Product Details
V3: LPR algoritmy adaptované pro Latinskou Ameriku
Created: 2023
English title
V3: LPR algorithms adapted for Latin America
Type
software
License
required - licence fee
Authors
Juhas Miroslav, Ing. (CAMEA)
Honec Peter, Ing., Ph.D. (CAMEA)
Klobušníková Zuzana (CAMEA)
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT)
Šustek Jiří, Ing. (CAMEA)
Ševčík Václav, Ing. (CAMEA)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Hradiš Michal, Ing., Ph.D. (COGNITECHNA)
Nosko Svetozár, Ing. (DCGM FIT BUT)
Honec Peter, Ing., Ph.D. (CAMEA)
Klobušníková Zuzana (CAMEA)
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT)
Šustek Jiří, Ing. (CAMEA)
Ševčík Václav, Ing. (CAMEA)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Hradiš Michal, Ing., Ph.D. (COGNITECHNA)
Nosko Svetozár, Ing. (DCGM FIT BUT)
Keywords
ANPR, LPR, Neural Network, Localization, SSD/YOLO, CTC, High Precision, High Recall, Brazil, South America
Description
Algorithms for automatic recognition and reading of license plates operating with high accuracy, adapted and optimized for the region of Brasil and Latin America. The algorithm is based on neural networks (CNNs) and the adaptation to the region of Brasil and Latin America was achieved through re-training of the network exploiting the data set collected in Latin America.
Projects
WIM Latin America (EG20_321/0025242)
Research groups
Computer Graphics Research Group (VZ GRAPH)
Departments