Face hallucination based on sparse local-pixel structure
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3551708
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2013.09.012
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 1261
- Volume
- 47
- Issue
- 3
- ISSN
- 0031-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 50
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Recovering high-resolution images from their low-resolution representations has widespread applications in computer vision and image processing but is a difficult and often ill-posed problem because it requires us to infer unobserved high dimensional data from limited noisy observations. This work establishes that the local pixel structures of high quality images exhibit sparsity characteristics; and shows that by modelling the local pixel structures through sparse representations, important image features such as sharp edges, discontinuities, and other high frequency visual features can be estimated more accurately and robustly against noise, and thus can recover higher quality high-resolution images.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
