Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points Article Swipe

PDF

Yanjie Xu , Handing Xu , Tianmu Wang , Yaguan Li , Yunzhi Chen , Zhenguo Nie ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.10992

Rotation-invariant recognition of shapes is a common challenge in computer vision. Recent approaches have significantly improved the accuracy of rotation-invariant recognition by encoding the rotational invariance of shapes as hand-crafted image features and introducing deep neural networks. However, the methods based on pixels have too much redundant information, and the critical geometric information is prone to early leakage, resulting in weak rotation-invariant recognition of fine-grained shapes. In this paper, we reconsider the shape recognition problem from the perspective of contour points rather than pixels. We propose an anti-noise rotation-invariant convolution module based on contour geometric aware for fine-grained shape recognition. The module divides the shape contour into multiple local geometric regions(LGA), where we implement finer-grained rotation-invariant coding in terms of point topological relations. We provide a deep network composed of five such cascaded modules for classification and retrieval experiments. The results show that our method exhibits excellent performance in rotation-invariant recognition of fine-grained shapes. In addition, we demonstrate that our method is robust to contour noise and the rotation centers. The source code is available at https://github.com/zhenguonie/ANRICN_CGA.

Related Topics

List Of States With Limited Recognition

Facial Recognition System

Pattern Recognition

Iris Recognition

Pattern Recognition (Novel)

Automatic Number-Plate Recognition

Legal Recognition Of Non-Binary Gender

Revenue Recognition

Diplomatic Recognition

Speech Recognition & Synthesis

Handwriting Recognition

Gesture Recognition

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2503.10992
PDF: https://arxiv.org/pdf/2503.10992
OA Status: green
OpenAlex ID: https://openalex.org/W4417281685

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417281685

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2503.10992

Digital Object Identifier
Title: Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-14

Full publication date if available
Authors: Yanjie Xu, Handing Xu, Tianmu Wang, Yaguan Li, Yunzhi Chen, Zhenguo Nie

List of authors in order
Landing page: https://arxiv.org/abs/2503.10992

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.10992

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2503.10992

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417281685
doi	https://doi.org/10.48550/arxiv.2503.10992
ids.doi	https://doi.org/10.48550/arxiv.2503.10992
ids.openalex	https://openalex.org/W4417281685
fwci
type	preprint
title	Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2503.10992
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2503.10992
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2503.10992
locations[1].id	doi:10.48550/arxiv.2503.10992
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2503.10992
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101044676
authorships[0].author.orcid	https://orcid.org/0000-0001-5327-5022
authorships[0].author.display_name	Yanjie Xu
authorships[0].author_position	first
authorships[0].raw_author_name	Xu, Yanjie
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5019751541
authorships[1].author.orcid	https://orcid.org/0000-0002-2547-4048
authorships[1].author.display_name	Handing Xu
authorships[1].author_position	middle
authorships[1].raw_author_name	Xu, Handing
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5000164834
authorships[2].author.orcid
authorships[2].author.display_name	Tianmu Wang
authorships[2].author_position	middle
authorships[2].raw_author_name	Wang, Tianmu
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5021038504
authorships[3].author.orcid
authorships[3].author.display_name	Yaguan Li
authorships[3].author_position	middle
authorships[3].raw_author_name	Li, Yaguan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5101592930
authorships[4].author.orcid	https://orcid.org/0000-0001-5917-3836
authorships[4].author.display_name	Yunzhi Chen
authorships[4].author_position	middle
authorships[4].raw_author_name	Chen, Yunzhi
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5068855808
authorships[5].author.orcid	https://orcid.org/0000-0002-1990-3037
authorships[5].author.display_name	Zhenguo Nie
authorships[5].author_position	last
authorships[5].raw_author_name	Nie, Zhenguo
authorships[5].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2503.10992
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points
has_fulltext	False
is_retracted	False
updated_date	2025-12-13T23:11:00.310470
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2503.10992
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2503.10992
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2503.10992
primary_location.id	pmh:oai:arXiv.org:2503.10992
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2503.10992
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2503.10992
publication_date	2025-03-14
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	5, 125
abstract_inverted_index.In	66, 154
abstract_inverted_index.We	84, 123
abstract_inverted_index.an	86
abstract_inverted_index.as	28
abstract_inverted_index.at	175
abstract_inverted_index.by	21
abstract_inverted_index.in	8, 59, 117, 148
abstract_inverted_index.is	4, 53, 161, 173
abstract_inverted_index.of	2, 18, 26, 63, 78, 119, 129, 151
abstract_inverted_index.on	41, 92
abstract_inverted_index.to	55, 163
abstract_inverted_index.we	69, 112, 156
abstract_inverted_index.The	100, 139, 170
abstract_inverted_index.and	32, 48, 136, 166
abstract_inverted_index.for	96, 134
abstract_inverted_index.our	143, 159
abstract_inverted_index.the	16, 23, 38, 49, 71, 76, 103, 167
abstract_inverted_index.too	44
abstract_inverted_index.code	172
abstract_inverted_index.deep	34, 126
abstract_inverted_index.five	130
abstract_inverted_index.from	75
abstract_inverted_index.have	13, 43
abstract_inverted_index.into	106
abstract_inverted_index.much	45
abstract_inverted_index.show	141
abstract_inverted_index.such	131
abstract_inverted_index.than	82
abstract_inverted_index.that	142, 158
abstract_inverted_index.this	67
abstract_inverted_index.weak	60
abstract_inverted_index.aware	95
abstract_inverted_index.based	40, 91
abstract_inverted_index.early	56
abstract_inverted_index.image	30
abstract_inverted_index.local	108
abstract_inverted_index.noise	165
abstract_inverted_index.point	120
abstract_inverted_index.prone	54
abstract_inverted_index.shape	72, 98, 104
abstract_inverted_index.terms	118
abstract_inverted_index.where	111
abstract_inverted_index.Recent	11
abstract_inverted_index.coding	116
abstract_inverted_index.common	6
abstract_inverted_index.method	144, 160
abstract_inverted_index.module	90, 101
abstract_inverted_index.neural	35
abstract_inverted_index.paper,	68
abstract_inverted_index.pixels	42
abstract_inverted_index.points	80
abstract_inverted_index.rather	81
abstract_inverted_index.robust	162
abstract_inverted_index.shapes	3, 27
abstract_inverted_index.source	171
abstract_inverted_index.contour	79, 93, 105, 164
abstract_inverted_index.divides	102
abstract_inverted_index.methods	39
abstract_inverted_index.modules	133
abstract_inverted_index.network	127
abstract_inverted_index.pixels.	83
abstract_inverted_index.problem	74
abstract_inverted_index.propose	85
abstract_inverted_index.provide	124
abstract_inverted_index.results	140
abstract_inverted_index.shapes.	65, 153
abstract_inverted_index.vision.	10
abstract_inverted_index.However,	37
abstract_inverted_index.accuracy	17
abstract_inverted_index.cascaded	132
abstract_inverted_index.centers.	169
abstract_inverted_index.composed	128
abstract_inverted_index.computer	9
abstract_inverted_index.critical	50
abstract_inverted_index.encoding	22
abstract_inverted_index.exhibits	145
abstract_inverted_index.features	31
abstract_inverted_index.improved	15
abstract_inverted_index.leakage,	57
abstract_inverted_index.multiple	107
abstract_inverted_index.rotation	168
abstract_inverted_index.addition,	155
abstract_inverted_index.available	174
abstract_inverted_index.challenge	7
abstract_inverted_index.excellent	146
abstract_inverted_index.geometric	51, 94, 109
abstract_inverted_index.implement	113
abstract_inverted_index.networks.	36
abstract_inverted_index.redundant	46
abstract_inverted_index.resulting	58
abstract_inverted_index.retrieval	137
abstract_inverted_index.anti-noise	87
abstract_inverted_index.approaches	12
abstract_inverted_index.invariance	25
abstract_inverted_index.reconsider	70
abstract_inverted_index.relations.	122
abstract_inverted_index.rotational	24
abstract_inverted_index.convolution	89
abstract_inverted_index.demonstrate	157
abstract_inverted_index.information	52
abstract_inverted_index.introducing	33
abstract_inverted_index.performance	147
abstract_inverted_index.perspective	77
abstract_inverted_index.recognition	1, 20, 62, 73, 150
abstract_inverted_index.topological	121
abstract_inverted_index.experiments.	138
abstract_inverted_index.fine-grained	64, 97, 152
abstract_inverted_index.hand-crafted	29
abstract_inverted_index.information,	47
abstract_inverted_index.recognition.	99
abstract_inverted_index.finer-grained	114
abstract_inverted_index.regions(LGA),	110
abstract_inverted_index.significantly	14
abstract_inverted_index.classification	135
abstract_inverted_index.Rotation-invariant	0
abstract_inverted_index.rotation-invariant	19, 61, 88, 115, 149
abstract_inverted_index.https://github.com/zhenguonie/ANRICN_CGA.	176
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile