Erkut Erdem, Ph.D


Erkut Erdem obtained his B.Sc., M.Sc., and Ph.D. degrees from our department. He received his Ph.D. in 2008, on “Simultaneous Bottom-up/Top-down Processing in Early and Mid Level Vision” and is continuing his academic pursuits at Telecom ParisTech. His current research is about about the computational aspects of visual perception.

Erkut worked as a Teaching Research Assistant in our department throughout his graduate studies and assisted in Dynamic Systems, Image Processing, Scientific Computing, and Algorithms and Data Structures courses. He was an Invited Researcher in Virginia Polytechnic Institute and State University, Virginia, USA (2004), and in Department of Mathematics at the University of California, Los Angeles, USA (2007).

Erkut's reserach interests are primarily in Computer Vision and Image Processing.
In particular, he explores various ways of enriching computer vision modules with a capacity to learn and exploit high-level knowledge. Methodologically, he is interested in unified formulations where bottom-up and top-down processing take place simultaneously.
The projects that he is currently working on include visual tracking, skeleton based analysis of natural images, image smoothing and image segmentation.

Selected Publications

  1. E. Erdem and S. Tari, Mumford-Shah Regularizer with Contextual Feedback, Journal of Mathematical Imaging and Vision, Vol. 33, No. 1, pp. 67-84, January 2009.
  2. C. Aslan, A. Erdem, E. Erdem and S. Tari, Disconnected Skeleton: Shape at its Absolute Scale, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 30, No.12 pp. 2188-2203, December 2008.
  3. A. Erdem, E. Erdem, V. Atalay and A. E. Çetin, Vision-based Continuous Graffiti-like Text Entry System, Optical Engineering, Vol. 43, Issue 3, pp. 553-558, March 2004
people/alumni/erkut/index.txt · Last modified: 2010/05/24 16:04 (external edit)