Home » ReSIFT, BLeSS, Pooling, Boosting

ReSIFT, BLeSS, Pooling, Boosting

bless2

This paper proposes a biologically-inspired low-level spatiochromatic-model-based similarity method (BLeSS) to assist full-reference image-quality estimators that originally oversimplify color perception processes. More specifically, the spatiochromatic model is based on spatial frequency, spatial orientation, and surround contrast effects. The assistant similarity method is used to complement image-quality estimators based on phase congruency, gradient magnitude, and spectral residual. The effectiveness of BLeSS is validated using FSIM, FSIMc and SR-SIM methods on LIVE, Multiply Distorted LIVE, and TID 2013 databases. In terms of Spearman correlation, BLeSS enhances the performance of all quality estimators in color-based degradations and the enhancement is at 100% for both feature- and spectral residual-based similarity methods. Moreover, BleSS significantly enhances the performance of SR-SIM and FSIM in the full TID 2013 database.

[Related Publications]

  1. D. Temel and G. AlRegib, “BLeSS: Bio-inspired Low-level Spatiochromatic Similarity Assisted Image Quality Assessment “, the IEEE International Conference on Multimedia and Expo , Seattle, USA, Jul. 11-15, 2016. [PDF] [PPT (Poster/Slide)] [Bib] [Code]
  2. D. Temel and G. AlRegib, “ReSIFT: Reliability-weighted SIFT-based Image Quality Assessment”, the IEEE International Conference on Image Processing, Phoenix, Arizona, USA, Sep. 25-28, 2016. [PDF] [PPT (Poster/Slide)] [Bib] [Code]
  3. D. Temel and G. AlRegib, “A Comparative Study of Quality and Content-Based Spatial Pooling Strategies in Image Quality Assessment” IEEE Global Conf. on Signal and Information Processing (GlobalSIP), Orlando, Florida, Dec. 14-16, 2015. [PDF] [PPT (Poster/Slide)] [Bib] [Code]
  4. D.Temel and G. AlRegib, “Boosting in Image Quality Assessment”, the IEEE International Workshop on Multimedia and Signal Processing (MMSP 2016), Montreal, Canada, Sep. 21-23, 2016. [PDF] [PPT (Poster/Slide)] [Bib] [Code]
%d bloggers like this: