An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images

Martin Hirzer, Martin Urschler, Horst Bischof, Josef Alois Birchbauer

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

With the introduction of electronic personal documents (e.g. passports) in recent years the analysis of suitable photographs has become an important field of research. Such photographs for machine readable travel documents have to fulfill a set of minimal quality requirements defined by the International Civil Aviation Organization (ICAO). As some of the specified requirements are related to certain image regions only, these regions must be located in advance. In this work we present an automatic segmentation method for aligned color face images. The method is based on a convex variational energy formulation which is solved using weighted total variation. We apply constraints in the form of prior knowledge about the spatial configuration of typical passport photographs in order to solve for a global energy minimum. Several experiments on face images from two different datasets are presented to evaluate the performance of our algorithm. The obtained results demonstrate that our method is fairly robust and significantly outperforms other methods targeted at the same problem, in particular an expert system and an AdaBoost classifier.
Original languageEnglish
Title of host publicationProceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR)
PublisherÖsterreichische Computergesellschaft
Pages49-60
Publication statusPublished - 2009

Fingerprint

Civil aviation
Adaptive boosting
Expert systems
Classifiers
Color
Experiments

Fields of Expertise

  • Information, Communication & Computing

Cite this

Hirzer, M., Urschler, M., Bischof, H., & Birchbauer, J. A. (2009). An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images. In Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR) (pp. 49-60). Österreichische Computergesellschaft.

An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images. / Hirzer, Martin; Urschler, Martin; Bischof, Horst; Birchbauer, Josef Alois.

Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR). Österreichische Computergesellschaft, 2009. p. 49-60.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Hirzer, M, Urschler, M, Bischof, H & Birchbauer, JA 2009, An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images. in Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR). Österreichische Computergesellschaft, pp. 49-60.
Hirzer M, Urschler M, Bischof H, Birchbauer JA. An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images. In Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR). Österreichische Computergesellschaft. 2009. p. 49-60
Hirzer, Martin ; Urschler, Martin ; Bischof, Horst ; Birchbauer, Josef Alois. / An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images. Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR). Österreichische Computergesellschaft, 2009. pp. 49-60
@inproceedings{3ffc1e3396db4f9ca2b967552fb2a6c1,
title = "An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images",
abstract = "With the introduction of electronic personal documents (e.g. passports) in recent years the analysis of suitable photographs has become an important field of research. Such photographs for machine readable travel documents have to fulfill a set of minimal quality requirements defined by the International Civil Aviation Organization (ICAO). As some of the specified requirements are related to certain image regions only, these regions must be located in advance. In this work we present an automatic segmentation method for aligned color face images. The method is based on a convex variational energy formulation which is solved using weighted total variation. We apply constraints in the form of prior knowledge about the spatial configuration of typical passport photographs in order to solve for a global energy minimum. Several experiments on face images from two different datasets are presented to evaluate the performance of our algorithm. The obtained results demonstrate that our method is fairly robust and significantly outperforms other methods targeted at the same problem, in particular an expert system and an AdaBoost classifier.",
author = "Martin Hirzer and Martin Urschler and Horst Bischof and Birchbauer, {Josef Alois}",
year = "2009",
language = "English",
pages = "49--60",
booktitle = "Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR)",
publisher = "{\"O}sterreichische Computergesellschaft",
address = "Austria",

}

TY - GEN

T1 - An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images

AU - Hirzer, Martin

AU - Urschler, Martin

AU - Bischof, Horst

AU - Birchbauer, Josef Alois

PY - 2009

Y1 - 2009

N2 - With the introduction of electronic personal documents (e.g. passports) in recent years the analysis of suitable photographs has become an important field of research. Such photographs for machine readable travel documents have to fulfill a set of minimal quality requirements defined by the International Civil Aviation Organization (ICAO). As some of the specified requirements are related to certain image regions only, these regions must be located in advance. In this work we present an automatic segmentation method for aligned color face images. The method is based on a convex variational energy formulation which is solved using weighted total variation. We apply constraints in the form of prior knowledge about the spatial configuration of typical passport photographs in order to solve for a global energy minimum. Several experiments on face images from two different datasets are presented to evaluate the performance of our algorithm. The obtained results demonstrate that our method is fairly robust and significantly outperforms other methods targeted at the same problem, in particular an expert system and an AdaBoost classifier.

AB - With the introduction of electronic personal documents (e.g. passports) in recent years the analysis of suitable photographs has become an important field of research. Such photographs for machine readable travel documents have to fulfill a set of minimal quality requirements defined by the International Civil Aviation Organization (ICAO). As some of the specified requirements are related to certain image regions only, these regions must be located in advance. In this work we present an automatic segmentation method for aligned color face images. The method is based on a convex variational energy formulation which is solved using weighted total variation. We apply constraints in the form of prior knowledge about the spatial configuration of typical passport photographs in order to solve for a global energy minimum. Several experiments on face images from two different datasets are presented to evaluate the performance of our algorithm. The obtained results demonstrate that our method is fairly robust and significantly outperforms other methods targeted at the same problem, in particular an expert system and an AdaBoost classifier.

M3 - Conference contribution

SP - 49

EP - 60

BT - Proceedings of the Workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR)

PB - Österreichische Computergesellschaft

ER -