| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_7dfdf9811f88ba4d268eea0768927ae2 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V30-10 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V30-153
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-62 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-34
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-32
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
| filingDate |
2021-05-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8ca76912ff1aa79c31d10f1686b8d7a0
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b544b34c7dc257f6c2b64c22971ddc9f |
| publicationDate |
2021-06-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-112990204-A |
| titleOfInvention |
Target detection method, device, electronic device and storage medium |
| abstract |
The present application discloses a target detection method, device, electronic device and storage medium. The specific implementation scheme is as follows: perform feature extraction on a first text image based on a feature extraction module to obtain a feature image; input the feature image into a first detection module to obtain a feature image. The probability map of the indented text area and the threshold map of the text area; the feature image is input into the second detection module to obtain a score map used to characterize whether the pixel belongs to the probability of the text area and a score map used to characterize the coordinates of the text area required for regression processing. Regression prediction map; take the detection network obtained by training based on the probability map of the indented text area, the threshold map of the text area, the score map and the regression prediction map as a target detection network; according to the target detection network , and detect the corresponding text area in the second text image, and locate the text area. By adopting the present application, the accuracy of target detection can be improved. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113378838-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113343987-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113343987-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113269280-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113591839-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113591839-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113313083-A |
| priorityDate |
2021-05-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |