Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/19056
DC Field | Value | |
---|---|---|
dc.title | Digital Image super resolution | |
dc.contributor.author | LIU SHUAICHENG | |
dc.date.accessioned | 2011-01-31T18:00:53Z | |
dc.date.available | 2011-01-31T18:00:53Z | |
dc.date.issued | 2010-06-07 | |
dc.identifier.citation | LIU SHUAICHENG (2010-06-07). Digital Image super resolution. ScholarBank@NUS Repository. | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/19056 | |
dc.description.abstract | Edge-directed image super resolution (SR) focuses on ways to remove edge artifacts in upsampled images. Under large magnification, however, textured regions become blurred and appear homogenous, resulting in a super-resolution image that looks unnatural. Alternatively, learning-based SR approaches use a large database of exemplar images for ?hallucinating? detail. The quality of the upsampled image, especially about edges, is dependent on the suitability of the training images. This thesis proposes a method aims to combine the benefits of edge-directed SR with those of learning-based SR. In particular, an approach is proposed to extend edge-directed super-resolution to include detail from an image/texture example provided by the user (e.g., from the Internet). A significant benefit the approach is that only a single exemplar image is required to supply the missing detail ? strong edges are obtained in the SR image even if they are not present in the example image due to the combination of the edge-directed approach. In addition, quality results are achieved at very large magnification, which is often problematic for both edge-directed and learning-based approaches. Besides, another method is proposed in the thesis to handle color in image Super Resolution(SR). Most existing SR techniques focus primarily on enforcing image priors or synthesizing image details; less attention is paid to the final color assignment. As a result, many existing SR techniques exhibit some form of color aberration in the final upsampled image. In this paper, a procedure is outlined based on image colorization and back-projection to perform color assignment guided by the super resolution luminance channel.It is found that the procedure produces better results both quantitatively and qualitatively than existing approaches. In addition, the approach is generic and can be incorporated into any existing SR techniques. | |
dc.language.iso | en | |
dc.subject | Super resolution, Detail synthesis, Edge Prior, Colorization, Back projection | |
dc.type | Thesis | |
dc.contributor.department | COMPUTER SCIENCE | |
dc.contributor.supervisor | MICHAEL S. BROWN | |
dc.description.degree | Master's | |
dc.description.degreeconferred | MASTER OF SCIENCE | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Master's Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
LiuSC.pdf | 2.03 MB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.