DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2023

DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition

Résumé

Unconstrained handwritten document recognition is a challenging computer vision task. It is traditionally handled by a two-step approach combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to the text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ dataset at page level, as well as double-page level with a CER of 3.53% and 3.69%, respectively. We also provide results for the RIMES dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN.

Dates et versions

hal-03621784 , version 1 (28-03-2022)

Identifiants

Citer

Denis Coquenet, Clément Chatelain, Thierry Paquet. DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, In press, ⟨10.1109/tpami.2023.3235826⟩. ⟨hal-03621784⟩
47 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More