http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106557758-B

Outgoing Links

Predicate Object
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-695
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-698
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2414
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
filingDate 2016-11-25-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2019-04-19-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2019-04-19-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-106557758-B
titleOfInvention A multi-target automatic identification method for sand microscopic images
abstract The invention discloses a multi-target automatic identification method for sand microscopic images. The steps are: 1) preparing sand microscopic images and pre-processing by median filtering; adding corresponding labels to sand sample images to prepare sand grains Cell library; 2) Segment the sand microscopic image using the region growing algorithm, remove impurities and extract multi-objective cells; 3) Calculate the texture and shape features of the sand cell; 4) Based on the sand cell library, train the RBF neural network classifier 5) Predict the type of sand unit and output the composition of the sand microscopic image. The method uses image processing technology and machine learning method to automatically extract and identify multi-target units in sand microscopic images, and can solve the problem that there are many impurities in the image and thus affect the extraction of multi-target units.
priorityDate 2016-11-25-04:00^^<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/SID449029786
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID61775

Total number of triples: 20.