http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110232317-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_13ce3bb9fabf374d7b709249452fd18a |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10036 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4053 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-13 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T3-40 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/G06T7-11 |
| filingDate | 2019-05-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_77aedda97a924159c4db6ab4cbc2eecf http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4688cac5e878685dc387d47a0f724f97 |
| publicationDate | 2019-09-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-110232317-A |
| titleOfInvention | Hyperspectral image classification method based on superpixel segmentation and two-stage classification strategy |
| abstract | The present invention proposes a method for classifying hyperspectral images based on superpixel segmentation and a two-stage classification strategy, comprising the following steps: A, preparing hyperspectral images to be processed and initial training sample data sets; B, performing hyperspectral images on hyperspectral images Pixel segmentation processing, and judging whether each super pixel data in the hyperspectral image contains initial training sample data, if so, and when the initial training sample data it contains only belongs to one class, classify all the data in the super pixel data to the same class as the initial training sample data, and add the classified superpixel data to the initial training sample data set to generate an expanded training sample data set; C, judge whether the data in the hyperspectral image has been classified into a class, If not, a second classification process is performed on the unclassified data based on the enlarged training sample data set. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112101381-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112417188-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112950654-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112950654-B |
| priorityDate | 2019-05-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 29.