-
公开(公告)号:US10210180B2
公开(公告)日:2019-02-19
申请号:US14959304
申请日:2015-12-04
Applicant: Intel Corporation
Inventor: Hila Barel , Gilad Michael , Hadas Dahan
Abstract: Techniques related to approximate nearest neighbor searching are discussed. Such techniques may include traversing an approximate nearest neighbor search tree from root node to a resultant leaf node while maintaining a priority queue of best matches, determining candidate entries for evaluation based on the resultant leaf node, and generating search results based on the priority queue and the candidate entries.
-
公开(公告)号:US10296605B2
公开(公告)日:2019-05-21
申请号:US14968164
申请日:2015-12-14
Applicant: INTEL CORPORATION
Inventor: Hila Barel , Gilad Michael , Edmond Chalom
Abstract: Techniques related to generating dictionaries for example based image processing algorithms are discussed. Such techniques may include iteratively performing example based image processing for candidate look up entries of candidate pairs from a training set database using a current dictionary to determine a test result for each of the look up entries of the candidate pairs and selecting one or more of the candidate pairs for entry in a resultant dictionary based on an error between the test result and a predetermined result entry for the candidate pairs.
-
3.
公开(公告)号:US20180270489A1
公开(公告)日:2018-09-20
申请号:US15857447
申请日:2017-12-28
Applicant: INTEL CORPORATION
Inventor: Shay Maymon , Hila Barel
IPC: H04N19/182 , G06T5/00 , H04N19/186
Abstract: An apparatus is described herein. The apparatus comprises a controller, a logarithmic tone-reproduction operator, a processor, and a compressor. The controller is to calculate a regularization term and a contrast preservation term of an objective function. The logarithmic tone-reproduction operator is to produce a reference image. The processor is to obtain a compressed luminance from the objective function as applied to the reference image. The compressor is to compress a high dynamic range (HDR) image by applying a gain term to the HDR image based on the compressed luminance.
-
公开(公告)号:US10567777B2
公开(公告)日:2020-02-18
申请号:US15857447
申请日:2017-12-28
Applicant: INTEL CORPORATION
Inventor: Shay Maymon , Hila Barel
IPC: H04N19/182 , H04N19/186 , G06T5/00
Abstract: An apparatus is described herein. The apparatus comprises a controller, a logarithmic tone-reproduction operator, a processor, and a compressor. The controller is to calculate a regularization term and a contrast preservation term of an objective function. The logarithmic tone-reproduction operator is to produce a reference image. The processor is to obtain a compressed luminance from the objective function as applied to the reference image. The compressor is to compress a high dynamic range (HDR) image by applying a gain term to the HDR image based on the compressed luminance.
-
公开(公告)号:US20170169057A1
公开(公告)日:2017-06-15
申请号:US14968164
申请日:2015-12-14
Applicant: INTEL CORPORATION
Inventor: Hila Barel , Gilad Michael , Edmond Chalom
CPC classification number: G06F17/30277 , G06K9/00 , G06K9/228 , G06K9/4642 , G06K9/4652 , G06K9/6223 , G06K9/6255 , G06K9/6807 , G06N99/005 , G06T3/4015
Abstract: Techniques related to generating dictionaries for example based image processing algorithms are discussed. Such techniques may include iteratively performing example based image processing for candidate look up entries of candidate pairs from a training set database using a current dictionary to determine a test result for each of the look up entries of the candidate pairs and selecting one or more of the candidate pairs for entry in a resultant dictionary based on an error between the test result and a predetermined result entry for the candidate pairs.
-
公开(公告)号:US20170161271A1
公开(公告)日:2017-06-08
申请号:US14959304
申请日:2015-12-04
Applicant: Intel Corporation
Inventor: Hila Barel , Gilad Michael , Hadas Dahan
CPC classification number: G06F17/3025 , G06F17/30327 , G06F17/3033 , G06F17/30964 , G06N5/047 , G06N99/005 , G06T3/4015
Abstract: Techniques related to approximate nearest neighbor searching are discussed. Such techniques may include traversing an approximate nearest neighbor search tree from root node to a resultant leaf node while maintaining a priority queue of best matches, determining candidate entries for evaluation based on the resultant leaf node, and generating search results based on the priority queue and the candidate entries.
-
-
-
-
-