Image quality assessment based on visual perception
Event date:  December 4, 2017 4:00 PM  to November 4, 2017 5:00 PM

Talk Abstract

The application and use of multimedia signals such as image, video, and sound have increased immensely in daily-life. These visual signals are contaminated with several varieties of distortions during the acquisition, compression, transmission and/or display of the signal on screens. The human vision is the ultimate receiver of these multimedia signals. Consequently, visual perception based image quality assessment (IQA) and just noticeable difference (JND) have become important as they can predict the signal quality and highlight the regions of importance which are compatible with human vision. With this view, we will discuss the modelling of human vision based on how it perceives information from visual signals. Our goal is to discuss the properties of human vision with the statistical properties of visual signals for efficient quality assessment of these signals and JND estimation. We will discuss mainly four algorithms 1) a new JND estimation algorithm for images using RMS contrast and feed-back mechanism, 2) the first no-reference IQA algorithm for 3D synthesized images using local descriptors, 3) a reduced-reference IQA algorithms for screen content images based upon the prediction, and 4) an application of perceptual IQA metrics in forming a generic image reconstruction algorithm which can be applied to several image/video processing applications.


Speaker’s Bio

Vinit Jakhetiya works as an assistant professor in Bennett University, India. His research interests are image and video processing, perceptually motivated image reconstruction, image quality assessment, image and video coding, and visual perception.

Previously, he was working as a senior engineer (R & D) in the Hong Kong Applied Science and Technology Research Institute (ASTRI), where his topic of research was image processing and 3D reconstruction. Before that, he was working as a project officer in the School of Computer Engineering, Nanyang Technological University ( NTU), Singapore. He was working with Prof. Weisi Lin and his research areas were visual perception, application of visual perception for image processing and medical imaging. From 2011-2016, he was working as the PhD candidate in the Department of Electronics and Computer Engineering, Hong Kong University of Science and Technolgy (HKUST), Hong Kong. He was a member of the Multimedia Technology Research Center (MTREC) of HKUST, under supervision of Prof. Oscar C. Au and Prof. Matthew Mckay. He did his undergraduate studies from The LNM Institute of Information and Technology (LNMIIT), Jaipur, India. During his stay at LNMIIT, he worked under the guidance of Prof. Anil Kumar Tiwari (Currently working with the Indian Institute of Technology, Jodhpur, Rajasthan) for a period of two and half years.

More information on https://sites.google.com/view/vinitjakhetiya/home


Location

University of Konstanz, Universitätsstr. 10, Konstanz
Powerwall C202

University of Stuttgart, VISUS-Building, Allmandring 19, Vaihingen
Powerwall Room -01.116 (Live Transmission)