| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ae2be58a477cef66248d0dc28cb0ea82 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30141
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02P90-30
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/G06T7-0008
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-774
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-82
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-764
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-774
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
| filingDate |
2022-05-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8936652f0a5a4d03307db4fc30d8d7e1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7aa7c53f485885b55da8cc85b18379b1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_99f61e2c3e8f45215a25c3eae5a7251e
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a0a8485ae20c9e88b8ac7723793ff9b2 |
| publicationDate |
2022-08-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-114898153-A |
| titleOfInvention |
A Two-Stage Surface Defect Recognition Method Combining Classification and Detection |
| abstract |
The invention discloses a two-stage surface defect identification method combining classification and detection. The method includes the following steps: S1, respectively constructing a defect classification network model and a defect detection network model; S2, constructing a data set according to S1 and training defect classification respectively Network model and defect detection network model; S3. Build a two-stage surface defect recognition algorithm model according to S2. S4. Input the inspected object into the two-stage surface defect recognition algorithm model in S3 to classify large-scale overall defects and small local defects. location identification. The beneficial effect of the present invention is that, by introducing a new feature learning method and constructing a two-stage network model of classification and detection, not only the targeted reinforcement of key features in the feature map is realized, the robustness and interpretability of the algorithm are improved, but also the At the same time, it integrates the advantages of the image classification network and the target detection network to achieve efficient identification of overall defects and accurate localization of local defects, and has high computational efficiency. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115359307-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115359307-A |
| priorityDate |
2022-05-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |