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
Multi-component AM-FM image models and wavelet-based demodulation with component tracking
Joseph P. Havlicek,Alan C. Bovik +1 more
TL;DR: This paper utilizes multi-component AM-FM functions to model multi-partite nonstationary images that are locally coherent, yet globally wideband, and details an approach for simultaneously estimating the modulating functions associated with each of the multiple components.
Journal ArticleDOI
Multidimensional orthogonal FM transforms
TL;DR: The proposed signal-adaptive FM transform produces point spectra for multidimensional signals with uniformly distributed samples, suggesting that the proposed transform is suitable for energy compaction and subsequent coding of broadband signals and images that locally exhibit significant level diversity.
Posted Content
No-Reference Video Quality Assessment Using Space-Time Chips
TL;DR: This work proposes a new prototype model for no-reference video quality assessment (VQA) based on the natural statistics of space-time chips of videos, which achieves high correlation against human judgments of video quality and is competitive with state-of-the-art models.
Proceedings ArticleDOI
Unequal Power Allocation for JPEG Transmission Over MIMO Systems
TL;DR: This work presents an unequal power allocation scheme for transmission of JPEG compressed images over multiple-input multiple-output systems employing spatial multiplexing, and shows that this scheme provides significant image quality improvement as compared to different equal power schemes.
Journal ArticleDOI
Blind Image Quality Assessment for Super Resolution via Optimal Feature Selection
TL;DR: A new dataset of super-resolved images with associated human quality scores is introduced and two no-reference, (NR) opinion-distortion unaware (ODU) IQA models are implemented, achieving better than state-of-the-art performance among the NR-IQA metrics.