Generating various composite human faces from real 3D facial
images

J 2017

Generating various composite human faces from real 3D facial images

CHALÁS, Igor, Petra URBANOVÁ, Vojtěch JUŘÍK, Zuzana FERKOVÁ, Marie JANDOVÁ et. al.

Basic information

Original name

Generating various composite human faces from real 3D facial images

Authors

CHALÁS, Igor (703 Slovakia, belonging to the institution), Petra URBANOVÁ (203 Czech Republic, belonging to the institution), Vojtěch JUŘÍK (203 Czech Republic, belonging to the institution), Zuzana FERKOVÁ (703 Slovakia, belonging to the institution), Marie JANDOVÁ (203 Czech Republic, belonging to the institution), Jiří SOCHOR (203 Czech Republic, guarantor, belonging to the institution) and Barbora KOZLÍKOVÁ (203 Czech Republic, belonging to the institution)

Edition

The Visual Computer, Springer-Verlag, 2017, 0178-2789

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 1.036

RIV identification code

RIV/00216224:14330/17:00095856

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1007/s00371-016-1277-1

UT WoS

000398767100005

Keywords in English

Facial composite; 3D face model;Face perception; Crowd simulation; Morphological modification

Abstract

V originále

Generating large human crowds of distinguishable individuals is one of the challenges in the gaming industry. When the scene contains many characters, it becomes impracticable to create all the individual characters manually. However, the requirement for the different appearances of individuals in a crowd, namely their faces, is now in greater demand. Therefore, this paper describes our solution to the automatic generation of human faces that are created as a composite of facial parts of 3D scans of real human faces. However, the user has the possibility to further adjust the composite by designing replacements, leading to a desired appearance. The final composite can be exported and attached to a given avatar. To evaluate the usability of our solution, we performed two case studies. The conducted perception study performed with 104 participants aimed to confirm the decreasing human ability to recognize morphologically modified faces. The morphological study focused on the quantification of the extent of facial modifications. Both studies were performed by domain experts from psychology and anthropology.

Links

MUNI/A/0892/2015, interní kód MU

Name: Výzkum v aplikované informatice na FI MU (Acronym: VAIFIMU)

Investor: Masaryk University, Category A

MUNI/A/0897/2016, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VI.

Investor: Masaryk University, Category A

MUNI/A/1379/2015, interní kód MU

Name: Rozvoj analytických nástrojů pro studium tělesných znaků člověka se zaměřením na analýzu dynamiky pohybu

Investor: Masaryk University, Category A

Files attached

10.1007_s00371-016-1277-1.pdf

Request the author's version of the file

Citovat

CHALÁS, Igor, Petra URBANOVÁ, Vojtěch JUŘÍK, Zuzana FERKOVÁ, Marie JANDOVÁ, Jiří SOCHOR and Barbora KOZLÍKOVÁ. Generating various composite human faces from real 3D facial images. The Visual Computer. Springer-Verlag, 2017, vol. 33, No 4, p. 443-458. ISSN 0178-2789. Available from: https://dx.doi.org/10.1007/s00371-016-1277-1.

@article{1347822,
   author = {Chalás, Igor and Urbanová, Petra and Juřík, Vojtěch and Ferková, Zuzana and Jandová, Marie and Sochor, Jiří and Kozlíková, Barbora},
   article_number = {4},
   doi = {http://dx.doi.org/10.1007/s00371-016-1277-1},
   keywords = {Facial composite; 3D face model;Face perception; Crowd simulation; Morphological modification},
   language = {eng},
   issn = {0178-2789},
   journal = {The Visual Computer},
   title = {Generating various composite human faces from real 3D facial images},
   url = {http://dx.doi.org/10.1007/s00371-016-1277-1},
   volume = {33},
   year = {2017}
}

TY  - JOUR
ID  - 1347822
AU  - Chalás, Igor - Urbanová, Petra - Juřík, Vojtěch - Ferková, Zuzana - Jandová, Marie - Sochor, Jiří - Kozlíková, Barbora
PY  - 2017
TI  - Generating various composite human faces from real 3D facial images
JF  - The Visual Computer
VL  - 33
IS  - 4
SP  - 443-458
EP  - 443-458
PB  - Springer-Verlag
SN  - 01782789
KW  - Facial composite
KW  - 3D face model;Face perception
KW  - Crowd simulation
KW  - Morphological modification
UR  - http://dx.doi.org/10.1007/s00371-016-1277-1
N2  - Generating large human crowds of distinguishable individuals is one of the challenges in the gaming industry. When the scene contains many characters, it becomes impracticable to create all the individual characters manually. However, the requirement for the different appearances of individuals in a crowd, namely their faces, is now in greater demand. Therefore, this paper describes our solution to the automatic generation of human faces that are created as a composite of facial parts of 3D scans of real human faces. However, the user has the possibility to further adjust the composite by designing replacements, leading to a desired appearance. The final composite can be exported and attached to a given avatar. To evaluate the usability of our solution, we performed two case studies. The conducted perception study performed with 104 participants aimed to confirm the decreasing human ability to recognize morphologically modified faces. The morphological study focused on the quantification of the extent of facial modifications. Both studies were performed by domain experts from psychology and anthropology.
ER  -

CHALÁS, Igor, Petra URBANOVÁ, Vojtěch JUŘÍK, Zuzana FERKOVÁ, Marie JANDOVÁ, Jiří SOCHOR and Barbora KOZLÍKOVÁ. Generating various composite human faces from real 3D facial images. \textit{The Visual Computer}. Springer-Verlag, 2017, vol.~33, No~4, p.~443-458. ISSN~0178-2789. Available from: https://dx.doi.org/10.1007/s00371-016-1277-1.

Detailed Information on Publication Record