发明名称 |
Super resolution image enhancement technique |
摘要 |
A method for image enhancement may include selecting a plurality of patches of an image and determining at least one dimensionally reduced feature for each of the plurality of patches. The system may further determine a generally closest cluster from a set of clusters for each of the dimensionally reduced features and select a corresponding set of regression coefficients for each of the set of generally closest cluster. The system may also apply the selected set of regression coefficients to a corresponding patch to enhance the image. |
申请公布号 |
US9589323(B1) |
申请公布日期 |
2017.03.07 |
申请号 |
US201514827030 |
申请日期 |
2015.08.14 |
申请人 |
Sharp Laboratories of America, Inc. |
发明人 |
Choudhury Anustup Kumar;Chen Xu;van Beek Petrus J. L. |
分类号 |
G06K9/40;G06T3/40;G06K9/46;G06K9/34;G06T5/00 |
主分类号 |
G06K9/40 |
代理机构 |
Chernoff Vilhauer McClung & Stenzel, LLP |
代理人 |
Chernoff Vilhauer McClung & Stenzel, LLP |
主权项 |
1. A method for image enhancement comprising:
(a) selecting a plurality of patches of an image; (b) determining at least one feature for each of said plurality of patches; (c) reducing the dimensionality of said at least one feature for each of said plurality of patches to determine a dimensionally reduced feature for each of said plurality of patches; (d) determining a generally closest cluster from a set of clusters based on said dimensionally reduced feature for each of said plurality of patches; (e) identifying a corresponding set of regression coefficients for each of said generally closest cluster; (f) applying said selected regression coefficients to a corresponding said patch to enhance said image. |
地址 |
Camas WA US |