Self-supervised Data Bootstrapping for Deep Optical Character Recognition of Identity Documents
This addresses the time-consuming task of identity verification at airports and borders, offering a practical solution with high accuracy, though it is incremental as it builds on existing neural network methods.
The paper tackles the problem of optical character recognition for identity documents, which is challenging due to high text variability and unknown fonts, by proposing a self-supervised bootstrapping approach that combines mined real data with synthetic data to train convolutional neural networks, achieving an average class-wise accuracy of 99.4% on a dataset with 74 character classes.
The essential task of verifying person identities at airports and national borders is very time consuming. To accelerate it, optical character recognition for identity documents (IDs) using dictionaries is not appropriate due to high variability of the text content in IDs, e.g., individual street names or surnames. Additionally, no properties of the used fonts in IDs are known. Therefore, we propose an iterative self-supervised bootstrapping approach using a smart strategy to mine real character data from IDs. In combination with synthetically generated character data, the real data is used to train efficient convolutional neural networks for character classification serving a practical runtime as well as a high accuracy. On a dataset with 74 character classes, we achieve an average class-wise accuracy of 99.4 %. In contrast, if we would apply a classifier trained only using synthetic data, the accuracy is reduced to 58.1 %. Finally, we show that our whole proposed pipeline outperforms an established open-source framework