http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110009590-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10024 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-005 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 |
filingDate | 2019-04-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2021-02-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2021-02-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110009590-B |
titleOfInvention | A high-quality color image demosaicing method based on convolutional neural network |
abstract | The invention discloses a high-quality color image demosaicing method based on a convolutional neural network, which belongs to the field of image signal processing. The invention makes full use of the self-similarity and redundant information of the image in the process of color image demosaicing without greatly increasing the calculation amount, designs the color image demosaicing network, and uses the color image demosaicing network to represent the transformation from mosaic image to color image. end-to-end mapping; make a training set for training the designed color image demosaicing network; configure the parameters required for color image demosaicing network training; use the made training set to update network parameters using stochastic gradient descent; use the training set The obtained network model directly reconstructs the target color image of any resolution, and obtains a high-quality color image. The invention has the advantages of high reconstruction efficiency and high reconstructed color image quality. The present invention can be used in all cameras based on Bayer color filter array to complete the image demosaicing task. |
priorityDate | 2019-04-12-04:00^^<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/compound/CID22978774 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419701332 |
Total number of triples: 16.