Facial image de-identification using active appearance model

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F17%3APU127893" target="_blank" >RIV/00216305:26220/17:PU127893 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/25313436:_____/17:N0000001

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8280304/" target="_blank" >https://ieeexplore.ieee.org/document/8280304/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICETCCT.2017.8280304" target="_blank" >10.1109/ICETCCT.2017.8280304</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Facial image de-identification using active appearance model

Popis výsledku v původním jazyce

Nowadays, the task of preservation of personal data present in public audio-visual records becomes more important. This paper describes an image processing method for de-identification of visual personal data based on a facial image. There are many primitive methods with high robustness but image quality of de-identified data is usually very poor. The advantages of this proposed method include especially very good results in quality preservation of the original image data and the possibility of a partial image reconstruction from de-identified data. The main objective has been achieved by using Active Appearance Model algorithm tested on a created database with the overall success rate of automatic recognition tool around 0.8 %. The de-identified image data look also authentic and it is possible to determine the expression or gender of the de-identified person.

Název v anglickém jazyce

Facial image de-identification using active appearance model

Popis výsledku anglicky

Nowadays, the task of preservation of personal data present in public audio-visual records becomes more important. This paper describes an image processing method for de-identification of visual personal data based on a facial image. There are many primitive methods with high robustness but image quality of de-identified data is usually very poor. The advantages of this proposed method include especially very good results in quality preservation of the original image data and the possibility of a partial image reconstruction from de-identified data. The main objective has been achieved by using Active Appearance Model algorithm tested on a created database with the overall success rate of automatic recognition tool around 0.8 %. The de-identified image data look also authentic and it is possible to determine the expression or gender of the de-identified person.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20206 - Computer hardware and architecture

Projekt

<a href="/cs/project/VI20172020105" target="_blank" >VI20172020105: Automatizovaný panoramatický dohledový systém pro ochranu osob a majetku na sportovních stadionech</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2017 International Conference on Emerging Trends in Computing and Communication Technologies

ISBN

978-1-5386-1147-0

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

1-5

Název nakladatele

IEEE

Místo vydání

Dehradun, India

Místo konání akce

Dehradun

Datum konání akce

17. 11. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426970400013