報告題目：JND Modeling: Approaches, Applications, and Research Challenges
報告人：Sos Agaian教授
報告人單位：Dept.of Computer Science, College of Staten Island, City University of New York
報告時間：2019年5月21日（周二）下午16:00
報告地點：教十樓四樓學術(shù)報告廳
個人簡介
Prof. Sos Agaian is a Distinguished Professor of Computer Science at College of Staten Island and the Graduate Center, CUNY. Prior to joining the City University of New York, Dr. Agaian was a Peter T. Flawn Professor of Electrical and Computer Engineering with the University of Texas at San Antonio. His main research interests are in Computational Vision and Machine Learning, Big and Small Data Analytics, Multimodal Biometric and Digital Forensics. He has authored over 600 peer-reviewed research papers, ten books, and nineteen edited proceedings. He is listed as a co-inventor on 44 patents/disclosures. Dr. Agaian was elected IEEE Fellow, SPIE Fellow. Dr. Agaian received his M.S. degree (summa cum laude) in Mathematics and Mechanics from Yerevan State University, Armenia; his Ph.D. in Mathematics and Physics from the Steklov Institute of Mathematics, Russian Academy of Sciences (RAS); and his Doctor of Engineering Sciences degree from the Institute of Control Systems, RAS. Refer (http://www2.cuny.edu/about/alumni-students-faculty/faculty/distinguished-professors/) for more of Sos Agaian.
內(nèi)容摘要
Recently, Just Noticeable Difference (JND) has become a topic of interest for many industries including academic environments, Information Technology Companies, and government organizations. The importance of JND results from its relationship to the visibility threshold; the threshold below which the Human Visual System cannot detect change. JND provides the useful application to perception-oriented computer vision systems and plays an important part in image and video applications such as Digital Watermarking, Image/Video Coding, and Image/Video Streaming. Several JND models have been proposed throughout the past decade. This survey categorizes and briefly reviews the JND literature including JND tools used in image and video processing applications, which have been cited in at least fifty recently published papers.
