CERN Computing Seminar

Are All Pixels Equally Important?

by Dr Gökhan Yildirim (EPFL)

Europe/Zurich
31/3-004 - IT Amphitheatre (CERN)

31/3-004 - IT Amphitheatre

CERN

105
Show room on map
Description

When we look at our environment, we primarily pay attention to visually distinctive objects. We refer to these objects as visually important or salient. For efficient visual processing, the human visual system identifies salients objects and dedicates most of its processing resources to them. An analogous resource allocation can be performed by salient-object detection algorithms, which identify objects of interest in an image. Consequently, thanks to salient-object detection, complex visual computing operations can focus on the important parts of the visual data and can save time and resources.

About the speaker

Dr. Gokhan Yildirim is a research assistant in the School of Computer and Communication Sciences (IC) at the École Polytechnique Fédérale de Lausanne (EPFL). His research interests include image understanding, multimedia, pattern recognition, machine learning, salient-object detection on images & videos and its applications on image processing and computer vision. He completed his B.Sc. and M.Sc. degrees in Middle East Technical University (METU) in Turkey and his Ph.D. in EPFL.


Organised by: Maria Dimou and Miguel Angel Marquina
Computing Seminars /IT Department