A
Alan C. Bovik
Researcher at University of Texas at Austin
Publications - 872
Citations - 120104
Alan C. Bovik is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Image quality & Video quality. The author has an hindex of 102, co-authored 837 publications receiving 96088 citations. Previous affiliations of Alan C. Bovik include University of Illinois at Urbana–Champaign & University of Sydney.
Papers
More filters
Proceedings ArticleDOI
Nonlinear regression for image enhancement via generalized deterministic annealing
Scott T. Acton,Alan C. Bovik +1 more
TL;DR: Using a new optimization technique for nonconvex combinatorial optimization problems, generalized deterministic annealing (GDA), fuzzy nonlinear regressions of noisy images with respect to characteristic image sets defined by certain local image models are computed.
Proceedings ArticleDOI
Optimal Feature Selection for Blind Super-resolution Image Quality Evaluation
TL;DR: This paper presents an opinion-unaware BIQA measure of super resolved images based on optimally extracted perceptual features selected using a floating forward search whose objective function is the correlation with human judgment.
Proceedings ArticleDOI
Enhancing Temporal Quality Measurements in a Globally Deployed Streaming Video Quality Predictor
TL;DR: An enhanced model called SpatioTemporal VMAF (ST- VMAf) is proposed that incorporates temporal features that are easy to compute and demonstrated the improved performance of ST-VMAF on many subjective video databases.
Journal ArticleDOI
Perceptual Video Quality Prediction Emphasizing Chroma Distortions
TL;DR: An objective video quality model is designed which builds on existing video quality algorithms, by considering the fidelity of chroma channels in a principled way, and implies that there is room for reducing bitrate consumption in modern video codecs by creatively increasing the compression factor onchroma channels.
Proceedings ArticleDOI
Detecting spread spectrum watermarks using natural scene statistics
TL;DR: Novel techniques for detecting watermarks in images in a known-cover attack framework using natural scene models and indicates that this statistical framework is effective in the steganalysis of spread spectrum watermarks.