SSR2: Sparse signal recovery for single-image super-resolution on faces with extreme low resolutions

Pattern Recognition, pp. 308-324, 2019.

Cited by: 9|Bibtex|Views17|Links
EI

Abstract:

Abstract Automatic face recognition in the wild still suffers from low-quality, low resolution, noisy, and occluded input images that can severely impact identification accuracy. In this paper, we present a novel technique to enhance the quality of such extreme low-resolution face images beyond the current state of the art. We model the...More

Code:

Data:

Your rating :
0

 

Tags
Comments