Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset
This work addresses a specific, incremental problem for transportation management and surveillance systems by improving recognition of non-standard enlarged license plates, though it is limited to this domain and builds on existing text recognition methods.
The paper tackles the problem of recognizing enlarged license plates on large vehicles, which are challenging due to non-standard positions, sizes, and noisy backgrounds, by proposing a Disentangled Generation Network (DGNet) that disentangles text and background generation to enhance data diversity and integrity, achieving robust recognition results as demonstrated on a new dataset of 9342 images across three text recognition frameworks.
License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks.