We present an Automatic License Plate Recognition system designed around Convolutional Neural Networks (CNNs) and trained over synthetic plate images. We first design CNNs suitable for plate and character detection, sharing a common architecture and training procedure. Then, we generate synthetic images that account for the varying illumination and pose conditions encountered with real plate images and we use exclusively such synthetic images to train our CNNs. Experiments with real vehicle images captured in natural light with commodity imaging systems show precision and recall in excess of 93% despite our networks are trained exclusively on synthetic images.

Automatic License Plate Recognition with Convolutional Neural Networks Trained on Synthetic Data

FIANDROTTI, ATTILIO
;
2017-01-01

Abstract

We present an Automatic License Plate Recognition system designed around Convolutional Neural Networks (CNNs) and trained over synthetic plate images. We first design CNNs suitable for plate and character detection, sharing a common architecture and training procedure. Then, we generate synthetic images that account for the varying illumination and pose conditions encountered with real plate images and we use exclusively such synthetic images to train our CNNs. Experiments with real vehicle images captured in natural light with commodity imaging systems show precision and recall in excess of 93% despite our networks are trained exclusively on synthetic images.
2017
IEEE 19th International Workshop on Multimedia Signal Processing (MMSP 2017)
Luton, UK
16-18 October 2017
Proceding of Multimedia Signal Processing (MMSP), 2017 IEEE 19th International Workshop on
IEEE
Proceding of Multimedia Signal Processing (MMSP), 2017 IEEE 19th International Workshop on
1
6
978-1-5090-3649-3
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8122260
CNN; ALPR; license plate
BJORKLUND, TOMAS PER ROLF; FIANDROTTI, ATTILIO; Mauro, Annarumma; Gianluca, Francini; MAGLI, ENRICO
File in questo prodotto:
File Dimensione Formato  
08122260.pdf

Accesso riservato

Dimensione 603.49 kB
Formato Adobe PDF
603.49 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1769419
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 3
social impact