| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1a258fbf53a4ae7f921767140d611c06 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30024
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20021
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20036
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10056
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30096 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0012
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-45
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-90 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 |
| filingDate |
2006-09-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d37ccedf1ad1830b5c71a4bd1f449b98
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a603e855d2efca476cfe76ee7ebd5c2d |
| publicationDate |
2008-06-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
KR-20080055898-A |
| titleOfInvention |
Automatic selection of image areas |
| abstract |
A method of automatic selection of image regions ("tiles") in an entire image includes calculating a gray level co-occurrence matrix and entropy of the green plane of the entire image, applying intimate morphology to the matrix, and providing binary masks. Thresholding the matrix and entropy images. The matrix and entropy masks are combined with a vignette mask, wherein the combination refers to areas of acceptable tissue in which tiles are randomly selected. For cancer gradation; Image data is converted into HS, Saturation and Value (HSV); Steroid / protein expression analysis is converted to cyan and cyan levels are calculated. Feature measurements are calculated for each tile based on color and texture and are performed arbitrarily but are affected by feature measurements. Finally, from further selection, the tiles are selected to combine low overlap and high feature measurements. |
| priorityDate |
2005-09-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |