ICAO Face Normalization and Analysis

The goal of this project is the research and development of state of the art computer vision and object recognition algorithms to analyze face portrait images according to the ICAO (International Civil Aviation Organization) standards and specifications. Therefore a close cooperation with Siemens IT Solutions and Services Biometric Center in Graz exists, where the Biometry group is developing a software solution for this purpose.

Current passports issued in the European Union contain biometric data like e.g. digital photographs and fingerprints in order to uniquely identify its owner. To be able to read passports all over the world, the ICAO has specified a number of guidelines and requirements for the structure of these biometric features. In case of face portrait images, examples for these requirements are neutral appearance, eyes opened, mouth closed, frontal pose, straight-looking eyes, properly-sitting eye-glasses, or uncovered faces. Since these analysis steps have to be performed in an automatic fashion, each of these requirements imposes certain computer vision research challenges which are tackled in this research project. Examples for the topics involved in these analysis steps are model-based segmentation using active shape and active appearance models, fast and robust AdaBoost based machine learning algorithms for face and face component detection, or classification of facial expressions using multi-classifier fusion approaches.

CONTACT - RESEARCHERS

Markus Storer

Markus Storer

Martin Urschler

Martin Urschler

CONTACT - STUDENTS

Martin Hirzer

Martin Hirzer did his master thesis on the fully automatic segmentation of normalized face portrait images using a hybrid segmentation framework combining prior knowledge, a color distribution model and a total variation based boundary delineation.

Paul Urthaler

Paul Urthaler did his master thesis on the segmentation of different types of eyeglasses in the context of ICAO face analysis. Additionally the accordance of different eyeglasses to the ICAO specification was evaluated.

Matthias Straka

Matthias Straka is currently working on his master thesis in the context of head pose estimation from facial images. He is working on the analysis of SIFT and HOG descriptors in the context of a support vector regression for pose estimation.

PUBLICATIONS

  Efficient Robust Active Appearance Model Fitting                
  Markus Storer, Peter M. Roth, Martin Urschler, Horst Bischof , Josef A. Birchbauer        
  Book Communications in Computer and Information Science (CCIS), vol. 68 , Springer-Verlag, 2010 (to appear)  
paper The Active Appearance Model (AAM) is a widely used approach for model based vision showing excellent results. But one major drawback is that the method is not robust against occlusions. Thus, if parts of the image are occluded the method converges to local minima and the obtained results are unreliable. To overcome this problem we propose a robust AAM fitting strategy.
Show Details
 
  Intensity-Based Congealing for Unsupervised Joint Image Alignment                
  Markus Storer, Martin Urschler, Horst Bischof        
  Proc. 20th International Conference on Pattern Recognition (ICPR) , Istanbul, Turkey, 2010 (to appear)  
paper We present an approach for unsupervised alignment of an ensemble of images called congealing.
Show Details
 
  Occlusion Detection for ICAO Compliant Facial Photographs                
  Markus Storer, Martin Urschler, Horst Bischof        
  Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Workshop on Biometrics , San Francisco, USA, 2010 (to appear)  
paper In this work we present a novel algorithm for occlusion detection and evaluate its performance on several databases.
Show Details
 
  Person Independent Head Pose Estimation by Non-Linear Regression and Manifold Embedding                
  Matthias Straka, Martin Urschler, Markus Storer, Horst Bischof, Josef A. Birchbauer        
  Proc. 34th Workshop of the Austrian Association for Pattern Recognition (OAGM), 2010 (to appear)  
paper This paper describes an approach to head pose estimation in passport type images with an emphasis on high accuracy for near-frontal poses as well as person independence.
Show Details
 
  3D-MAM: 3D Morphable Appearance Model for Efficient Fine Head Pose Estimation from Still Images. paper              
  Markus Storer, Martin Urschler, Horst Bischof        
  Proc. International Conference on Computer Vision (ICCV), Workshop on Subspace Methods, Kyoto, Japan, 2009  
paper We present a novel 3D head pose estimation approach, which utilizes the flexibility and expressibility of a dense generative 3D facial model in combination with a very fast fitting algorithm.
Show Details Download Paper
 
  Fast-Robust PCA                
  Markus Storer, Peter M. Roth, Martin Urschler, Horst Bischof        
  Proc. 16th Scandinavian Conference on Image Analysis (SCIA), Oslo, Norway, 2009  
paper Principal Component Analysis (PCA) is not robust against outliers. Hence, we propose a novel fast and robust PCA (FR-PCA) algorithm.
Show Details
 
  An Automatic Hybrid Segmentation Approach for Aligned Face Portrait Images paper              
  Martin Hirzer, Martin Urschler, Horst Bischof, Josef A. Birchbauer        
  Proc. 33rd Workshop of the Austrian Association for Pattern Recognition (OAGM), Stainz, Austria, 2009  
paper In this work a fully automatic facial image segmentation algorithm working on ICAO normalized face images is presented. We make use of prior geometric, color and texture regional as well as edge information in a variational framework.
Show Details Download Paper
 
  Robust Facial Component Detection for Face Alignment Applications paper              
  Martin Urschler, Markus Storer, Horst Bischof, Josef A. Birchbauer        
  Proc. 33rd Workshop of the Austrian Association for Pattern Recognition (OAGM), Stainz, Austria, 2009  
paper In this work we present a robust facial component detection framework for identifying face and eyes in arbitrary image in order to perform ICAO compliant face normalization.
Show Details Download Paper
 
  Active Appearance Model Fitting Under Occlusion Using Fast-Robust PCA paper   videos          
  Markus Storer, Peter M. Roth, Martin Urschler, Horst Bischof, Josef A. Birchbauer        
  Proc. International Conference on Computer Vision Theory and Applications (VISAPP), Lisbon, Portugal, 2009  
paper One of the major drawbacks of Active Appearance Model (AAM) fitting is its non-rubustness against occlusions. The main idea is to apply a robust PCA model to reconstruct the missing feature information and to use the thus obtained image as input for the standard AAM fitting process.
Show Details Download Paper
 
  Classifier Fusion for Robust ICAO Compliant Face Analysis paper              
  Markus Storer, Martin Urschler, Horst Bischof, Josef A. Birchbauer        
  Proc. IEEE International Conference on Automatic Face and Gesture Recognition (FG), Amsterdam, The Netherlands, 2008  
paper Fusing several classifiers leads to a more robust classfication result. Some fusion strategies are evaluated for the determination of eyes-open and mouth-closed status for arbitrary facial images.
Show Details Download Paper
 
  On Combining Classifiers for Assessing Portrait Image Compliance with ICAO/ISO Standards                
  Markus Storer, Martin Urschler, Horst Bischof, Josef A. Birchbauer        
  Proc. Biometrics and Electronic Signatures (BIOSIG), Darmstadt, Germany, 2008  
paper Evaluation of several classifier combination schemes for checking facial images against parts of the International Civil Aviation Organization (ICAO) criteria.
Show Details
 
  Face Image Normalization and Expression/Pose Validation for the Analysis of Machine Readable Travel Documents                
  Markus Storer, Martin Urschler, Horst Bischof, Josef A. Birchbauer        
  Proc. 32nd Workshop of the Austrian Association for Pattern Recognition (OAGM), Linz, Austria, 2008  
paper We present a face normalization and analysis system implementing several parts of the International Civil Aviation Organization (ICAO) standard. The goal is to prepare automated recognition from travel document photos.
Show Details