loading
Documents

Research.Publish.Connect.

Paper

Authors: Geoffrey Roman-Jimenez ; Christian Viard-Gaudin ; Adeline Granet and Harold Mouchére

Affiliation: University of Nantes, France

ISBN: 978-989-758-276-9

Keyword(s): Handwritting Recognition, Image Generation, Digit Detection, Deep Neural Networks, Knowledge Transfer.

Related Ontology Subjects/Areas/Topics: Classification ; Pattern Recognition ; Theory and Methods

Abstract: Despite recent achievements in handwritten text recognition due to major advances in deep neural networks, historical handwritten documents analysis is still a challenging problem because of the requirement of large annotated training database. In this context, knowledge transfer of neural networks pre-trained on already available labeled data could allow us to process new collections of documents. In this study, we focus on localization of structures at the word-level, distinguishing words from numbers, in unlabeled handwritten documents. We based our approach on a transductive transfer learning paradigm using a deep convolutional neural network pre-trained on artificial labeled images randomly generated with strokes, word and number patches. We designed our model to predict a mask of the structures positions at the pixel-level, directly from the pixel values. The model has been trained using 100,000 generated images. The classification performances of our model were assessed by usin g randomly generated images coming from a different set of images of words and digits. At the pixel level, the averaged accuracy of the proposed structures detection system reach 96.1%. We evaluated the transfer capability of our model on two datasets of real handwritten documents unseen during the training. Results show that our model is able to distinguish most ”digits” structures from ”word” structures while avoiding other various structures present in the documents, showing the good transferability of the system to real documents. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.157.61.68

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Roman-Jimenez, G.; Viard-Gaudin, C.; Granet, A. and Mouchére, H. (2018). Transfer Learning for Structures Spotting in Unlabeled Handwritten Documents using Randomly Generated Documents.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 417-425. DOI: 10.5220/0006598204170425

@conference{icpram18,
author={Geoffrey Roman{-}Jimenez. and Christian Viard{-}Gaudin. and Adeline Granet. and Harold Mouchére.},
title={Transfer Learning for Structures Spotting in Unlabeled Handwritten Documents using Randomly Generated Documents},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={417-425},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006598204170425},
isbn={978-989-758-276-9},
}

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Transfer Learning for Structures Spotting in Unlabeled Handwritten Documents using Randomly Generated Documents
SN - 978-989-758-276-9
AU - Roman-Jimenez, G.
AU - Viard-Gaudin, C.
AU - Granet, A.
AU - Mouchére, H.
PY - 2018
SP - 417
EP - 425
DO - 10.5220/0006598204170425

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.