Multi-Dimensional Connectionist Classification : Reading Text in One Step
- Offline handwriting recognition systems often use LSTM networks, trained with line- or word-images. Multi-line text makes it necessary to use segmentation to explicitly obtain these images. Skewed, curved, overlapping, incorrectly written text, or noise can lead to errors during segmentation of multi-line text and reduces the overall recognition capacity of the system. Last year has seen the introduction of deep learning methods capable of segmentation-free recognition of whole paragraphs. Our method uses Conditional Random Fields to represent text and align it with the network output to calculate a loss function for training. Experiments are promising and show that the technique is capable of training a LSTM multi-line text recognition system.
Author: | Martin Schall, Marc-Peter Schambach, Matthias O. FranzORCiDGND |
---|---|
URN: | urn:nbn:de:bsz:kon4-opus4-14348 |
URL: | https://ieeexplore.ieee.org/document/8395230 |
DOI: | https://doi.org/10.1109/DAS.2018.36 |
ISBN: | 978-1-5386-3346-5 |
Parent Title (English): | 13th IAPR International Workshop on Document Analysis Systems, 24 - 27. April 2018, Vienna, Austria |
Publisher: | IEEE |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2018 |
Release Date: | 2019/01/08 |
First Page: | 405 |
Last Page: | 410 |
Institutes: | Institut für Optische Systeme - IOS |
Open Access?: | Ja |
Relevance: | Keine peer reviewed Publikation (Wissenschaftlicher Artikel und Aufsatz, Proceeding, Artikel in Tagungsband) |
Licence (German): | ![]() |