Journal
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Volume -, Issue -, Pages 4489-4496Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ICPR48806.2021.9412868
Keywords
-
Categories
Funding
- Czech Technical University [SGS20/171/OHK3/3T/13]
- MEYS VVV project [CZ.02.1.01/0.0/0.0/16 019/0000765]
- Spanish Research project [TIN2017-89779-P]
- CERCA Programme/Generalitat de Catalunya
Ask authors/readers for more resources
The method proposed leverages weakly annotated images to enhance text extraction pipelines, by combining imprecise text transcriptions with weak annotations to generate nearly error-free instances of scene text for training, resulting in consistent improvements in accuracy for state-of-the-art recognition models.
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 method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as pseudo ground truth (PGT). The method is applied 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available