Dissecting multi-line handwriting for multi-dimensional connectionist classification
- Multi-Dimensional Connectionist Classification is amethod for weakly supervised training of Deep Neural Networksfor segmentation-free multi-line offline handwriting recognition.MDCC applies Conditional Random Fields as an alignmentfunction for this task. We discuss the structure and patterns ofhandwritten text that can be used for building a CRF. Since CRFsare cyclic graphical models, we have to resort to approximateinference when calculating the alignment of multi-line text duringtraining, here in the form of Loopy Belief Propagation. This workconcludes with experimental results for transcribing small multi-line samples from the IAM Offline Handwriting DB which showthat MDCC is a competitive methodology.
Author: | Martin Schall, Marc-Peter Schambach, Matthias O. FranzORCiDGND |
---|---|
DOI: | https://doi.org/10.1109/ICDAR.2019.00015 |
ISBN: | 978-1-7281-3015-6 |
ISBN: | 978-1-7281-3014-9 |
Parent Title (English): | 15th International Conference on Document Analysis and Recognition (ICDAR 2019), 20-25 September, Sydney, Australia |
Publisher: | IEEE |
Document Type: | Conference Proceeding |
Language: | English |
Year of Publication: | 2020 |
Release Date: | 2020/01/15 |
Page Number: | 38 |
First Page: | 31 |
Note: | Volltextzugriff für Angehörige der Hochschule Konstanz möglich |
Institutes: | Institut für Optische Systeme - IOS |
Open Access?: | Nein |
Licence (German): | ![]() |