http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108805027-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_3c020a3bfe9d62d22c33f10c20d4262b |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V40-172 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 |
| filingDate | 2018-05-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_df4ce7f844f2a49ab6d10cfa3c3ed5cf http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_945f7b352fed5c9ca06217abf1d5d16d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_066ba91a8d01abb0b091c45b884a3bfd http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8cefc84c960700dd2358940c7e24e8bc |
| publicationDate | 2018-11-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108805027-A |
| titleOfInvention | Face Recognition Method under Low Resolution Condition |
| abstract | The invention discloses a face recognition method under low-resolution conditions, which normalizes M face image samples at low resolution and face images to be recognized to preset sizes, and extracts slider LBP feature vectors respectively , the extraction method is: find the LBP feature image of the face image, use the slider to traverse and count the LBP histogram feature vector of each slider area, arrange the LBP histogram feature vector according to the serial number of the slider area, and get The slider LBP feature vector of the face image; the slider LBP feature vector of the M face image samples and the slider LBP feature vector of the face image to be recognized are constructed into a matrix, and then dimensionality reduction is performed, according to the feature matrix after dimensionality reduction The eigenvectors in are identified. The invention can fully extract the features of the low-resolution human face image, and improve the accuracy of human face recognition under the low-resolution condition. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2020185525-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/EP-3935563-A4 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110189255-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11651623-B2 |
| priorityDate | 2018-05-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 26.