Publication result detail

Facial image de-identification using active appearance model

KŘÍŽ, P.; PŘINOSIL, J.; ŘÍHA, K.; DUTTA, M.; ISSAC, A.

Original Title

Facial image de-identification using active appearance model

English Title

Facial image de-identification using active appearance model

Type

Paper in proceedings (conference paper)

Original Abstract

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.

English abstract

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.

Keywords

Image reconstruction, Biometrics (access control), Databases, Active appearance model, Robustness, Computational modeling

Key words in English

Image reconstruction, Biometrics (access control), Databases, Active appearance model, Robustness, Computational modeling

Authors

KŘÍŽ, P.; PŘINOSIL, J.; ŘÍHA, K.; DUTTA, M.; ISSAC, A.

RIV year

2018

Released

17.11.2017

Publisher

IEEE

Location

Dehradun, India

ISBN

978-1-5386-1147-0

Book

2017 International Conference on Emerging Trends in Computing and Communication Technologies

Pages from

1

Pages to

5

Pages count

5

URL

https://ieeexplore.ieee.org/document/8280304/

BibTex

@inproceedings{BUT147372,
  author="Petr {Kříž} and Jiří {Přinosil} and Kamil {Říha} and Malay Kishore {Dutta} and Ashish {Issac}",
  title="Facial image de-identification using active appearance model",
  booktitle="2017 International Conference on Emerging Trends in Computing and Communication Technologies",
  year="2017",
  pages="1--5",
  publisher="IEEE",
  address="Dehradun, India",
  doi="10.1109/ICETCCT.2017.8280304",
  isbn="978-1-5386-1147-0",
  url="https://ieeexplore.ieee.org/document/8280304/"
}