http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200094218-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_34c88c465202a4bc7d8388cca9c9bf52 |
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2021-95676 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30148 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0004 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N21-956 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-001 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G03F1-84 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G03F1-84 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N21-956 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate | 2018-12-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_352d92dc8ba583984965118f60bc2a05 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9c8a13a13d162b4c95fed25a817b7179 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ae76c2f35a3c8ec2458443557b2e590b |
| publicationDate | 2020-08-06-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | KR-20200094218-A |
| titleOfInvention | Reticle inspection using machine learning |
| abstract | A method and apparatus for inspecting a photolithographic reticle is disclosed. The near field reticle image is generated through an in-depth learning process based on the reticle database image generated from the design database, and the far field reticle image is simulated through a physical based process based on the near field reticle image in the image plane of the inspection system. The deep learning process includes training a deep learning model based on minimizing differences between far field reticle images and a plurality of corresponding training reticle images obtained by imaging a training reticle manufactured from a design database, These training reticle images are selected for pattern diversity and are flawless. The test area of the test reticle manufactured from the design database is inspected for defects through a die-to-database process, and the die-to-database process tests multiple reference images from a reference far field reticle image by an inspection system And comparing with multiple test images obtained from the reticle. The reference far field reticle image is simulated based on the reference near field reticle image generated by the trained deep learning model. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023064194-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/DE-102021208165-A1 |
| priorityDate | 2017-12-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 34.