http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-102461585-B1
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02P90-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30164 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-007 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-90 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0004 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-13 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-90 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-13 |
filingDate | 2020-12-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-10-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-10-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-102461585-B1 |
titleOfInvention | Classification of defective plating of hexagonal nuts using object segmentation pre-processing and convolutional neural network |
abstract | The present invention uses four cameras to obtain each image of a hexagon nut object, then divides and extracts a hexagon nut object that does not contain a background that can act as a noise from each image It relates to an object division preprocessing that determines the plating state of a hexagon nut object by reflecting in learning and inference, and a hexagon nut plating defect determination method using CNN. The technical idea of the present invention is the object division pre-processing and the hexagon nut plating defect determination method using CNN, Placing a plated hexagon nut on top of a transparent glass of a predetermined thickness; First to third cameras arranged at a position of 120 degrees on the upper part of the transparent glass and spaced apart by a predetermined distance are photographed in the diagonal direction to obtain first to third hexagon nut images, and the acquiring a fourth hexagon nut image by vertically photographing a lower portion of the hexagon nut seated on the transparent glass with a fourth camera disposed; A preprocessing process of removing the background of each of the first to fourth hexagon nut images is performed, and it is determined whether the plating state of the hexagon nut is defective through deep learning. When performing "object division pre-processing and method for determining bad plating of hexagon nut using CNN" according to the present invention, only for the plating state of the hexagon nut itself by performing a pre-processing process of removing the background of the hexagon nut object that can recognize noise There is an advantage that the error in determining plating defects can be remarkably improved by performing deep learning. |
priorityDate | 2020-12-07-04:00^^<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/CID4933 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419514502 |
Total number of triples: 24.