http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112734763-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10024 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-22 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-90 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-90 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-74 |
filingDate | 2021-01-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-09-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-09-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-112734763-B |
titleOfInvention | Image decomposition method based on joint sparse coding of convolution and K-SVD dictionary |
abstract | The invention discloses an image decomposition method based on convolution and K-SVD dictionary joint sparse coding. First, an acquired color image is preprocessed to obtain an image to be decomposed; Superposition; build a priori constraints according to the prior characteristics of the two unknown components; finally solve the two unknown components through alternate optimization; judge whether a feasible solution is reached according to the convergence conditions. The invention can be used for image denoising. A set of convolution operators is obtained by learning according to different noise types, and the noise is approximated by updating the convolution kernel and the response coefficient. The method can be dynamically applied to various noise types, and overcomes the problem of constructing different Disadvantages of regularization constraints. |
priorityDate | 2021-01-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 27.