Models and methods for precise image analysis

Course description and technical details


  • To improve knowledge of existing methods, as well as practical adaption and use of already developed methods in existing projects (handwritten text recognition, virus particle classification, cancer diagnostics, protein analysis, etc.).
  • To efficiently spread the knowledge to the whole department, and to create a good foundation for development of new ideas.


  • To initiate concrete research tracks which include practical application of the framework of the coverage model to already existing research projects at CBA.
  • To further develop the framework through cooperation.
  • Collaborations initiated will be intensively carried on during the visit, along with the course, which will serve as a discussion platform/idea incubator. The collaborating projects will be continued, with an aim to be brought to some results and conclusions (hopefully, some publications) during the expected additional visit the following year.


  • Nataša Sladoje
  • Joakim Lindblad
  • Cris Luengo Hendriks
  • Robin Strand
  • Erik Wernersson
  • Ida-Maria Sintorn
  • Gustaf Kylberg
  • Anders Brun
  • Alexandra Pacureanu
  • Johan Nysjö

When and where:

  • Course is organized in period September - October 2012.
  • Lectures are kept at the lecture room at CBA according to the schedule.
  • Accomplished and presented (defended) project task, supported by a moderately sized report, is a requirement for earning 3 ECTS credits.

News and announcements

  • The course has started! PDFs with presentation slides are linked in the schedule.
  • Lecture by Johan Nysjö on Thursday 27.
  • Matlab code for "Soft thresholding" added to course material.
  • Anders' abmask code added to course material.
  • Some Matlab/DIPimage code illustrating what Cris talked about is added to course material.
  • Matlab code for refining crisp 2D segmentation (ICIAP2009) added to course material.
  • Matlab code for drawing some simple 2D objects added to course material.
  • Matlab code for perimeter estimation added to course material.
  • Matlab code for energy based coverage segmentation added to course material.
  • Project presentations postponed to Thursday 11th at 10.15!

Course programme and schedule

DateTimeContent Lecturer
Tue, Sept 1110-11Introduction to the courseNataša
 11-12Coverage segmentation methodsJoakim
Wed, Sept 1210-11Coverage segmentation by energy minimizationJoakim
 11-12Feature estimation using coverage representationNataša
Thu, Sept 1310-11Distance measuresNataša
 11-12Coverage model - Examples of ApplicationsJoakim
Mon, Sept 1710-11Orientation in digital images - A tutorial to estimation and representation methodsErik
Tue, Sept 1810-11Sub-pixel Euclidean distance transformRobin
 11-12Precise thresholdingAnders
 13-15Sub-pixel precision measurements using the point-sampling approachCris
Mon, Sept 2410-11 Ida-Maria
 11-12Precise texture measuresGustaf
Tue, Sept 2510-11The necessity of precise image analysis to explore an interconnected 3D cell networkAlexandra 
 11-12Discussion and Project assignmentsAll lecturers and participants
Thu, Sept 2711-12Soft thresholding applied on CT dataJohan 
  Project work is progressing...
Thu, Oct 1110-12Project presentations - OBS new time!All lecturers and participants
  Promising projects are further developed into publications...

Course literature (see also Course material)


  • N. Sladoje and J. Lindblad. The coverage model and its use in image processing.

This is a book chapter that is accepted and will soon appear in Zbornik radova (Collection of Papers), Mathematical Institute of the Serbian Academy of Sciences and Arts, Belgrade, 2012.


Scientific papers which are related to the coverage model, its properties and applications. They are summarized in the main course material, and can be utilized by readers interested in more details.

  • J. Lindblad and N. Sladoje. Coverage Segmentation based on Linear Unmixing and Minimization of Perimeter and Boundary Thickness.
    Pattern Recognition Letters, Vol. 33, No.6, pp. 728-738, 2012. Online
  • S. Dražić, J. Lindblad, N. Sladoje. Precise Estimation of the Projection of a Shape from a Pixel Coverage Representation.
    In Proceedings of the 7th IEEE International Symposium on Image and Signal Processing and Analysis (ISPA), Dubrovnik, Croatia. IEEE, pp. 569-574, 2011. Online
  • F. Malmberg, J. Lindblad, N. Sladoje, and I. Nyström. A Graph-based Framework for Sub-pixel Image Segmentation.
    Theoretical Computer Science, Vol. 412, No. 15, pp. 1338-1349, 2011. Online
  • A. Tanács, J. Lindblad, N. Sladoje, and Z. Kato. Estimation of linear deformations of 3D objects.
    In Proceedings of International Conference on Image Processing (ICIP), Hong Kong, China.
    IEEE, pp. 153-156, 2010. Online
  • N. Sladoje and J. Lindblad. High Precision Boundary Length Estimation by Utilizing Gray-Level Information.
    IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 2, pp. 357-363, 2009. Online
    See also Tech. Rep. 33: Perimeter estimation based on grey level object representation.
  • N. Sladoje, J. Lindblad. Pixel coverage segmentation for improved feature estimation.
    In Proceedings of the 15th International Conference on Image Analysis and Processing (ICIAP),Vietri sul Mare, Italy.
    Lecture Notes in Computer Science, Vol. 5716, pp. 929-938, 2009. Online
  • A. Tanács, C. Domokos, N. Sladoje, J. Lindblad, and Z. Kato. Recovering affine deformations of fuzzy shapes.
    In Proceedings of the 16th Scandinavian Conference on Image Analysis (SCIA), Oslo, Norway.
    Lecture Notes in Computer Science, Vol, 5575, pp. 735-744, 2009. Online
  • J. Chanussot, I. Nyström and N. Sladoje. Shape Signatures of Fuzzy Star-shaped Sets Based on Distance from the Centroid.
    Pattern Recognition Letters, Vol. 26(6), pp. 735-746, 2005. Online
  • N. Sladoje, I. Nyström, and P.K. Saha. Measurements of digitized objects with fuzzy borders in 2D and 3D.
    Image and Vision Computing, Vol. 23, pp 123-132, 2005. Online
  • N. Sladoje and J. Lindblad. Estimation of Moments of Digitized Objects with Fuzzy Borders.
    In Proceedings of International Conference on Image Analysis and Processing (ICIAP2005), Cagliari, Italy.
    Lecture Notes in Computer Science, Vol. 3617, pp. 188-195, 2005. Online

Course material

On separate page.