Prof. Dr. Marek R. Ogiela

Head of CCI Research Group

 
e-mail: mogiela at agh.edu.pl
e-mail: mogiela at up.krakow.pl
web: home.agh.edu.pl/~mogiela

The members of Laboratory conduct research in the field of cryptography and application of cognitive methods in analysis of image data.

GDL (Gesture Description Language)

GDL (Gesture Description Language) is semantic classifier with syntactic description of gestures. The very heart of our method is an automated reasoning module. It performs forward chaining reasoning (similar to that of a classic expert system) with its inference engine any time new portion of data arrives from the feature extraction library. All rules of the knowledge base are organized in GDL scripts which are text files that are parsed with a context-free grammar. See official website of GDL project.


Teaching aids available for download - GDL application in computer games

Field of Judgement is an open source two-player 3D shooter game that uses Kinect-based interface. This application is a good illustration of application of GDL technology to body movements recognition.


Crypto-biometric - generating the bundles of keys

We are developing novel algorithms able to generate bundles of keys basing on biometric data

Detecting and describing pathological changes in dynamic perfusion computed tomography brain maps

We introduced a novel method of detecting and describing pathological changes that can be visualized on dynamic computed tomography brain maps (CTP). The solution is consisted of asymmetry detection algorithm, two-dimensional brain atlas and rule-based algorithm for ischemia evaluation prognosis.


Segmentation and visualization of tubular structures in computed tomography angiography

We conduct researches on filtering algorithms for detecting tubular structures (veins / arteries) in three-dimensional medical images, especially in carotid artery bifurcation region


Real-time direct volume rendering

The implementations of our direct volume rendering algorithms supplies applications with high quality visualization of discrete scalar field data (for example computed tomography volumes) on consumers hardware in real-time.
Lately we have proposed remote direct volume rendering protocol for mobile devices (cell phones, tablets, etc.) with Android OS.


Augmented reality technology

Augmented reality (AR) is a technology that allows the real time fusion of computer generated digital content with the real world. In our system AR together with real-time direct volume rendering is used as intuitive interface that enable easy and reliable manipulation of visualized objects (for example medical volumetric data).


Syntactic patterns recognition - random graphs

We make a theoretical studies in the area of the syntactic methods helpful for representation and analysis a high-complicated structural patterns. We are developing an approach basing on random IE graphs where two-layer graph structures and two-level graph grammars are used. Our solutions concerns both parsing and concluding algorithms where some additional statistic (semantic) information is included and taken into consideration. Read paper
Biometrics - handwritten signatures/kanji verification

We concentrate mainly on off-line algorithms (HSV) intended to recognition and verification of handwritten signatures, ideograms or kanji. We introduced an approach using an attributed random IE graphs and stochastic ETPL(k) graph grammars. In developing model we are also trying to utilize a semi-dynamic characteristic of the signing process. Read paper
Teaching aids available for download - XNA technology

DSM - multiplayer shooter game in XNA 4.0. This project was created during students course on Multimedia Netowrk Systems as teaching aid material. This application is a good illustration of applied contemporary computer graphic methods.