Text Recognition -- Real World Data and Where to Find Them
This work addresses the challenge of limited labeled data for text recognition in real-world applications, offering an incremental improvement over existing methods.
The paper tackles the problem of improving text extraction pipelines by exploiting weakly annotated images to generate pseudo ground truth, resulting in an average accuracy improvement of 3.7% across benchmark datasets and 24.5% on a specific weakly annotated dataset.
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The proposed method includes matching of imprecise transcription to weak annotations and edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as "pseudo ground truth" (PGT). We apply the method to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7~\% on average, across different benchmark datasets (image domains) and 24.5~\% on one of the weakly annotated datasets.