Title
Entropy Of Primitive: A Top-Down Methodology For Evaluating The Perceptual Visual Information
Abstract
In this paper, we aim at evaluating the perceptual visual information based on a novel top-down methodology: entropy of primitive (EoP). The EoP is determined by the distribution of the atoms in describing an image, and is demonstrated to exhibit closely correlation with the perceptual image quality. Based on the visual information evaluation, we further demonstrate that the EoP is effective in predicting the perceptual lossless of natural images. Inspired by this observation, in order to distinguish whether the loss of input signal is visual noticeable to human visual system (HVS), we introduce the EoP based perceptual lossless profile (PLP). Extensive experiments verify that, the proposed EoP based perceptual lossless profile can efficiently measure the minimum noticeable visual information distortion and achieve better performance compared to the-state-of-the-art just-noticeable difference (JND) profile.
Year
DOI
Venue
2013
10.1109/VCIP.2013.6706358
2013 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP 2013)
Keywords
Field
DocType
Entropy of primitive, visual information, just-noticeable difference, perceptual lossless profile
Computer vision,Pattern recognition,Human visual system model,Computer science,Top-down and bottom-up design,Image processing,Correlation,Artificial intelligence,Distortion,Perception,Visual perception,Lossless compression
Conference
Volume
Issue
Citations 
null
null
10
PageRank 
References 
Authors
0.63
10
5
Name
Order
Citations
PageRank
Xiang Zhang18812.61
Shiqi Wang21281120.37
Siwei Ma32229203.42
Shaohui Liu449646.44
Wen Gao511374741.77