognition capabilities. Experimental results show that the proposed improvements lead to a 0.7% increase in precision, a 1.1% increase in recall, and a 0.3% improvement in MAP@50. Furthermore, the model's parameter count is reduced to 1,009,668, and its processing speed is increased to 90 fps, significantly improving the ability to extract and recognize features in oracle bone script.
AbstractList	The recognition of oracle bone script is of significant importance for understanding the evolution of Chinese characters, their morphological features, and semantic changes. However, traditional methods and some deep learning models have limited ability to capture the complex forms and fine details of oracle bone script, which makes it difficult to fully detect subtle differences between characters. Additionally, models trained on such data tend to struggle with recognizing rare or unseen characters, often leading to recognition errors. Therefore, improving the robustness of these models is essential. This paper presents a novel recognition algorithm based on YOLOv5, incorporating BiFPN-SDI, C3-DAttention, and Detect_Efficient to significantly enhance detection performance. BiFPN-SDI enables more precise feature fusion and attention mechanisms, improving the detection of small targets. C3-DAttention combines channel and spatial attention mechanisms to enhance feature extraction in deep convolutional neural networks. Detect_Efficient further improves the model's detection and recognition capabilities. Experimental results show that the proposed improvements lead to a 0.7% increase in precision, a 1.1% increase in recall, and a 0.3% improvement in MAP@50. Furthermore, the model's parameter count is reduced to 1,009,668, and its processing speed is increased to 90 fps, significantly improving the ability to extract and recognize features in oracle bone script.
Author	Zhang, Xinhang Zhang, Yaru Ru, Huiying Ma, Zhenhua
Author_xml	– sequence: 1 givenname: Xinhang orcidid: 0009-0006-1831-1650 surname: Zhang fullname: Zhang, Xinhang organization: School of Science, Hebei University of Architecture, Zhangjiakou, Hebei, China – sequence: 2 givenname: Zhenhua orcidid: 0000-0002-2916-7117 surname: Ma fullname: Ma, Zhenhua organization: School of Science, Hebei University of Architecture, Zhangjiakou, Hebei, China – sequence: 3 givenname: Yaru surname: Zhang fullname: Zhang, Yaru organization: School of Science, Hebei University of Architecture, Zhangjiakou, Hebei, China – sequence: 4 givenname: Huiying orcidid: 0000-0002-6875-4525 surname: Ru fullname: Ru, Huiying email: 240944653@qq.com organization: School of Science, Hebei University of Architecture, Zhangjiakou, Hebei, China
BookMark	eNp9UU1P5SAUJcZJxq9fMC6auO4TSill-XzRGZNnXqLjwhW50NsnL7UotCbz74daTYwL2Vy4nHM4l3NI9nvfIyG_GF0wRtX5crW6vLtbFLQQCy54JQTfIwcFq1Q-Hfc_7X-Skxh3NK06tYQ8IOtbjAjBPma-zx42682ryDYBbIfZLVq_7d3g0s2y2_rghsen7AIiNhP4ZuwGl9_4ZkzYqzEm2DH50UIX8eS9HpH7q8u_qz_5evP7erVc57akashl1RbKljVUpuXGSgOyZrZFWRoBDWUSS6xAMWpqIzgFLgFA1aAqQy1Yyo_I9azbeNjp5-CeIPzTHpx-a_iw1RAGl4bQlApr6vRi20JpjTHSCkkLBdg0KGWRtM5mrefgX0aMg975MfTJvuasEio5ZjKh1IyywccYsNXWDTB9zRDAdZpRPWWh5yz0lIV-zyJx-Rfuh-PvWaczyyHiJ0YtUnQV_w8lSJcz
CODEN	IAECCG
CitedBy_id	crossref_primary_10_3390_ani15182709
Cites_doi	10.3390/s23146477 10.3390/s23208355 10.1142/S0217979216300012 10.3390/s22093537 10.1109/TIP.2015.2500019 10.5220/0006225706060611
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA
DOI	10.1109/ACCESS.2025.3536553
DatabaseName	IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2169-3536
EndPage	24367
ExternalDocumentID	oai_doaj_org_article_005cb876fffa4cbbb7c57029aedde772 10_1109_ACCESS_2025_3536553 10858166
Genre	orig-research
GrantInformation_xml	– fundername: Nature Science Foundation of Hebei Province grantid: A2023404001 funderid: 10.13039/501100003787 – fundername: Three-Three-Three Talent Project funded Project of Hebei Province 2023 grantid: C20231019 funderid: 10.13039/501100003787
GroupedDBID	0R~ 4.4 5VS 6IK 97E AAJGR ABAZT ABVLG ACGFS ADBBV AGSQL ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL GROUPED_DOAJ IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RNS AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c409t-76f29c48a6bf3bc7ba781cfe74b5ad017e4e6a910b8b530a37aaa98a96b0cac03
IEDL.DBID	DOA
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001420679000050&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2169-3536
IngestDate	Fri Oct 03 12:43:23 EDT 2025 Mon Jun 30 12:39:32 EDT 2025 Sat Nov 29 08:20:11 EST 2025 Tue Nov 18 20:47:28 EST 2025 Wed Aug 27 01:50:59 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c409t-76f29c48a6bf3bc7ba781cfe74b5ad017e4e6a910b8b530a37aaa98a96b0cac03
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0006-1831-1650 0000-0002-2916-7117 0000-0002-6875-4525
OpenAccessLink	https://doaj.org/article/005cb876fffa4cbbb7c57029aedde772
PQID	3165940917
PQPubID	4845423
PageCount	10
ParticipantIDs	doaj_primary_oai_doaj_org_article_005cb876fffa4cbbb7c57029aedde772 proquest_journals_3165940917 crossref_primary_10_1109_ACCESS_2025_3536553 crossref_citationtrail_10_1109_ACCESS_2025_3536553 ieee_primary_10858166
PublicationCentury	2000
PublicationDate	20250000 2025-00-00 20250101 2025-01-01
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– year: 2025 text: 20250000
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE access
PublicationTitleAbbrev	Access
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref14 ref10 Xiaojun (ref1) 2024; 19 Qinxia (ref6) 2012; 32 Shaotong (ref11) 2008; 22 Feng (ref5) 1996; 18 Xiaoqing (ref8) 2010; 25 ref17 Shaotong (ref7) 2016; 44 ref16 Yafei (ref4) 2023 Xinran (ref15) 2024 Tingzhu (ref3) 2023; 37 Ming (ref2) 2024; 37 Liu (ref9) 2004; 17
References_xml	– volume: 18 start-page: 41 issue: 1 year: 1996 ident: ref5 article-title: A graph-theoretic approach to automatic Oracle bone character recognition publication-title: J. Electron. Sci. – volume: 25 start-page: 92 issue: 2 year: 2010 ident: ref8 article-title: An Oracle classification method based on graph recognition publication-title: J. Beijing Univ. Inf. Sci. Technol. – volume: 37 start-page: 1 year: 2024 ident: ref2 article-title: A text recognition algorithm for Qinjian based on lightweight transformer model publication-title: Comput. Simul. – volume: 19 start-page: 106 issue: 1 year: 2024 ident: ref1 article-title: Small-sample Oracle bone character recognition based on supervised comparison learning publication-title: J. Intell. Syst. – year: 2023 ident: ref4 article-title: Research on Oracle bone character recognition based on convolutional neural network – volume: 17 start-page: 139 issue: 8 year: 2004 ident: ref9 article-title: Design and implementation of visual Oracle input method publication-title: Comput. Eng. Appl. – ident: ref16 doi: 10.3390/s23146477 – volume: 22 start-page: 123 issue: 4 year: 2008 ident: ref11 article-title: Research on Oracle input coding based on glyph topology publication-title: J. Chin. Inf. – volume: 44 start-page: 2001 issue: 10 year: 2016 ident: ref7 article-title: A topological alignment-based method for Oracle bone character recognition publication-title: Comput. Digit. Eng. – volume: 32 start-page: 2374 issue: 8 year: 2012 ident: ref6 article-title: Design and implementation of an Oracle bone input method based on directed strokes publication-title: Comput. Appl. – year: 2024 ident: ref15 article-title: Research on Oracle bone character detection method based on deep learning – ident: ref14 doi: 10.3390/s23208355 – ident: ref13 doi: 10.1142/S0217979216300012 – ident: ref17 doi: 10.3390/s22093537 – ident: ref12 doi: 10.1109/TIP.2015.2500019 – volume: 37 start-page: 1 issue: 1 year: 2023 ident: ref3 article-title: Oracle recognition based on feature point matching publication-title: Chin. Script Res. – ident: ref10 doi: 10.5220/0006225706060611
SSID	ssj0000816957
Score	2.341111
Snippet	The recognition of oracle bone script is of significant importance for understanding the evolution of Chinese characters, their morphological features, and...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Enrichment Source Index Database Publisher
StartPage	24358
SubjectTerms	Artificial neural networks Attention mechanisms BiFPN_SDI Bones C3_DAttention Character recognition Convolution detect_efficient Evolutionary algorithms Feature extraction Machine learning Neck Object recognition Optimization oracle recognition Target detection Text recognition Transforms YOLO YOLOv5
SummonAdditionalLinks	– databaseName: IEEE Electronic Library (IEL) dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED-xiQd4GAyG6BgoDzySLaljO37sKioethUhkMaTdXZsmDSaqWv39-_OcashBBJvUXJWHP9y57vzfQC8576PWAcuGypU2RjS4ZyOqow-EAP6JpjWp2YT-uKivbw0n3OyesqFCSGk4LNwzJfpLL_r_ZpdZSccKc_nXDuwo7UakrW2DhXuIGGkzpWF6sqcTKZT-giyAcfyWEihpBS_7T6pSH_uqvKHKE77y-zZf87sOexlRbKYDMjvw6OweAFPH5QXfAlnm7C6ol8U3-dn8ztZzJdI5MWXTdwQPZlc_-iXV6ufv4pT2tI6Jk5pueV5362JdrZmj9oBfJt9_Dr9VObuCaUnm21VahXHxjctKheF89qhbmsfg26cxI4YMTRBIWkLrnVSVCg0IpoWjXKVR1-JV7C76BfhNRTKiaoj0DpWv5AAlUEJDK2Jku1FHMF4s6rW59Li3OHi2iYTozJ2gMIyFDZDMYIP20E3Q2WNf5OfMlxbUi6LnW4QDjZzmSWR4h3J9xgjNt45p73U1dhgIClOdsQIDhi7B-8bYBvB0QZ9m3n41opaSUNLWevDvwx7A094ioNH5gh2V8t1eAuP_d3q6nb5Lv2e97r04eU priority: 102 providerName: IEEE
Title	Research on YOLOv5 Oracle Recognition Algorithm Based on Multi-Module Fusion
URI	https://ieeexplore.ieee.org/document/10858166 https://www.proquest.com/docview/3165940917 https://doaj.org/article/005cb876fffa4cbbb7c57029aedde772
Volume	13
WOSCitedRecordID	wos001420679000050&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center) customDbUrl: eissn: 2169-3536 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000816957 issn: 2169-3536 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELYQYoAB8RSFUmVgJJDU8Wtsq1YMQBECCSbr7DiABCnqa-S3c3ZSVIQEC0uG5CLH393Zd479HSEnvu4jpM7ThlIeZwpjOCMKHhfWoQPazClpQ7EJcX0tHx7UzVKpL78nrKIHroA7RyuxBl22KArIrDFGWCaStgKHjomhoR99E6GWkqkwBsuUKyZqmqE0UeedXg97hAlhm51RRjlj9NtUFBj76xIrP8blMNkMtshmHSVGnerrtsmKK3fIxhJ34C65XOyZi0Zl9Di8HM5ZNBwDike3i01B-KTz-jTC_P_5LerifJV74XDmNr4a5TOUHcz8ctkeuR_073oXcV0aIbaYkE1jxKOtbCaBm4IaKwwImdrCicwwyNHLXOY4YChgpGE0ASoAQElQ3CQWbEL3yWo5Kt0BibihSY4ayX1sBagt5jgFJ1XBfDIIDdJeoKRtzRvuy1e86pA_JEpX0GoPra6hbZDTr5feK9qM38W7Hv4vUc95HW6gJejaEvRfltAge155S-1J5v-KNkhzoU1dO-hE05QzhVCm4vA_2j4i674_1dpMk6xOxzN3TNbsfPoyGbeCbeL16qPfCicMPwGCoegB
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED_BQGJ74HMThQF54JFsSRzb8WNXrRqiaxEa0niybMcek0aDunZ__-4ctxpCQ-ItSs6K41_ufHe-D4CP1PfRlJ7KhjKR1wp1OCuDyIPzyICu9qpxsdmEnE6b83P1NSWrx1wY730MPvMHdBnP8tvOrchVdkiR8nTO9RAe8bquij5da-NSoR4SistUW6gs1OFwNMLPQCuw4geMM8E5-2P_iWX6U1-Vv4Rx3GHGz_5zbs_haVIls2GP_Qt44OcvYedOgcFXMFkH1mXdPPsxm8xueDZbGCTPvq0jh_DJ8OqiW1wuf_7KjnBTa4k4Jubmp127Qtrxinxqu_B9fHw2OslT_4TcodW2zKUIlXJ1Y4QNzDppjWxKF7ysLTctsqKvvTCoL9jGclYYJo0xqjFK2MIZV7A92Jp3c_8aMmFZ0SJsLSlgBiHlXjDjGxU4WYxmANV6VbVLxcWpx8WVjkZGoXQPhSYodIJiAJ82g373tTX-TX5EcG1IqTB2vIE46MRnGoWKsyjhQwimdtZa6bgsKmU8ynG0JAawS9jdeV8P2wD21-jrxMXXmpWCK1zKUr65Z9gHeHJydjrRk8_TL29hm6bb-2f2YWu5WPl38NjdLC-vF-_jr3oLoB_lLA
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Research+on+YOLOv5+Oracle+Recognition+Algorithm+Based+on+Multi-Module+Fusion&rft.jtitle=IEEE+access&rft.au=Zhang%2C+Xinhang&rft.au=Ma%2C+Zhenhua&rft.au=Zhang%2C+Yaru&rft.au=Ru%2C+Huiying&rft.date=2025&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=13&rft.spage=24358&rft.epage=24367&rft_id=info:doi/10.1109%2FACCESS.2025.3536553&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2025_3536553
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon