M
Michele A. Saad
Researcher at Intel
Publications - 30
Citations - 2934
Michele A. Saad is an academic researcher from Intel. The author has contributed to research in topics: Image quality & Video quality. The author has an hindex of 12, co-authored 29 publications receiving 2353 citations. Previous affiliations of Michele A. Saad include Telefónica & American University of Beirut.
Papers
More filters
Journal ArticleDOI
Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain
TL;DR: An efficient general-purpose blind/no-reference image quality assessment (IQA) algorithm using a natural scene statistics model of discrete cosine transform (DCT) coefficients, which requires minimal training and adopts a simple probabilistic model for score prediction.
Journal ArticleDOI
Blind Prediction of Natural Video Quality
TL;DR: It is shown that the proposed NSS and motion coherency models are appropriate for quality assessment of videos, and they are utilized to design a blind VQA algorithm that correlates highly with human judgments of quality.
Journal ArticleDOI
A DCT Statistics-Based Blind Image Quality Index
TL;DR: The BLIINDS index (BLind Image Integrity Notator using DCT Statistics) is introduced which is a no-reference approach to image quality assessment that does not assume a specific type of distortion of the image and it requires only minimal training.
Journal ArticleDOI
A Completely Blind Video Integrity Oracle
TL;DR: This work develops a new VQA model called the video intrinsic integrity and distortion evaluation oracle (VIIDEO), which is able to predict the quality of distorted videos without any external knowledge about the pristine source, anticipated distortions, or human judgments of video quality.
Proceedings ArticleDOI
DCT statistics model-based blind image quality assessment
TL;DR: The resulting algorithm, which is named BLIINDS-II, requires minimal training and adopts a simple probabilistic model for score prediction, and is shown to correlate highly with human visual perception of quality, at a level that is even competitive with the powerful full-reference SSIM index.