Al Bovik HonFRPS | |
---|---|
Born | |
Alma mater | University of Illinois |
Awards | |
Scientific career | |
Fields | Digital television, digital photography, image processing, vision science, video processing |
Institutions | The University of Texas at Austin |
Doctoral advisor | Thomas Huang David C. Munson |
Alan Conrad Bovik (born June 25, 1958) is an American engineer, vision scientist, and educator. He is a professor at the University of Texas at Austin (UT-Austin), where he holds the Cockrell Family Regents Endowed Chair in the Cockrell School of Engineering and is Director of the Laboratory for Image and Video Engineering (LIVE). He is a faculty member in the UT-Austin Department of Electrical and Computer Engineering, the Machine Learning Laboratory, the Institute for Neuroscience, and the Wireless Networking and Communications Group.
Bovik received a Primetime Emmy Award in 2015 for his development of perception-based video quality measurement tools that are now standards in television production. [1] He also received a Technology and Engineering Emmy Award in 2021 for the “development of perceptual metrics for video encoding optimization.” [2]
Al Bovik was educated at the University of Illinois at Urbana–Champaign (PhD 1984). He has made numerous fundamental contributions to the fields of digital photography, digital television, digital image processing, digital video processing, digital cinema, and computational visual perception. He is particularly well known for his work on low-level vision, natural scene modeling, image quality, and video quality. [3]
He has published more than 1000 technical articles, books, and patents in these areas. He is also the author/editor of The Handbook of Image and Video Processing (Academic Press, 2nd edition, 2005), with Zhou Wang of Modern Image Quality Assessment (Morgan and Claypool, 2006), and the author/editor of the companion books The Essential Guide to Image Processing and The Essential Guide to Video Processing (Academic Press, 2009). Overall, his work has been cited in the scientific and engineering literature more than 175,000 times according to Google Scholar. [4] He is one of the most highly cited engineers in the world according to the Web of Science. [5]
Bovik is an elected member of the United States National Academy of Engineering (NAE), an elected Foreign Fellow of the Indian National Academy of Engineering (INAE), an elected Fellow of the U.S. National Academy of Inventors, and an elected foreign member of Academia Europaea (2023). [6] He is also a Life Fellow of the IEEE, a Fellow of Optica [7] and of the Society of Photo-Optical and Instrumentation Engineers (SPIE), an Honorary Fellow of the Royal Photographic Society (HonFRPS) and an Honorary Member of the Society for Imaging Science and Technology (IS&T). He is a voting member of the Academy of Television Arts and Sciences (Television Academy) and was named an inaugural member of its Science and Technology Peer Group. He was named a Distinguished Alumnus of the University of Illinois at Urbana–Champaign in 2008. [7]
Bovik is credited with the development of order statistic filters, the image modulation model, computational modeling of visual texture perception, theories of foveated image processing, and for widely used and disseminated image quality and video quality computational models and measurement tools that are used throughout the television, cinematic, streaming video, and social media industries. His contributions include the invention or co-invention of the Emmy Award-winning Structural Similarity (SSIM) video quality measurement tool, the MOVIE Index, the Visual Information Fidelity (VIF) algorithms, the FUNQUE family of video quality models, and his extensive contributions to the Emmy Award-winning VMAF system, all reference models that predict human perception of image quality or distortion; the RRED indices, which are a family of reduced reference image and video quality prediction models, and BRISQUE, BLIINDS, DIIVINE, NIQE, and ChipQA, which are a new breed of image and video quality prediction models that produce accurate predictions of human judgments of picture quality without using reference information. His high-dynamic range (HDR) add-on model HDRMAX, which improves the quality prediction performance of leading models is marketed and used worldwide. His picture and video quality models SSIM, MS-SSIM, VIF, VMAF, MOVIE, BRISQUE, FUNQUE, NIQE, ChipQA, and HDRMAX currently process a significant percentage of all bits transmitted both in the United States as well as globally, and are implemented in commercial cable, satellite, broadcast, streaming video, television, home cinema / disc, and social media quality monitoring and control workflows around the world.[ citation needed ]
He was the founder and First General Chair of the IEEE International Conference on Image Processing (ICIP).[ citation needed ] He also co-founded (with David Munson, Jr.) the IEEE Transactions on Image Processing and was its longest-serving Editor-in-Chief, with a tenure of six years.
Bovik's academic legacy includes serving as the supervising professor of more than 70 PhD graduates, more than 50 master's degree recipients, and more than two dozen post-doctoral researchers.
He has created widely used, adopted, and cited books and online courseware, including The Handbook of Image and Video Processing (Academic Press, 2000, 2005), Modern Image Quality Assessment (Morgan & Claypool, 2006), The Essential Guide to Image Processing (Academic Press, 2009), and The Essential Guide to Video Processing (Elsevier Academic Press, 2009). His award-winning online courseware is used internationally: SIVA – [8] Courseware for Signal, Image, Video and Audio Processing. This online courseware offers broad, deep online curricula for digital image and video processing and digital signal processing. SIVA includes hundreds of signal, image and video processing demonstrations delivering live, interactive audio-visual experiences of signal and image processing algorithms.
Bovik has received a number of major international awards. These include:
In addition he has been recognized by the following honors:
Video quality is a characteristic of a video passed through a video transmission or processing system that describes perceived video degradation. Video processing systems may introduce some amount of distortion or artifacts in the video signal that negatively impact the user's perception of the system. For many stakeholders in video production and distribution, ensuring video quality is an important task.
The structural similarityindex measure (SSIM) is a method for predicting the perceived quality of digital television and cinematic pictures, as well as other kinds of digital images and videos. It is also used for measuring the similarity between two images. The SSIM index is a full reference metric; in other words, the measurement or prediction of image quality is based on an initial uncompressed or distortion-free image as reference.
Thomas Shi-Tao Huang was a Chinese-born American computer scientist, electrical engineer, and writer. He was a researcher and professor emeritus at the University of Illinois at Urbana-Champaign (UIUC). Huang was one of the leading figures in computer vision, pattern recognition and human computer interaction.
Thomas Wiegand is a German electrical engineer who substantially contributed to the creation of the H.264/AVC, H.265/HEVC, and H.266/VVC video coding standards. For H.264/AVC, Wiegand was one of the chairmen of the Joint Video Team (JVT) standardization committee that created the standard and was the chief editor of the standard itself. He was also a very active technical contributor to the H.264/AVC, H.265/HEVC, and H.266/VVC video coding standards. Wiegand also holds a chairmanship position in the ITU-T VCEG of ITU-T Study Group 16 and previously in ISO/IEC MPEG standardization organizations. In July 2006, video coding work of the ITU-T was jointly led by Gary J. Sullivan and Wiegand for the preceding six years. It was voted as the most influential area of the standardization work of the CCITT and ITU-T in their 50-year history. Since 2018, Wiegand has served as chair of the ITU/WHO Focus Group on Artificial Intelligence for Health (FG-AI4H). Since 2014, Thomson Reuters named Wiegand in their list of “The World’s Most Influential Scientific Minds” as one of the most cited researchers in his field.
Gary Joseph Sullivan is an American electrical engineer who led the development of the AVC, HEVC, and VVC video coding standards and created the DirectX Video Acceleration (DXVA) API/DDI video decoding feature of the Microsoft Windows operating system. He is currently Director of Video Research and Standards at Dolby Laboratories and is the chair of ISO/IEC JTC 1/SC 29 and of the ITU-T Video Coding Experts Group (VCEG).
Image quality can refer to the level of accuracy with which different imaging systems capture, process, store, compress, transmit and display the signals that form an image. Another definition refers to image quality as "the weighted combination of all of the visually significant attributes of an image". The difference between the two definitions is that one focuses on the characteristics of signal processing in different imaging systems and the latter on the perceptual assessments that make an image pleasant for human viewers.
Martin Vetterli is the president of École polytechnique fédérale de Lausanne (EPFL) in Switzerland, succeeding Patrick Aebischer. He's a professor of engineering and was formerly the president of the National Research Council of the Swiss National Science Foundation.
Scene statistics is a discipline within the field of perception. It is concerned with the statistical regularities related to scenes. It is based on the premise that a perceptual system is designed to interpret scenes.
Nasir Ahmed is an Indian-American electrical engineer and computer scientist. He is Professor Emeritus of Electrical and Computer Engineering at University of New Mexico (UNM). He is best known for inventing the discrete cosine transform (DCT) in the early 1970s. The DCT is the most widely used data compression transformation, the basis for most digital media standards and commonly used in digital signal processing. He also described the discrete sine transform (DST), which is related to the DCT.
Peter (Petre) Stoica is a researcher and educator in the field of signal processing and its applications to radar/sonar, communications and bio-medicine. He is a professor of Signals and Systems Modeling at Uppsala University in Sweden, and a Member of the Royal Swedish Academy of Engineering Sciences, the United States National Academy of Engineering, the Romanian Academy, the European Academy of Sciences, and the Royal Society of Sciences in Uppsala. He is also a Fellow of IEEE, EURASIP, IETI, and the Royal Statistical Society.
Murat Kunt is a Swiss scientist of Turkish origin. He is known for his research and teaching in the general area of digital signal processing and image and video processing in particular. He is the author of more than 240 publications, 15 books and 16 patents. He played a pioneering role in digital image and video compression. Among the 75 doctoral students he supervised, 20 are now university professors.
Robert W. Heath Jr. is an American electrical engineer, researcher, educator, wireless technology expert, and a professor in the Department of Electrical and Computer Engineering at the University of California, San Diego. He is also the president and CEO of MIMO Wireless Inc. He was the founding director of the Situation Aware Vehicular Engineering Systems initiative.
The MOtion-tuned Video Integrity Evaluation (MOVIE) index is a model and set of algorithms for predicting the perceived quality of digital television and cinematic pictures, as well as other kinds of digital images and videos.
Video Multimethod Assessment Fusion (VMAF) is an objective full-reference video quality metric developed by Netflix in cooperation with the University of Southern California, The IPI/LS2N lab Nantes Université, and the Laboratory for Image and Video Engineering (LIVE) at The University of Texas at Austin. It predicts subjective video quality based on a reference and distorted video sequence. The metric can be used to evaluate the quality of different video codecs, encoders, encoding settings, or transmission variants.
Mads Græsbøll Christensen is a Danish Professor in Audio Processing at Department of Architecture, Design & Media Technology, Aalborg University, where he is also head and founder of the Audio Analysis Lab which conducts research in audio and acoustic signal processing. Before that he worked at the Department of Electronic Systems at Aalborg University and has held visiting positions at Philips Research Labs, ENST, UCSB, and Columbia University. He has published extensively on these topics in books, scientific journals and conference proceedings, and he has given tutorials and keynote talks at major international scientific conferences.
Moeness G. Amin is an Egyptian-American professor and engineer. Amin is the director of the Center for Advanced Communications and a professor in the Department of Electrical and Computer Engineering at Villanova University.
Yonina C. Eldar is an Israeli professor of electrical engineering at the Weizmann Institute of Science, known for her pioneering work on sub-Nyquist sampling.
Jiebo Luo is a Chinese-American computer scientist, the Albert Arendt Hopeman Professor of Engineering and Professor of Computer Science at the University of Rochester. He is interested in artificial intelligence, data science and computer vision.
Jan P. Allebach is an American engineer, educator and researcher known for contributions to imaging science including halftoning, digital image processing, color management, visual perception, and image quality. He is Distinguished Professor Emeritus of Electrical and Computer Engineering at Purdue University.
Vishal Monga is an Indian American electrical engineer, researcher and academic. He is a professor of Electrical Engineering at the Pennsylvania State University.