Matching caricatures to photographs

Bahri Abaci; Tayfun Akgul

doi:10.1007/s11760-015-0819-8

Matching caricatures to photographs

Bahri Abaci^*, Tayfun Akgul

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Istanbul Technical University

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

Abstract

Facial caricatures are informative funny images that allow us to identify a subject even with a few lines and dots. Matching caricatures to photographs is a challenging cross-modal face matching problem. This paper addresses this problem by defining a set of qualitative face features both for caricatures and photographs where features are automatically extracted from photos and manually labeled in caricatures. Additionally we release a publicly available caricature-photograph database with 200 caricatures and corresponding photomates. In our experiments, we use genetic algorithms and logistic regression and achieve over (Formula presented.) recognition rate at 0.1 false accept rate.

Original language	English
Pages (from-to)	295-303
Number of pages	9
Journal	Signal, Image and Video Processing
Volume	9
DOIs	https://doi.org/10.1007/s11760-015-0819-8
Publication status	Published - 1 Dec 2015

Bibliographical note

Publisher Copyright:
© 2015, Springer-Verlag London.

Funding

This work is supported by The Scientific and Technological Research Council of Turkey (TUBITAK), Project No: 112E142. The authors would like to thank Anil Jain, Brendon Klare, Serhat Bucak and Mehmet Kerem Turkcan for their interest, initial help and contribution.

Funders	Funder number
TUBITAK	112E142
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Caricature recognition
Facial attributes
Genetic algorithms

Access to Document

10.1007/s11760-015-0819-8

Cite this

@article{a1c2e4c1782445448b3a36fc2d6dfc0a,

title = "Matching caricatures to photographs",

abstract = "Facial caricatures are informative funny images that allow us to identify a subject even with a few lines and dots. Matching caricatures to photographs is a challenging cross-modal face matching problem. This paper addresses this problem by defining a set of qualitative face features both for caricatures and photographs where features are automatically extracted from photos and manually labeled in caricatures. Additionally we release a publicly available caricature-photograph database with 200 caricatures and corresponding photomates. In our experiments, we use genetic algorithms and logistic regression and achieve over (Formula presented.) recognition rate at 0.1 false accept rate.",

keywords = "Caricature recognition, Facial attributes, Genetic algorithms",

author = "Bahri Abaci and Tayfun Akgul",

note = "Publisher Copyright: {\textcopyright} 2015, Springer-Verlag London.",

year = "2015",

month = dec,

day = "1",

doi = "10.1007/s11760-015-0819-8",

language = "English",

volume = "9",

pages = "295--303",

journal = "Signal, Image and Video Processing",

issn = "1863-1703",

publisher = "Springer London",

}

TY - JOUR

T1 - Matching caricatures to photographs

AU - Abaci, Bahri

AU - Akgul, Tayfun

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Facial caricatures are informative funny images that allow us to identify a subject even with a few lines and dots. Matching caricatures to photographs is a challenging cross-modal face matching problem. This paper addresses this problem by defining a set of qualitative face features both for caricatures and photographs where features are automatically extracted from photos and manually labeled in caricatures. Additionally we release a publicly available caricature-photograph database with 200 caricatures and corresponding photomates. In our experiments, we use genetic algorithms and logistic regression and achieve over (Formula presented.) recognition rate at 0.1 false accept rate.

AB - Facial caricatures are informative funny images that allow us to identify a subject even with a few lines and dots. Matching caricatures to photographs is a challenging cross-modal face matching problem. This paper addresses this problem by defining a set of qualitative face features both for caricatures and photographs where features are automatically extracted from photos and manually labeled in caricatures. Additionally we release a publicly available caricature-photograph database with 200 caricatures and corresponding photomates. In our experiments, we use genetic algorithms and logistic regression and achieve over (Formula presented.) recognition rate at 0.1 false accept rate.

KW - Caricature recognition

KW - Facial attributes

KW - Genetic algorithms

UR - http://www.scopus.com/inward/record.url?scp=84947487006&partnerID=8YFLogxK

U2 - 10.1007/s11760-015-0819-8

DO - 10.1007/s11760-015-0819-8

M3 - Article

AN - SCOPUS:84947487006

SN - 1863-1703

VL - 9

SP - 295

EP - 303

JO - Signal, Image and Video Processing

JF - Signal, Image and Video Processing

ER -

Matching caricatures to photographs

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this