Signal Processing

Signal Processing

Aytül Erçil
Aytül Erçil *

Research in Computer Vision and Pattern Recognition areas aim to automatically classify a given image or signal, such as the object in an image.

Our research activities include:

  • Invariant object recognition (Recognizing objects reliably using features extracted from the training image even under changes in image scale, noise and illumination. )
  • Activity monitoring (real time tracking, action recognition, exercise monitoring, fall detection)
  • Texture analysis (analyze spatial arrangement of color or intensities in an image or selected region of an image for defect inspection of textured surfaces, automatic assembly of puzzles)

VPALAB – Computer Vision and Pattern Analysis Laboratory has been selected as a potential center of excellence by the European Union and our work on 3D scanning of specular surfaces received first price in 1st Machinery and Parts Production Technologies award

Mehmet Keskinöz
Mehmet Keskinöz

Multimedia Security and Information Hiding

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; Multimedia Security and Information Hiding
  • 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

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.

Further Information
Müjdat Çetin
Müjdat Çetin
Statistical Signal and Image Processing
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.

Further Information