Automatic recognition of Colombian car license plates using convolutional neural networks and Chars74k database

A methodology for the automatic recognition of Colombian car license plates using convolutional neural networks is proposed. One of the biggest challenges when using onvolutional neural network is the demand for large amounts of samples for training. In this work, we show that if we do not have enou...

Full description

Autores:
Arroyo-Pérez, D E
Álvarez-Canchila, O I
Patiño-Saucedo, A
Rostro González, H
Patiño Vanegas, Alberto
Tipo de recurso:
Fecha de publicación:
2020
Institución:
Universidad Tecnológica de Bolívar
Repositorio:
Repositorio Institucional UTB
Idioma:
eng
OAI Identifier:
oai:repositorio.utb.edu.co:20.500.12585/9384
Acceso en línea:
https://hdl.handle.net/20.500.12585/9384
Palabra clave:
Character Recognition
Tesseract
Template Matching
Convolution
Database systems
Image processing
License plates (automobile)
Colombians
Large amounts
Vehicle license plates
Convolutional neural networks
Rights
openAccess
License
http://creativecommons.org/licenses/by-nc/4.0/
Description
Summary:A methodology for the automatic recognition of Colombian car license plates using convolutional neural networks is proposed. One of the biggest challenges when using onvolutional neural network is the demand for large amounts of samples for training. In this work, we show that if we do not have enough images of vehicle license plates to carry out the training, we can complement it with databases of letters and numbers that are not extracted from cars. The network was trained with the Chars74k database and images of characters extracted from plates of Colombian automobiles. The Chars74k contains approximately 74000 images of all the letters of the Spanish alphabet and all digits from 0 to 9. From chars74k database we have chosen 33849, because the Colombian plates have only uppercase letters and digits. Only 3549 (about 10% of the total) images of characters extracted manually from plates of Colombian automobiles were added. At the input of the convolutional neural network, 70% of the images were used for training, 20% for validation and 10% for testing and the resulting validation accuracy was above 99%. By making a preliminary test on Colombian plates never before used in training, a percentage of correctly recognized plates above 98% was achieved.