| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_452e625b5e37cfe3a61e33239649bded |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V2201-02 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-136
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V30-153
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-22
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-22 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-34
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-136
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
| filingDate |
2020-10-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2b5fccb8feaf5932099b4c2b26b391c4
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8290dc1e953b320980834fda0d6c076b
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b84a0794ff0cdcf81ce487be755b7667
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c26cd04f5e37321286d8650c56eedb04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2b791545fd154081ac9bd3c2227ffdcc
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_93389509002636b4037694f827c722ce
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2b3972da7390b266a13526ad0f318a2e |
| publicationDate |
2021-01-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-112270317-A |
| titleOfInvention |
A traditional digital water meter reading recognition method based on deep learning and frame difference method |
| abstract |
The invention discloses a water meter reading recognition method based on deep learning and frame difference method. The steps are as follows: step 1: collecting a large number of water meter pictures; Position the water meter character area in the water meter training set; Step 4: Perform character segmentation on the positioned water meter training set; Step 5: Use the AlexNet model to extract the water meter character features of the split water meter training set; Step 6: Send the water meter character features into Go to the fully connected network for training to get the training model; Step 7: Send the newly collected water meter image into the training model for recognition, and get the recognition result; Step 8: Save the original water meter image and label with the correct recognition result, and add Go to the training set and train the model again. The invention solves the problems of less data of different types of water meters, redundant useless data and low reading recognition accuracy. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116645682-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116645682-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113139541-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113647920-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114241725-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113269194-A |
| priorityDate |
2020-10-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |