Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition

被引:4
作者
Schirrmacher, Franziska [1 ]
Lorch, Benedikt [1 ]
Maier, Anatol [1 ]
Riess, Christian [1 ]
机构
[1] Univ Erlangen Nurnberg, Dept Comp Sci, IT Secur Infrastruct Lab, D-91058 Erlangen, Germany
关键词
License plate recognition; uncertainty; multitask learning;
D O I
10.1109/TITS.2023.3278533
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Learning-based algorithms for automated license plate recognition implicitly assume that the training and test data are well aligned. However, this may not be the case under extreme environmental conditions, or in forensic applications where the system cannot be trained for a specific acquisition device. Predictions on such out-of-distribution images have an increased chance of failing. But this failure case is oftentimes hard to recognize for a human operator or an automated system. Hence, in this work we propose to model the prediction uncertainty for license plate recognition explicitly. Such an uncertainty measure allows to detect false predictions, indicating an analyst when not to trust the result of the automated license plate recognition. In this paper, we compare three methods for uncertainty quantification on two architectures. The experiments on synthetic noisy or blurred low-resolution images show that the predictive uncertainty reliably finds wrong predictions. We also show that a multi-task combination of classification and super-resolution improves the recognition performance by 109\% and the detection of wrong predictions by 29 %.
引用
收藏
页码:9203 / 9216
页数:14
相关论文
共 53 条
[1]  
Agarwal S, 2017, Electronic Imaging, V29, P138, DOI [10.2352/issn.2470-1173.2017.7.mwsf-337, 10.2352/]
[2]   License plate recognition from still images and video sequences: A survey [J].
Anagnostopoulos, Christos-Nikolaos E. ;
Anagnostopoulos, Ioannis E. ;
Psoroulas, Ioannis D. ;
Loumos, Vassili ;
Kayafas, Eleftherios .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2008, 9 (03) :377-391
[3]  
Blundell C, 2015, PR MACH LEARN RES, V37, P1613
[4]   Multitask learning [J].
Caruana, R .
MACHINE LEARNING, 1997, 28 (01) :41-75
[5]  
Caruana R., 1993, Proceedings of the Tenth International Conference on Machine Learning, P41
[6]   Accelerating the Super-Resolution Convolutional Neural Network [J].
Dong, Chao ;
Loy, Chen Change ;
Tang, Xiaoou .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :391-407
[7]   Automatic License Plate Recognition (ALPR): A State-of-the-Art Review [J].
Du, Shan ;
Ibrahim, Mahmoud ;
Shehata, Mohamed ;
Badawy, Wael .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2013, 23 (02) :322-336
[8]  
Fort S, 2020, Arxiv, DOI [arXiv:1912.02757, 10.48550/arXiv.1912.02757, DOI 10.48550/ARXIV.1912.02757]
[9]  
Gal Y, 2016, PR MACH LEARN RES, V48
[10]  
Graves A., 2011, Neural Information Processing Systems, P2348, DOI [10.5555/2986459.2986721, DOI 10.5555/2986459.2986721]