A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.6/9171 |
Resumo: | Caricatures refer to a representation of aperson in which the distinctive features are deliberatelyexaggerated, with several studies showing that humansperform better at recognizing people from caricaturesthan using original images. Inspired by this observa-tion, this paper introduces the first fully automatedcaricature-based face recognition approach capable ofworking with data acquired in the wild. Our approachleverages the 3D face structure from a single 2D imageand compares it to a reference model for obtaininga compact representation of face features deviations.This descriptor is subsequently deformed using a ’mea-sure locally, weight globally’ strategy to resemble thecaricature drawing process. The deformed deviationsare incorporated in the 3D model using the Laplacianmesh deformation algorithm, and the 2D face cari-cature image is obtained by projecting the deformedmodel in the original camera-view. To demonstratethe advantages of caricature-based face recognition, wetrain the VGG-Face network from scratch using eitheroriginal face images (baseline) or caricatured images,and use these models for extracting face descriptorsfrom the LFW, IJB-A and MegaFace datasets. The ex-periments show an increase in the recognition accuracywhen using caricatures rather than original images.Moreover, our approach achieves competitive resultswith state-of-the-art face recognition methods, evenwithout explicitly tuning the network for any of theevaluation sets. |
id |
RCAP_9ef00f1f663fe50ab40e5728ef05d9d8 |
---|---|
oai_identifier_str |
oai:ubibliorum.ubi.pt:10400.6/9171 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based CaricaturesFace recognition3D caricatureCaricatures refer to a representation of aperson in which the distinctive features are deliberatelyexaggerated, with several studies showing that humansperform better at recognizing people from caricaturesthan using original images. Inspired by this observa-tion, this paper introduces the first fully automatedcaricature-based face recognition approach capable ofworking with data acquired in the wild. Our approachleverages the 3D face structure from a single 2D imageand compares it to a reference model for obtaininga compact representation of face features deviations.This descriptor is subsequently deformed using a ’mea-sure locally, weight globally’ strategy to resemble thecaricature drawing process. The deformed deviationsare incorporated in the 3D model using the Laplacianmesh deformation algorithm, and the 2D face cari-cature image is obtained by projecting the deformedmodel in the original camera-view. To demonstratethe advantages of caricature-based face recognition, wetrain the VGG-Face network from scratch using eitheroriginal face images (baseline) or caricatured images,and use these models for extracting face descriptorsfrom the LFW, IJB-A and MegaFace datasets. The ex-periments show an increase in the recognition accuracywhen using caricatures rather than original images.Moreover, our approach achieves competitive resultswith state-of-the-art face recognition methods, evenwithout explicitly tuning the network for any of theevaluation sets.uBibliorumNeves, JoãoProença, H.2020-02-10T14:12:01Z20182018-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.6/9171eng10.1109/TIFS.2018.2846617info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-15T09:49:50Zoai:ubibliorum.ubi.pt:10400.6/9171Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:49:20.863818Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
title |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
spellingShingle |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures Neves, João Face recognition 3D caricature |
title_short |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
title_full |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
title_fullStr |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
title_full_unstemmed |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
title_sort |
A Leopard Cannot Change Its Spots: Improving Face Recognition Using 3D-based Caricatures |
author |
Neves, João |
author_facet |
Neves, João Proença, H. |
author_role |
author |
author2 |
Proença, H. |
author2_role |
author |
dc.contributor.none.fl_str_mv |
uBibliorum |
dc.contributor.author.fl_str_mv |
Neves, João Proença, H. |
dc.subject.por.fl_str_mv |
Face recognition 3D caricature |
topic |
Face recognition 3D caricature |
description |
Caricatures refer to a representation of aperson in which the distinctive features are deliberatelyexaggerated, with several studies showing that humansperform better at recognizing people from caricaturesthan using original images. Inspired by this observa-tion, this paper introduces the first fully automatedcaricature-based face recognition approach capable ofworking with data acquired in the wild. Our approachleverages the 3D face structure from a single 2D imageand compares it to a reference model for obtaininga compact representation of face features deviations.This descriptor is subsequently deformed using a ’mea-sure locally, weight globally’ strategy to resemble thecaricature drawing process. The deformed deviationsare incorporated in the 3D model using the Laplacianmesh deformation algorithm, and the 2D face cari-cature image is obtained by projecting the deformedmodel in the original camera-view. To demonstratethe advantages of caricature-based face recognition, wetrain the VGG-Face network from scratch using eitheroriginal face images (baseline) or caricatured images,and use these models for extracting face descriptorsfrom the LFW, IJB-A and MegaFace datasets. The ex-periments show an increase in the recognition accuracywhen using caricatures rather than original images.Moreover, our approach achieves competitive resultswith state-of-the-art face recognition methods, evenwithout explicitly tuning the network for any of theevaluation sets. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018 2018-01-01T00:00:00Z 2020-02-10T14:12:01Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.6/9171 |
url |
http://hdl.handle.net/10400.6/9171 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1109/TIFS.2018.2846617 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799136385865613312 |