http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109801295-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ca46be4e68fa1f5a8b2ef4ab654c490a |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-143 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-187 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 |
| filingDate | 2018-12-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f3766cffeed90cf4b352825e0ec680dc http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9ca93666d8ace72fbb1e711401fea34d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_90ec02ea5eb770c15ee9a02b4ebabea3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b2ee44863379f1de05a08d11f55e06cb |
| publicationDate | 2019-05-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-109801295-A |
| titleOfInvention | Image segmentation method based on quadratic restricted region growing method |
| abstract | The invention belongs to the technical field of image segmentation, and in particular relates to an image segmentation method based on a secondary restricted region growing method, comprising: step 1, converting an image from RGB space to Lab space; step 2, setting the number of seed points and a threshold, throwing the seed points, Use the restricted area growing method and the threshold to mark the image; Step 3, traverse the entire image in raster scan order for secondary restricted area growth, and mark the unmarked points; Step 4, Calculate the superpixel blocks divided in the previous two steps In step 5, set the expected number of classifications, and use the simulated annealing algorithm based on hidden Markov model, Ising model and Gaussian function to merge the superpixel results obtained in step 3 to obtain the final segmentation. result. The image segmentation method of the present invention uses the restricted region growing method, so that various sub-points are grown within the image range of the step size multiplied by the step size, which reduces the computational workload and improves the running speed. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110619643-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110619643-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110910400-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110717915-A |
| priorityDate | 2018-12-26-04:00^^<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/CID3001055 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419580923 |
Total number of triples: 21.