http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114399684-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-047 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-048 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2415 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N21-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-44 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N21-25 |
filingDate | 2022-03-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-08-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-08-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114399684-B |
titleOfInvention | A method for openness classification of hyperspectral images based on dual loss functions |
abstract | In order to solve the problem that most of the open classification methods of hyperspectral images in the existing image processing are used to classify images at the image level, they are not suitable for pixel-level image classification; or are susceptible to noise and mixed pixels in the classification process. However, a method for classification of openness of hyperspectral images based on dual loss functions is provided. Including the following steps: step 1, taking a neighborhood block for each pixel of the known three-dimensional hyperspectral image X and the three-dimensional hyperspectral image S to be tested; step 2, constructing a feature extraction network, using the neighborhood block of the hyperspectral image X The data and its corresponding category labels are used to train the feature extraction network; step 3, the feature vector of the corresponding category data is obtained; step 4, the double loss function classification network is constructed, and the feature vector is used to train the double loss function classification network; The loss function classification network and preset thresholds are used to openly classify the neighborhood block data of the 3D hyperspectral image S. |
priorityDate | 2022-03-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 26.