Back to Search
Start Over
Single Image Super-Resolution via L0 Image Smoothing
- Source :
- Mathematical Problems in Engineering, Vol 2014 (2014)
- Publication Year :
- 2014
- Publisher :
- Hindawi Limited, 2014.
-
Abstract
- We propose a single image super-resolution method based on aL0smoothing approach. We consider a low-resolution image as two parts: one is the smooth image generated by theL0smoothing method and the other is the error image between the low-resolution image and the smoothing image. We get an intermediate high-resolution image via a classical interpolation and then generate a high-resolution smoothing image with sharp edges by theL0smoothing method. For the error image, a learning-based super-resolution approach, keeping image details well, is employed to obtain a high-resolution error image. The resulting high-resolution image is the sum of the high-resolution smoothing image and the high-resolution error image. Experimental results show the effectiveness of the proposed method.
- Subjects :
- Article Subject
business.industry
General Mathematics
Binary image
lcsh:Mathematics
General Engineering
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Image processing
Edge-preserving smoothing
lcsh:QA1-939
Image texture
lcsh:TA1-2040
Computer Science::Computer Vision and Pattern Recognition
Computer vision
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
Image restoration
Smoothing
Image gradient
Feature detection (computer vision)
Mathematics
Subjects
Details
- Language :
- English
- ISSN :
- 15635147
- Volume :
- 2014
- Database :
- OpenAIRE
- Journal :
- Mathematical Problems in Engineering
- Accession number :
- edsair.doi.dedup.....5cabbe1a86e2f44fef39331a2ee46d6b