Skip to Main content Skip to Navigation
Conference papers

Transfer Learning for Handwriting Recognition on Historical Documents

Adeline Granet 1, 2, 3 Emmanuel Morin 1, 3 Harold Mouchère 1, 2 Solen Quiniou 1, 3 Christian Viard-Gaudin 1, 2 
2 IPI - Image Perception Interaction
LS2N - Laboratoire des Sciences du Numérique de Nantes
3 TALN - Traitement Automatique du Langage Naturel
LS2N - Laboratoire des Sciences du Numérique de Nantes
Abstract : In this work, we investigate handwriting recognition on new historical handwritten documents using transfer learning. Establishing a manual ground-truth of a new collection of handwritten documents is time consuming but needed to train and to test recognition systems. We want to implement a recognition system without performing this annotation step. Our research deals with transfer learning from heterogeneous datasets with a ground-truth and sharing common properties with a new dataset that has no ground-truth. The main difficulties of transfer learning lie in changes in the writing style, the vocabulary, and the named entities over centuries and datasets. In our experiment, we show how a CNN-BLSTM-CTC neural network behaves, for the task of transcribing handwritten titles of plays of the Italian Comedy, when trained on combinations of various datasets such as RIMES, Georges Washington, and Los Esposalles. We show that the choice of the training datasets and the merging methods are determinant to the results of the transfer learning task.
Complete list of metadata
Contributor : Harold Mouchère Connect in order to contact the contributor
Submitted on : Wednesday, December 16, 2020 - 9:06:49 PM
Last modification on : Friday, August 5, 2022 - 2:54:51 PM
Long-term archiving on: : Wednesday, March 17, 2021 - 8:14:10 PM


Files produced by the author(s)


  • HAL Id : hal-01681126, version 1


Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, Christian Viard-Gaudin. Transfer Learning for Handwriting Recognition on Historical Documents. 7th International Conference on Pattern Recognition Applications and Methods (ICPRAM), Jan 2018, Madeira, Portugal. ⟨hal-01681126⟩



Record views


Files downloads