http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2022126220-A1
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_812df1562683620f8929d57692477f02 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-117 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V40-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-117 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate | 2021-12-20-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_812a2dfcf64637e7b22fb917767eec62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_db51f659d2e88e5e5fb20cb73f034daf |
publicationDate | 2022-06-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | WO-2022126220-A1 |
titleOfInvention | Image recognition method and system, training method, and biometric authentication system |
abstract | The present invention discloses an image recognition method implemented in a system provided with a processor that executes a trained model. To do so, the present invention discloses a training method for the model using Triplet and ArcFace cost functions combined in a sum for the secure, efficient and effective recognition of individuals. More specifically, the present invention discloses a system for recognising images such as images of finger blood vessels for biometric authentication, including a processor that executes the model previously trained using the training method. The present invention pertains to the fields of electrical engineering, data security, deep neural networks, computer sciences, and information engineering. |
priorityDate | 2020-12-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 20.