http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114581536-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_96b9f465dbb4c797acef6db9e837aa16 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-90 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-90 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 |
| filingDate | 2022-02-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_494af1847ea7e759a0c10f090b9c2f4e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8a48f3582912ec0b36d5e358e2b55ba9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_834826b8f304f49f9a006d2eed518626 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9fc4cb57521aa5726793e84f0030533b |
| publicationDate | 2022-06-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-114581536-A |
| titleOfInvention | Image color difference detection method based on feature perception and multi-channel learning |
| abstract | The invention discloses an image color difference detection method based on feature perception and multi-channel learning, comprising: 1) constructing a training set for training a color difference detection network. 2) Input the image into the multi-channel learning module to obtain the comprehensive image feature map; 3) Input the image comprehensive feature map into the feature perception module to obtain the perceptually weighted feature map; 4) Input the perceptually weighted feature map into the region suggestion network to obtain the block feature map; 5) input the block feature map into the prediction regression network to obtain the chromatic aberration offset and position, calculate the loss with the real value, and backpropagate the adjustment parameters; 6) iteratively train to the preset value, determine Color difference detection network; 7) Input the image to be detected into the color difference detection network to obtain the color difference offset and position. The invention can realize high-speed and high-precision chromatic aberration detection for images with complex textures and patterns. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114972976-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114972976-B |
| priorityDate | 2022-02-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID6318 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419484328 |
Total number of triples: 26.