http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106778919-B

Outgoing Links

Predicate Object
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-25
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-507
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-267
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-34
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/G06K9-32
filingDate 2017-01-24-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2020-01-07-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2020-01-07-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-106778919-B
titleOfInvention A method for country identification of euro coins based on local binary patterns
abstract The invention discloses a method for country identification of euro coins based on a local binary pattern, comprising the following steps: step 1: acquiring a grayscale image of a coin, extracting a target area to be detected from the acquired coin image, and performing size normalization processing; step 2: decompose the target area into annular space; step 3: extract the uniform rotation-invariant local binary pattern of each annular area, and count its histogram distribution characteristics, and then follow the steps from the inner ring to the outer ring. Assemble in sequence to obtain the final coin image description feature; Step 4: Design a classifier by using a support vector machine, and design multiple classifiers according to different currency values to detect and identify euro coins of different currency values. The invention uses the area as a feature to determine the currency value of the euro coin, and then selects different classifiers for identification according to the currency value, thereby decomposing the euro coin country identification problem, reducing the difficulty of the problem, and ensuring the accuracy of subsequent country identification.
priorityDate 2017-01-24-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2001175911-A
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419523291
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID977

Total number of triples: 19.