| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ee9e885f6556d65d0185a7be38f8c8a2
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_33084ccb2ec7d9f4c4c8b4311f9ace6d |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30164
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-194
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-136
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-751
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0004 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
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/G06T7-194
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-136 |
| filingDate |
2020-07-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_70e34e5ebd8a787856c2bbae4acd7d86
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fd1ae7ca9fa4c92ed8a8fc94afde26b8 |
| publicationDate |
2020-11-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-111951234-A |
| titleOfInvention |
Model checking methods |
| abstract |
The invention provides a model detection method, comprising the following steps: a building step: designing and building a deep learning model for detecting workpiece defects; a classification step: classifying each pixel in the learning image to be learned, Confidence determination of each pixel point is performed on the type; deep learning model training step: train the learning images that have completed pixel category classification and confidence determination to obtain a trained deep learning model; defect detection step: use the depth after training. The learned model performs defect detection on the workpiece. Through deep learning detection, the present invention greatly reduces the time complexity, reduces the generation of redundant windows, and greatly improves the speed and performance of subsequent feature extraction and classification; the present invention improves the robustness of images through deep learning detection; The invention combines multiple detection modes, and the detection is more comprehensive and accurate. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114998315-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114998315-A |
| priorityDate |
2020-07-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |