Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ca46be4e68fa1f5a8b2ef4ab654c490a |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50 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/G06T5-50 |
filingDate |
2018-08-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a9c5a82a4b42966f285ef15ee2fa15c8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a8de257b45c477145ef5fe0ec5f6444b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fbfe818f96e2dac279535dc07e73fcf1 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0161ba97f1d034af13aca17ccf99e108 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b179128213ef00daada27d45f552dcc2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ade32fdf9f19b0f1a43a69c8154e8533 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_34ef4a7d91a1380c6d2781ee8cdbedfe |
publicationDate |
2019-03-01-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-109410158-A |
titleOfInvention |
A Multifocal Image Fusion Method Based on Convolutional Neural Network |
abstract |
The invention relates to a multi-focus image fusion method based on a convolutional neural network, comprising: constructing an original focus detection convolutional neural network; training the original focus detection convolutional neural network to obtain a trained focus detection convolutional neural network; According to the trained focus detection convolutional neural network and the preprocessed image, a focus distribution image is obtained; the focus distribution map and the preprocessed image are fused to obtain a fusion image. The multi-focus image fusion method based on the convolutional neural network provided by the present invention adopts the end-to-end convolutional neural network to directly generate the focus distribution map, which greatly improves the speed of generating the focus distribution map, the real-time performance is stronger, and the focus is directly used. The distribution map performs weighted average summation processing on the source images, without introducing additional human intervention measures, avoiding artificial defects in the fusion result map. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111551117-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111551117-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110555820-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111504227-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111504227-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110400307-A |
priorityDate |
2018-08-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |