With the fast development of Internet, the need to create, store and distribute the digital multimedia gets more and more increasing. This raises, however, security concerns since multimedia is highly vulnerable to the illegal copying, distribution, manipulations and other attacks. To remedy these security issues, the idea of “the digital watermarking” and “stenography” have been introduced where the secret information is carried over the host signal.For example one can embed;
Road map into the image
Digital signature into the speech to prevent from illegal copying
Logo into the video
The name of the patient into the X-ray reports and MRI Scans
Embed watermark into text document to ensure that it is not changed
In communication theory and technologies (CTT) group at Sabanci, which is supervised by Dr. Keskinoz, conduct research to develop practical and efficient algorithms for the multimedia and information hiding.
Correlation Filter Pattern Recognition for Biometric Verification and Security
Biometric person identification and verification is a promising methodology for authentication applications. However, there are many issues that need to be addressed to ensure the security of biometric templates in biometric authentication systems. One such aspect is the cancelability of a biometric. For example, consider a scenario where a biometric template is stored on a card for authenticating a user. What happens when that card with the user’s biometric template is lost or stolen? How does one cancel the lost or stolen card and re-issue a new biometric card for that person? In order to protect the user’s biometric templates from possible hacking and to ensure cancelability, the templates must be encrypted. Then in case of theft or loss, a different encrypted biometric template can be issued from the same original biometric pattern. Recent work in using advanced correlation filters has shown promise for biometric verification. Correlation filter methods offer advantages such as shift-invariance and graceful degradation.
In communication theory and technologies (CTT) group at Sabanci, which is supervised by Dr. Keskinoz, conduct research to devise new correlation filters and/or techniques based on correlation filters for the purpose of developing secure biometric authentication systems.
Müjdat Çetin is affiliated with the SPIS and VPA Laboratories. His research is focused around the general theme of developing statistically-based methods and algorithms for robust and efficient information extraction from observed uncertain data. His current research spans a wide variety of topics including
inverse problems and computed imaging with applications to radar and biomedical imaging;
sparse signal representation and compressed sensing;
machine learning methods for EEG-based brain-computer and brain-machine interfaces;
image analysis for biomedical and biological data with applications to MR and microscopic images;
image analysis and pattern recognition for defense applications based on airborne and spaceborne remotely sensed data such as synthetic aperture radar imagery.
Dr. Çetin and his students’ research has received several best paper awards in international journals, including the IEEE Signal Processing Society Best Paper Award; the Elsevier Signal Processing Best Paper Award; and the IET Radar, Sonar and Navigation Premium Award.
Machine Learning, Statistical Signal Processing and Computer Vision
Dr. Huseyin Ozkan is currently an assistant professor of electronics engineering and with the Faculty of Engineering and Natural Sciences at Sabanci University. Dr. Ozkan received his B.Sc. degrees in Electrical Engineering and Mathematics from Bogazici University; and his M.Sc. and Ph.D. degrees in Electrical Engineering from Boston University and Bilkent University, respectively. Previously, he had been working as a postdoctoral research associate in Vision and Computational Neuroscience at Massachusetts Institute of Technology. His research interests are in machine learning, signal processing, computer vision and computational neuroscience.