- Blind image /video quality assessment
- Image Forensics
- Iris Recognition Systems
Blind image and video quality assessment
Images and videos are subject to a variety of distortions during acquisition, processing, compression, transmission, and reproduction. Designing objective image quality assessment methods are not only to monitor image quality degradation and to benchmark image processing systems but also to optimize many image processing algorithms and systems.
Humans are sensitive to image distortions and can effortlessly identify image distortions without any information about the pristine version. Developing objective methods to emulate this human ability is the main goal of blind or no-reference image quality assessment.
Quality of iris images acquired under visible light
Since the stability of the iris patterns over a human lifetime and their uniqueness were noticed in 1987, the use of iris images increased for identifications and authentications in biometric security applications. Most of the commercially available iris recognition systems use near infrared (NIR) images, but due to the popularity of consumer cameras, iris recognition systems using images acquired under visible light by smartphones were introduced. Iris Image quality is a key factor that affects the performance of iris recognition systems.
My research directed to propose a method to consider the quality of the iris image on the iris recognition pipeline.
Blind image forgery detection
Today, the growing popularity of smartphones and social media has increased the use of digital photography over the past few years. News agencies, courts, and Police use the visual information captured by an eyewitness citizens as key pieces of evidence. This trend and available software’s for image manipulating opens the door for digital images forgery. This poses many challenges for verification of the authenticity and integrity of a digital media from unknown sources in absence of any prior digital watermarking or authentication technique.
My research in this area is directed to explore the ability to detect images manipulated by a copy-move forgery method.
|2017/2018 Winter||Introduction to Applied Scientific Computing with MATLAB||Course Information|
|since 10/2016||Research assistant, Department of Computer and Information Science, University of Konstanz, Germany.|
|03/2016 - 10/2016||Researcher, Norwegian Colour and Visual Computing Laboratory, Faculty of Computer Science and Media Technology, Norwegian University of Science and Technology (NTNU), Norway.|
|09/2012 - 03/2016||Research assistant, Faculty of Computer Science and Engineering, Shahid Beheshti University (SBU), G. C, Tehran, Iran.|
|09/2009- 02/2012||Master of Science in Computer Engineering- Artificial Intelligence, Faculty of Computer Science and Engineering, Shahid Beheshti University (SBU), G. C, Tehran, Iran.|