http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2013156374-A1
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_99505f5f312672820e9f78c254c00a4d |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2136 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2013-04-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_49c6a05058a47cbafe385af60437da4c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a4da3e37a222730bc55a36e7939e8741 |
| publicationDate | 2013-10-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | WO-2013156374-A1 |
| titleOfInvention | Method for recognizing a visual context of an image and corresponding device |
| abstract | The invention relates to a method for recognizing a visual context in an image (I), said method comprising at least one step of extracting characteristics (211) from the image (I) and at least one step of encoding (2112) the plurality of local descriptors (2111) creating an encoding matrix (2113) by associating each local descriptor with at least one visual word from a reference dictionary (2010) according to at least one similarity criterion. The method according to the invention is characterised in that said encoding step (2112) results from a compromise between the similarity between a given local descriptor and the visual words of a reference dictionary (2101) and its resemblance to the visual words associated with the local descriptors that are spatially close thereto in the domain of the image (I). |
| priorityDate | 2012-04-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 19.