Premium
68‐1: A Machine Learning Approach to Objective Image Quality Evaluation
Author(s) -
Ribera Javier,
Cook Gregory W.,
Stolitzka Dale,
Xiong Wei
Publication year - 2019
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1002/sdtp.13084
Subject(s) - lossless compression , computer science , machine learning , artificial intelligence , image quality , image (mathematics) , quality (philosophy) , image compression , gold standard (test) , standard test image , test (biology) , correlation , computer vision , pattern recognition (psychology) , image processing , data compression , mathematics , statistics , paleontology , philosophy , geometry , epistemology , biology
Subjective Test Scoring is the gold standard for evaluating visual lossless image compression, but its high cost and long lead time prohibits testing more than a few images. Here, we model the display and human eye and use Machine Learning models of increased complexity, achieving a Pearson correlation of 0.95.