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%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition


    Contributors:


    Publication date :

    2023-09-01


    Size :

    9969019 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    License plate recognition system and license plate recognition method

    CHEN SHU-HENG / LIAO CHIH-LUN / SHEN CHENG-FENG et al. | European Patent Office | 2020

    Free access

    LICENSE PLATE RECOGNITION SYSTEM AND LICENSE PLATE RECOGNITION METHOD

    CHEN SHU-HENG / LIAO CHIH-LUN / SHEN CHENG-FENG et al. | European Patent Office | 2020

    Free access

    LICENSE PLATE RECOGNITION DEVICE, LICENSE PLATE RECOGNITION METHOD, AND PROGRAM

    SUZUKI MARI / MASUDA MAKOTO / OISHI KEIKO | European Patent Office | 2020

    Free access

    LICENSE PLATE RECOGNITION SYSTEM, LICENSE PLATE RECOGNITION METHOD, AND PROGRAM

    KOJIMA YOHEI / NAKAYAMA HIROYUKI / OWARI NOBUYUKI et al. | European Patent Office | 2023

    Free access