Abstract
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach exploits an arbitrary existing end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. A process that includes imprecise transcription to annotation matching and edit distance guided neighbourhood search produces nearly error-free, localised instances of scene text, which we treat as pseudo ground truth used for training. We apply the method to two weakly-annotated datasets and show that the process consistently improves the accuracy of a state of the art recognition model across different benchmark datasets (image domains) as well as providing a significant performance boost on the same dataset.
Abstract (translated)
URL
https://arxiv.org/abs/2007.03098
