Assist. Prof. dr. Luka Šajn
T: +386 1 479 8220
E:Send a message
Office hours: Thursday 2pm
Room: R2.15 - Kabinet

Luka Šajn was born on 24.10.1977 in Ljubljana, Slovenia. He finished his PhD studies from the University of Ljubljana in 2007 with the thesis "Multi-resolution parametrization for texture classification and its application in analysis of scintigraphy images". His research interests are in: automating medical report’s classification, cell counting, multi-resolution pattern parametrization, ischaemic heart-disease diagnosing from scintigraphic images and whole-body bone scintigraphy segmentation. Currently he is a researcher and an assistant professor at the same faculty.

Activities and Events


Multi-resolution parametrization for texture classification and its application in analysis of scintigraphy images

The dissertation contributes to the new approaches in the major area of computer science, specifically in the domain field of machine learning, computer vision, texture parametrization and intelligent data analysis in medical applications. 
In the dissertation multiresolutional texture parametrization is addressed and the original algorithm ARes for finding more informative resolutions in the sense of classification accuracy is proposed. ARes is designed to be used in combination with the existing parametrization algorithm ArTex developed by Bevk (2005). The results obtained using the ArTex parametrization algorithm in combination with ARes are compared with standard parametrization methods such as Gabor filters, Haar and Laws wavelets and Image Processor. 
Our study explores the multiresolutional texture parametrization approach based on the image content with regard to the parametrization quality, especially in case of the ArTex algorithm. The tested parametrization algorithms (geometric algorithms, signal processing methods and statistical methods) using multiresolutional approach have demonstrated significant improvements in results over one scale parametrization. This supports the hypothesis that the resolution selection is important for texture parametrization. The developed algorithm ARes in combination with the ArTex algorithm has shown to be an appropriate tool as it achieves statistically significant improvements over single resolution and also over equidistant resolutions. The algorithm ARes in many cases also improves the performance of other parametrization algorithms in comparison to single resolution approach, whereas compared to the equidistant resolution approach it usually shows no significant improvement. We have confirmed that the use of the equidistant resolution space when parameterizing textures significantly outperforms the use of the exponential resolution space, which is used by majority of authors.
For the multiresolution parametrization applicative domain two medical cases have been used, sequential diagnostics of coronary artery disease and diagnostics of whole-body bone scintigraphy.

Past projects

Simon Knez, Luka Šajn, "Food object recognition using a mobile device : evaluation of currently implemented systems", Trends food sci. technol., vol. 99, str. 460-471, May 2020

Luka Šajn, "Automatic localization of white spot lesions caused by teeth braces", IPSI BGD Trans. Internet Res., vol. 15, no. 2, str. 1-11, Jul. 2019

Aleš Jaklič, Franc Solina, Luka Šajn, "User interface for a better eye contact in videoconferencing", Displays, vol. 46, str. 25-36, Jan. 2017

Žiga Zupanec, Fabio Ricciato, Luka Šajn, "Trajectory estimation of a moving target from Ultra-wideband ranging measurements", Elektrotehniški vestnik, letn. 83, št. 5, str. 236-242, 2016

Aleš Jaklič, Luka Šajn, Gašper Derganc, Peter Peer, "Automatic digitization of pluviograph strip charts", Meteorol. appl., vol. 23, no. 1, str. 57-64, Jan. 2016

Jasna Lojk, Uroš Čibej, David Karlaš, Luka Šajn, Mojca Pavlin, "Comparison of two automatic cell-counting solutions for fluorescent microscopic images", J. Microsc. (Oxf.), vol. 260, no. 1, str. 107-116, 2015

Luka Šajn, Simon Knez, "Food object recognition using a mobile device : state of the art", V: New trends in image analysis and processing - ICIAP 2015 workshops : ICIAP 2015 International Workshops, BioFor, CTMR, RHEUMA, ISCA, MADiMa, SBMI, and QoEM, Genoa, Italy, September 7-8, 2015

Peter Peer, Aleš Jaklič, Luka Šajn, "A computer vision based system for a rehabilitation of a human hand", Period. biol., vol. 115, no. 4, str. 535-544, 2013

Luka Šajn, Matjaž Kukar, "Image processing and machine learning for fully automated probabilistic evaluation of medical images", Comput. methods programs biomed., vol. 104, no. 3, str. 75-86, Dec. 2011

Matjaž Kukar, Luka Šajn, "Improving probabilistic interpretation of medical diagnoses with multi-resolution image parameterization : a case study", Springer, cop. 2009, str. 136-145

Matjaž Kukar, Luka Šajn, "Supporting diagnostics of coronary artery disease with multi-resolution image parameterization and data mining", V: Computer vision/Computer graphics collaboration techniques : 4th International Conference, Mirage 2009, Rocquencourt, France, May 4-6, 2009

Luka Šajn, Igor Kononenko, "Multiresolution image parametrization for improving texture classification", EURASIP J. Adv. Signal Process. (Print), vol. 2008

Matjaž Kukar, Luka Šajn, Ciril Grošelj, Jera Grošelj, "Multi-resolution image parametrization in stepwise diagnostics of coronary artery disease", V: Artificial intelligence in medicine : proceedings, 11th Conference on Artificial Intelligence in Medicine, AIME 2007, Amsterdam, The Netherlands, July 7-11, 2007

Luka Šajn, Igor Kononenko, Metka Milčinski, "Computerized segmentation and diagnostics of whole-body bone scintigrams", Comput. med. imaging graph., vol. 31, no. 7, str. 531-541, 2007

Luka Šajn, Matjaž Kukar, Igor Kononenko, Metka Miličinski, "Automatic segmentation of whole-body bone scintigrams as a preprocessing step for computer assisted diagnostics", V: Artificial intelligence in medicine : proceedings, 10th Conference on Artificial Intelligence in Medicine, AIME 2005, Aberdeen, UK, July 23-27, 2005

Luka Šajn, Matjaž Kukar, Igor Kononenko, Metka Miličinski, "Computerized segmentation of whole-body bone scintigrams and its use in automated diagnostics", Comput. methods programs biomed., vol. 80, no. 1, str. [47]-55, 2005