TY  - CONF
AU  - Manuel Carbonell
AU  - Joan Mas
AU  - Mauricio Villegas
AU  - Alicia Fornes
AU  - Josep Llados
A2  - ICDAR WML
PY  - 2019//
TI  - End-to-End Handwritten Text Detection and Transcription in Full Pages
BT  - 2nd International Workshop on Machine Learning
SP  - 29
EP  - 34
VL  - 5
KW  - Handwritten Text Recognition
KW  - Layout Analysis
KW  - Text segmentation
KW  - Deep Neural Networks
KW  - Multi-task learning
N2  - When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affectthe transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assumesegmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
UR  - https://ieeexplore.ieee.org/document/8892971
L1  - http://refbase.cvc.uab.es/files/CMV2019.pdf
UR  - http://dx.doi.org/10.1109/ICDARW.2019.40077
N1  - DAG; 600.140; 601.311; 600.140
ID  - Manuel Carbonell2019
ER  -