31 May 2011 An image similarity measure using enhanced human visual system characteristics
Author Affiliations +
Abstract
Image similarity measures are crucial for image processing applications which require comparisons to ideal reference images in order to assess performance. The Structural Similarity (SSIM), Gradient Structural Similarity (GSSIM), 4-component SSIM (4-SSIM) and 4-component GSSIM (4-GSSIM) indexes are motivated by the fact that the human visual system is adapted to extract local structural information. In this paper, we propose a new measure which enhances the gradient information used for quality assessment. An analysis of the proposed image similarity measure using the LIVE database of distorted images and their corresponding subjective evaluations of visual quality illustrate the improved performance of the proposed metric.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shahan Nercessian, Shahan Nercessian, Sos S. Agaian, Sos S. Agaian, Karen A. Panetta, Karen A. Panetta, "An image similarity measure using enhanced human visual system characteristics", Proc. SPIE 8063, Mobile Multimedia/Image Processing, Security, and Applications 2011, 806310 (31 May 2011); doi: 10.1117/12.883301; https://doi.org/10.1117/12.883301
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

SPCA a no reference image quality assessment based on...
Proceedings of SPIE (February 03 2013)
Color image attribute and quality measurements
Proceedings of SPIE (May 27 2014)
Three-component weighted structural similarity index
Proceedings of SPIE (January 18 2009)
Advances In Transform Image Coding
Proceedings of SPIE (April 23 1987)
New vistas in image and video quality
Proceedings of SPIE (March 13 2007)

Back to Top