At the University of Groningen he was head of the divisions High Performance Computing and Imaging, and Intelligent Systems (1991-2000, resp.
Nicolai Petkov's initial research in the 1980s and early 1990s was in the field of systolic parallel algorithms.
In this area he considers as most valuable his and his students' work on the computational modeling of non-classical receptive field inhibition (also known as surround suppression) in neural cells in the visual cortex.
It led to the development of more effective computer vision algorithms for various industrial, medical and other applications.
His further work was/is for the development of pattern recognition and machine learning algorithms for various types of data: image, video, audio, and time series with applications in robotics, manufacturing, agricultural industry, medicine, finance, etc.