http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-103996052-B
Outgoing Links
Predicate | Object |
---|---|
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2014-05-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2017-05-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2017-05-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-103996052-B |
titleOfInvention | Three-dimensional face gender classification method based on three-dimensional point cloud |
abstract | The present invention discloses a kind of three-dimensional face Gender Classification device and method based on three-dimensional point cloud, and described device includes:The characteristic area detection unit positioned to three-dimensional point cloud characteristic area;The three-dimensional point cloud normalized mapping of positioning to the depth image map unit in depth image space will be detected;The LBP feature calculation units of LBP feature calculations are carried out to the depth image after mapping;And the classifier calculated unit of Gender Classification is carried out to the LBP histogram features that LBP feature calculations are obtained.Methods described includes:Characteristic area detecting step, depth image mapping step, LBP feature calculations step and classifying step.This patent utilizes the LBP histogram feature accurate descriptions characteristic of three dimensional depth facial image, and Accurate classification is realized on LBP histogram features using sex SVM classifier, and nicety of grading is high.The present invention can carry out lifting system precision as the solution of three-dimensional face Gender Classification application or as the rough classification step of three-dimensional face Gender Classification. |
priorityDate | 2014-05-12-04:00^^<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/substance/SID415713197 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID25572 |
Total number of triples: 12.