http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-104077319-B

Outgoing Links

Predicate Object
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-5866
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-30
filingDate 2013-03-29-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2018-03-06-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2018-03-06-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-104077319-B
titleOfInvention Image labeling method based on non-Euclidean space Diversity measure
abstract Social Media shares the rapid development of digital picture quantity on website, is greatly promoted research enthusiasm of the people to Semantic Image Retrieval.However, due to the wide gap between image low-level feature and high-level semantic pattern so that many existing automatic image annotation technologies can not reach gratifying retrieval effectiveness.Therefore, the present invention proposes a kind of image labeling method based on non-Euclidean space Diversity measure.This method calculates three jump opposite sex features of image first by high order statistics, to reach the purpose that correlation between image is better described;Then, using the maximal posterior probability algorithm spread based on gauss hybrid models and otherness increment, to estimate the correlation of each label and picture material.
priorityDate 2013-03-29-04:00^^<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/CID25572
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415713197

Total number of triples: 12.