KOSTAS TSIRIKOLIAS - R&D Engineer (Informatics)

Personal Data 

    Name:              Kostas Tsirikolias
    Date of birth:    3/2/1965
    Place of birth:  Toronto-Canada
    Family status:  Married, one child

Studies - Education

  • Diploma of Electrical Engineering from Democritus University of Thrace, (HELLAS).
  • Master Thesis "Digital Image Processing".
  • PhD "Statistical Pattern Recognition".

Languages

  • Greek
  • English

Work Experience

  • Senior R&D Engineer of Daedalus Informatics, in the fields of image processing and artificial intelligence since 1993.
  • Design and S/W implementation of digital filters.
  • S/W implementation of an O.C.R. system.
  • S/W implementation of special image and video effects.
  • Design of intelligent agents for pattern recognition applications.

Scientific fields of interest

  • Image Processing.
  • Pattern Recognition.
  • Digital Filters Signal Coding and Compression.
  • Chaos and Fractals.
  • Morphogenetic Fields.
  • Intelligent agents.
  • Statistic and Physics.

Publications

  • Sixteen international scientific conferences.
  • Six international scientific journals.

Participation in International Conferences

  • "Fast Shape Discrimination via One-Dimensional Moments", Proceedings of the 1991 International Conference on Acoustics, Speech and Signal Processing, (ICASSP-91), pp. 2473-2475, Toronto, Canada, May 14-17, 1991.
  • "A New Polygon Approximation Approach for Fast Shape Analysis", Proceedings of the IMACS-IFAC Symposium on Parallel and Distributed Computing in Engineering Systems, pp. 257-261, Corfu, Hellas, June 23-28, 1991.
  • "Shape Discrimination Using Neural Networks", Proceedings of the IMACS-IFAC Symposium on Parallel and Distributed Computing in Engineering Systems, pp. 393-397, Corfu, Hellas, June 23-28, 1991.
  • "Logic Filters in Image Processing", Proceedings of the International Conference on Digital Signal Processing, pp. 285-287, Florence, Italy, September 4-6, 1991.
  • "The Use of One Dimensional Moments for Efficient Shape Discrimination Techniques with Applications to Industrial Objects", Proceedings of the International Conference on DSP Applications and Technology, pp. 847-857, Berlin, Germany, October 28-31, 1991.
  • "Edge Extraction and Enhancement with Coordinate Logic Filters Using Block Represented Images", Proceedings of the Twelfth European Conference on Circuit Theory and Design, ECCTD-95, pp. 1035-1038, Constantinoupolis, August 27-31, 1995.
  • "Image Feature Extraction Using Coordinate Logic Filters", Proceedings of the 13th International Conference on Digital Signal Processing, pp. 295-298, July 2-4, 1997, Santorini, Hellas.

Papers

    COORDINATE LOGIC FILTERS IN IMAGE PROCESSING
    In this paper we present a method for image feature extraction and compression using Coordinate Logic Filters. Coordinate Logic Filters constitute a new kind of non linear filters which are closely related to morphological filters. The key issue to the coordinate logic analysis of images is the method of fast successive filtering and managing of the residues. The desired processing is succeeded by executing only direct logic operations among the pixels of the given image. The Coordinate Logic Filters can be easily and fast implemented using logic circuits or cellular automata.

    STATISTICAL SHAPE DISCRIMINATION AND CLUSTERING USING AN EFFICIENT SET OF MOMENTS
    This paper refers to the use of a modified set of moments for the development of efficient shape discrimination and classification techniques. These moments may be applied in general for the discrimination of other patterns as well, such as geological , medical, and robotic vision signals. A new set of efficient set of moments is introduced, which is invariant under rotation translation and scale of the image. These moments are normalized with respect to standard deviation, they appear to have better classification performance over the existing sets of moments, and they are less sensitive to noise. Application of the proposed technique to the classification of silhouettes of airplanes is given. The discrimination of an unknown shape is achieved by testing a weighted least square function.

    CREATION OF FRACTAL FORMS USING COORDINATE LOGIC OPERATIONS
    In this paper we present a new method for the creation of Sierpinsky forms as well as other fractal forms. The specific method is based on the execution of Coordinate Logic Operations. Application of the proposed method to the creation of various fractal and life forms is given. [FRACTAL MODELING USING COORDINATE LOGIC FILTERS - http://www.daedalus.gr/jsauxilpublic/CLF-.pdf],
    COORDINATE LOGIC FILTERS: Theory and Applications in Image Analysis - http://www.daedalus.gr/jsauxilpublic/CLTsMertzios&Tsirikolias/CLTs-Theory_and_Applications_in_Image_Analysis.pdf