Research areas

• computer vision problems, such as biometric identification and verification (especially methods of  face recognitnion, detection and localization), application of active models to object localization, motion analysis,
• statistical pattern recognition, in particular classification algorithms based on discriminant analysis and using matrix-structured data
  

Selected publications

• SMIATACZ M., PRZYBYCIEŃ K., A Framework for Training and Testing of Complex Pattern Recognition Systems. IEEE Conference on Signal and Image Processing Applications (ICSIPA 2011), Kuala Lumpur 2011, pp. 198-203.
• SMIATACZ M., Subspace Algorithms for Face Verification. Computer Recognition Systems 4, Advances in Intelligent and Soft Computing vol. 95, Springer Verlag 2011, pp. s. 23-31.
• DEMBSKI J., SMIATACZ M., Modular machine learning system for training object detection algorithms on a supercomputer. Advances in Systems Science, Academic Publishing House EXIT 2010, pp. 353-361.
• SMIATACZ M., SIKORA D., AAM Toolkit: a system for visual object appearance modeling. Advances in Multimedia and Network Information System Technologies, Advances in Intelligent and Soft Computing vol. 80, Springer-Verlag 2010, pp. 121-129.
• SMIATACZ M., Erosion of privacy in computer vision systems. J. Inform., Commun. & Ethics, Soc.**2002 vol. 1 Supplement, pp. 17-22.

      Full list is available here.

Projects

• national research project N N516 367936, Biometric security system for mobile workstations based on face recognition and interface usage analysis, Gdansk University of Technology, 2009-2012 - project leader
• national research project  3 T11C 027 28, Interactive digital library of electronic musical documents, Gdansk University of Technology, 2005-2008 - member of the research team

Functions

• expert for The National Centre for Research and Development
• member of the scientific committee of International Conference on Computer Vision and Graphics ICCVG