N. Petkov

Nicolai Petkov

News | Research | Publications | Programs and data sets | Vacancies | Governance | Press | Hobbies

News from university governance

I am candidate for a new term in the University Council (elections 15-19 May).
You can read more on this here.

News from research

For a comprehensive list of news, see the news page of my research group http://www.cs.rug.nl/is/News/News.


I am head of the Intelligent Systems research group.

Big data and financial modelling

We designed a method that helps a big international bank recognise automatically in an early phase who among the delayers of mortgage rate payments will default. Early recognition is important because banks need to reserve certain capital in such cases and timely arrangements with clients may reduce the overall amount. The method and its computer implementation are in use at the concerned bank since mid-2013 and led to large reduction of operation costs [Sun et al., 2014]. No further disclosure can be done at this moment but if you represent a bank of another financial institution and are interested in collaboration, you are welcome to contact me.
Financial markets generate huge amounts of data. I apply pattern recognition and machine learning techniques to identify stocks that are likely to out- or underperform the market indexes. I am interested in collaboration with fund managers and investors regarding the development and application of algorithms for investment and trading decisions.

Brain-inspired computer vision, pattern recognition and machine learning

This research concerns computer simulations of the visual system of the brain and development of brain-inspired computer vision, pattern recognition and machine learning algorithms.

A neural mechanism in areas V1 and V2 of visual cortex, known as surround suppression or non-classical receptive field inhibition, gave inspiration for a texture suppression algorithm that improves the detection of object contours in cluttered scenes. more...
An algorithm inspired by the function of a specific type of shape-slective neuron in area V4 of visual cortex is very effective in the detection of vascular bifurcations in retinal fundus images. more...

Computer applications in medicine, health care and life sciences

Content-based image retrieval and expert systems for dermatology
In a joint project with the Department of Dermatology of the University Medical Center Groningen and the Netherlands Association for Dermatology and Vennerology we develop an automatic diagnosis support system that deploys content-based image retrieval and other intelligent systems techniques.

Pattern recognition in ophthalmology
Retinal funds images give a unique opportunity to take a non-invasive look at the state of the vascular system of people. The analysis of the retinal vascular tree can reveal increased risks for cardio-vascular diseases. We replace a tedious manual process by automatic computer analysis. more...

Computer support for schizophrenic patients
In a joint project with the group Distributed Systems and the Department of Psychiatry we create a system that will help schizophrenic patients and their families.

Computers for artistic expression and creative industries

We want to help people express themselves artistically - you only need a digital camera and a computer program, try these:

Water color more... Van Gogh more 1... more 2... more 3...

Parallel computing

In the past, my research concerned the development of systolic algorithms. I wrote two monographs on this topic.


Best cited | Books | Editted books | Journals | Conferences | Chapters in books and other publications | Programs and image data sets


If you have a fellowship/scholarship/stipend or intend to apply for one, then you may contact me. On 1 September 2016, the University of Groningen will start with a new PhD scholarship programme, read more here.

Last changed: 2017-05-12.