Perceptual evaluation of single-image super-resolution reconstruction

In recent years, single-image super-resolution (SR) reconstruction has aroused wide attention. Massive SR enhancement algorithms have been proposed. However, much less work has been down on the perceptual evaluation of SR enhanced images and the corresponding enhancement algorithms. In this work, we...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Image Processing (ICIP) pp. 3145 - 3149
Main Authors Wang, Guangcheng, Li, Leida, Li, Qiaohong, Gu, Ke, Lu, Zhaolin, Qian, Jiansheng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2017
Subjects
Image enhancement
Image quality
Image quality assessment
Image reconstruction
Image resolution
Interpolation
Measurement
No-reference
Super-resolution reconstruction
Online AccessGet full text

Cover

More Information
Summary:In recent years, single-image super-resolution (SR) reconstruction has aroused wide attention. Massive SR enhancement algorithms have been proposed. However, much less work has been down on the perceptual evaluation of SR enhanced images and the corresponding enhancement algorithms. In this work, we create a Super-resolution Reconstructed Image Database (SRID), which consists of images produced by two interpolation methods and six popular SR image enhancement algorithms at different amplification factors. Then, subjective experiment is conducted to collect the subjective scores by using the single-stimulus method. The performances of the SR image enhancement algorithms are then evaluated by the obtained subjective scores. Finally, the performances of the general-purpose no-reference (NR) image quality metrics are investigated on the SRID database. This study shows that it is difficult for the state-of-the-art NR image quality metrics to predict the quality of SR enhanced images.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296862