.png){kind=icon}
.png){kind=icon}
Return
Image interpolation model based on packet losing network
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-09255-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, a method combining an error hiding algorithm with image super-resolution reconstruction is proposed, which uses packet loss compensation as an alternative to traditional reconstruction processes. Our algorithm provides an alternative to traditional frameworks by firstly estimating the edge direction of the block and then interpolating along the edge direction. We define a pixel span function to obtain the missing image details, and the pixels are reconstructed using this function to detect their possible textures. Experiments using established image data sets show that comparison with seven other classical image interpolation algorithms, the proposed approach achieves both higher quantitative and qualitative performance results, ultimately providing better visual effects.
Keywords:
Image super-resolution
Packet loss
Packet loss compensation
Interpolation
Error hiding
Pixel span
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W