Publication Details
Holistic Recognition of Low Quality License Plates by CNN using Track Annotated Data
Sochor Jakub, Ing. (DCGM FIT BUT)
Juránek Roman, Ing., Ph.D. (DCGM FIT BUT)
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT)
Maršík Lukáš, Ing. (DCGM FIT BUT)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
holistic license plate recognition, convolutional neural network, low resolution, low quality
This work is focused on recognition of license plates in low resolution and low quality images. We present a methodology for collection of real world (non-synthetic) dataset of low quality license plate images with ground truth transcriptions. Our approach to the license plate recognition is based on a Convolutional Neural Network which holistically processes the whole image, avoiding segmentation of the license plate characters. Evaluation results on multiple datasets show that our method significantly outperforms other free and commercial solutions to license plate recognition on the low quality data. To enable further research of low quality license plate recognition, we make the datasets publicly available.
@INPROCEEDINGS{FITPUB11491, author = "Jakub \v{S}pa\v{n}hel and Jakub Sochor and Roman Jur\'{a}nek and Adam Herout and Luk\'{a}\v{s} Mar\v{s}\'{i}k and Pavel Zem\v{c}\'{i}k", title = "Holistic Recognition of Low Quality License Plates by CNN using Track Annotated Data", pages = "1--6", booktitle = "International Workshop on Traffic and Street Surveillance for Safety and Security (AVSS 2017)", year = 2017, location = "Lecce, IT", publisher = "IEEE Computer Society", ISBN = "978-1-5386-2939-0", doi = "10.1109/AVSS.2017.8078501", language = "english", url = "https://www.fit.vut.cz/research/publication/11491" }