Projects

1. CADOCT – Maximizing informative content of low quality OCT scans for modern computer-aided diagnostic procedures

 

http://dsp.org.pl/Project_CADOCT/175/

 

http://krzyk87.github.io/OCTAnnotate/

 

The main objectives of the project are:

  • to develop a new method for retina images parameterization
  • to develop tools for detection, segmentation and classification of particular stages of selected vitreoretinal pathologies
  • to devolop methods for super-resolution of OCT datasets
  • to improve the existing approaches by combining eye features into one integrated multilevel hierarchical model.

2. REVEMOD – Modeling three-dimmentional structure of human retina blood vessels

The main objectives of the project are:

  • to develop robust method for precise volumetric segmentation of vessels from a single 3D OCT scan
  • to three-dimentional hierarchical modeling and visualization of retina vascular network
  • to analyse profile of selected vitreoretinal pathologies with regard to the developed model.

3. INDECT (http://www.indect-project.eu)

Intelligent information system supporting observation, searching and detection for security of citizens in urban environment.

 

The INDECT Project aims at developing tools for enhancing the security of citizens and protecting the confidentiality of recorded and stored information. INDECT targets threat detection in both real environments (intelligent cameras) and virtual environments (computer networks, especially Internet).

The main objectives of the INDECT Project are:

  • to develop an intelligent information system for automatic detection of threats and recognition of criminal behavior or violence,
  • to develop new methods and techniques providing tools to support activities of police officers, including tools for threat detection in the Internet; this includes the development of a new type of search engine combining direct search of images and video based on watermarked contents and storage of metadata in the form of digital watermarks,
  • to develop techniques for data and privacy protection in storage and transmission of data based on quantum cryptography and new methods of digital watermarking.

I have worked as a part of a team that took part in Work Package 1 and 7.
My responsibilities:

  • development of iris recognition algirthms,
  • development of algorithms for stereovision impressions,
  • implementation of situation recognition algorithms based on multiple sources,
  • research and implementation of computer vision algorithms on Node Station.

4. Polish Platform for Homeland Security (http://www.ppbw.pl)

My responsibilites:

  • development of algorithms for speaker recognition systems with GMM and MFCC, research on the influence of silence removal algorithms on speaker recognition,
  • creation emergency calls databese for research purposes,
  • creation database of short polish sequences,
  • transcription of emergency calls.

5. Compact Portable System for Knee Rehabilitation

  • construction and testing of one of the prototypes of the knee rehabilitation manipulator,
  • testing of algorithms for manipulators with elastic joint.