CS Department Colloquium Series Presents
“Blind Image Quality Assessment Using Local Binary Patterns”
Professor Mylène C.Q. Farias
University of Brasilia (UnB)
In recent years, there has been an increase of video-based multimedia services. It is estimated that, in a near future, over 80% of all consumer Internet traffic will be from video. As video traffic increases, so the demand for a better quality of experience. Therefore, the development of efficient real-time quality assessment methods, which can quantify the audio-visual experience (as perceived by the end user), can bring real benefits to Internet Service Providers (ISP) and broadcast companies. Given that the original (reference) is not generally available at the measuring point (receiver), the development of blind (no-reference) quality assessment (NR-IQA) methods is crucial. So far, most efforts have been in the development of full-reference methods and there are still many open questions in the area of NR-IQA. In this talk, we explore the use of local binary patterns (LBP) operators and its variations in the design of fast NR-IQA methods. The proposed methods use machine learning algorithms and texture features extracted by LBPs. We explore several variations of LBP operators to account for the different types of image distortions. Results show that the proposed methodology is competitive in terms of prediction precision and computational complexity.
Mylene C.Q. Farias received her B.Sc. degree in electrical engineering from Federal University of Pernambuco (UFPE), Brazil, in 1995 and her M.Sc. degree in electrical engineering from the State University of Campinas (UNICAMP), Brazil, in 1998. She received her Ph.D. in electrical and computer engineering from the University of California Santa Barbara (UCSB), USA, in 2004 for work in no-reference video quality metrics. Dr. Farias has worked as a research engineer at CPqD (Brazil) in video quality assessment and validation of video quality metrics. She has also worked as an intern for Philips Research Laboratories (The Netherlands) in video quality assessment of sharpness algorithms and for Intel Corporation (Phoenix, USA) developing no-reference video quality metrics. Currently, she is an Assistant professor in the Department of Electrical Engineering at the University of Brasilia (UnB), where she is a member of the Graduate Program in Informatics and of the Graduate Program on Electronic Systems and Automation Engineering (PGEA). Dr. Farias is a researcher of the GPDS and her current interests include video quality metrics, video processing, multimedia signal processing, watermarking, and visual attention. Dr. Farias is a member of IEEE and the IEEE Signal Processing Society.
Date: Tuesday, February 7 2017
Time: 11:00am to 12:00pm
Location: ECSS 2.102 TI Auditorium
Refreshments will be served at 10:45am