http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-105809188-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V2201-03 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-285 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-462 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2016-02-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2017-08-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2017-08-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-105809188-B |
titleOfInvention | An Image Recognition Method of Fungal Keratitis Based on AMBP Improved Algorithm |
abstract | The invention discloses an image recognition method for fungal keratitis based on the AMBP improved algorithm, comprising the following steps: using the RX abnormal detection algorithm to preprocess and binarize the mycelium image and the normal corneal nerve image, and then perform expansion and corrosion processing , strengthen the hyphae and neural characteristic information in the image; improve the AMBP algorithm, calculate the mean value of the pixels in the analysis window except the central pixel, as a new parameter; calculate the average value and median value of the pixels in the analysis window respectively pixels, calculate the variance between the two and the rest of the pixels in the analysis window, and use the difference as a new discriminant condition to extract image texture features; use the extracted features to train a classifier, and use this classifier to identify images acquired by confocal microscopes. Identify nerves and hyphae in images. |
priorityDate | 2016-02-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 24.