Home Działalność badawcza Zespoły badawcze Biometric Recognition Team

Biometric Recognition Team

ROIThe Institute of Control and Information Engineering has been actively conducting research in the
field of image processing and analysis for a long time. The research team focuses on developing of
image processing algorithms applications for biometrics, medical imaging, robotics and control.

The main fields of interest

• Detection and recognition of faces
• Statistical shape models to extract the shapes of faces and their parts
• Statistical classifiers in the context of the face recognition based on facial feature shape
• Biometric recognition based on the vein patters
• Liveness detection by tracking the pupils contractions
• Analysis of face surface in response to active lighting system

 

Group Members

• Andrzej Kasinski, professor (team leader, head of CIE)
• Andrzej Florek PhD
• Paweł Drapikowski PhD
• Robert Baczyk PhD
• Adam Schmidt MSc
• Marek Kraft MSc
• Rafał Kabacinski (PhD student)
• Mateusz Kowalski(PhD student)
• MScs students

 

Projects and applications

The PUT Face databaseLandmarksContours

– gathered from 100 people
– almost 1000 high-resolution images
– taken in semi-controlled environment
– manually annotated positions of face, eyes, nose
and mouth
– over 2000 images annotated with a 196-pointcontour model
– publicly available at https://webmail1.cie.put.poznan.pl/biometrics
Has been used by over 180 institutions!

 

Near infrared image acquisition system

org

Zdjcie367_2

– based on low cost standard USB camera
– modular construction
– changeable lightning section
– suitable for palm, and wrist acquisition
– quasi-rigid positioning systems


 

Selected publications

1. M.Król, A.Florek, Comparision of Statistical Classifiers as Applied to the Face recognition
System Based on Active Shape Models, Proceedings of the 4th International Conference on
Computer Recognition Systems CORES’05, Advances in Soft Computing, Springer-Verlag
Berlin Heidelberg, 2005, pp. 791-797.
2. Kasinski A., Schmidt A., The Architecture of the Face and Eyes Detection System Based on
Cascade Classifiers, Advances in Soft Computing, vol. 45, Springer, 2007, pp. 124-131.
3. Schmidt A., Kasinski A., The Performance of the Haar Cascade Classifiers Applied to the
Face and Eyes Detection, Advances in Soft Computing, vol. 45, Springer, 2007, pp. 816-823
4. Florek, M.Król, Classifier Selection for Face Recognition Algorithm Based on Active Shape
Model, Proceedings of the Third International Conference on Computer Vision Theory and
Applications, vol. 2, Funchal-Madeira, Portugal, January 22-25, 2008, pp. 276-281.
5. Kasinski A.,Florek A., Schmidt A., The PUT Face Database, Image Processing &
Communication, vol. 13 no. 3-4/ 2008, pp. 59-64
6. Schmidt A., Kasinski A., The Performance of Two Deformable Shape Models in the Context
of the Face Recognition, Lecture Notes in Computer Science, vol. 5337 (International
Conference on Computer Vision and Graphics ICCGV’2008), Springer, 2009 pp. 400-409.
7. Schmidt A., The Comparison of Normal Bayes and SVM Classifiers in the Context of Face
Shape Recognition, Advances in Soft Computing, vol. 57, Springer, 2009, pp. 95-102.
8. Florek, M.Król, Classifier Sensitivity for Boundary Case Testing Set in the Face
Recognition Algorithm Based on the Active Shape Model, , Proceedings of the Fourth
International Conference on Computer Vision Theory and Applications, vol. 2, Lisboa,
Portugal, February5-8, 2009, pp 281-287.
9. Kasinski A., Schmidt A., The Architecture and Performance of the Face and Eyes Detection
System Based on Haar Cascade Classifiers, Pattern Analysis & Applications, Vol. 13, Nr 2,
2010, pp. 197-211
10. Kabacinski R., Kowalski M., Human Vein Pattern Segmentation From Low Quality Images
– A Comparison of Methods , Advances in Soft Computing, vol. 84, Springer, 2010, pp. 105-
112.

Logowanie pracowników



Administracja

Strona jest własnością Politechniki Poznańskiej. W razie pytań, proszę o kontakt z:


Łukasz Matuszczak


pp-put logo_pelne