About the Event:
The watershed transform is a popular image segmentation procedure from mathematical morphology used in many applications of computer vision. This work proposes a novel parallel watershed procedure designed for graphics processing unit (GPU) implementation. Our algorithm constructs paths of steepest descent and reduces these paths into direct pointers to catchment basin minima in logarithmic time, also crucially incorporating successful resolution of plateaux. Three implementation variants and their parameters are analysed through experiments on 2D and 3D images; a comparison against the state-of-the-art shows a runtime improvement of around 30%. For 3D images of 128 megavoxels execution times of approximately 1.5–2 seconds are achieved.
About the Speaker:
Varduhi Yeghiazaryan is a doctoral student at the Department of Computer Science, University of Oxford. She received her BSc degree in Applied Mathematics and Informatics from the Russian-Armenian (Slavonic) University in 2012, and her MSc degree in Computer Science from the University of Oxford in 2013. She recently joined the Foundation for Armenian Science and Technology as an Innovation Analyst.