http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106203476-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-44 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24147 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2016-06-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2019-03-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2019-03-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-106203476-B |
| titleOfInvention | A method of pig head and tail contour recognition based on nearest neighbor classification and fuzzy algorithm |
| abstract | The invention discloses a pig head and tail outline recognition method based on nearest neighbor classification and fuzzy algorithm. Establish a rectangular coordinate system and a pig body contour information queue, detect and obtain the two endpoints of the long axis of the pig body, and convert them into a circular queue, and construct the first and second end contours, and change the coordinate positions of the first and second end contours into The complex number form is used for fast Fourier transform, and the modulus length of the coefficient is taken as the feature vector, and the sample standard library containing the pig head and tail sample feature set is established; for the pig image to be recognized, repeat the steps to obtain the feature vector, and calculate the Mahalanobis distance. Large arrangement, take a part to calculate the identification reference value, and obtain the identification result of pig head and tail contour through analysis. The invention enhances the robustness, so that the recognition work can be better completed under the condition that the image segmentation quality is poor and the contour information is relatively imperfect, and the traditional classifier can avoid the failure of the traditional classifier to identify the unsatisfactory contour information caused by the image itself. properly handle the situation. |
| priorityDate | 2016-06-24-04:00^^<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/CID25572 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415713197 |
Total number of triples: 14.