Learning text-line localization with shared and local regression neural networks

Bastien Moysset 1, 2 Jérôme Louradour 2 Christopher Kermorvant 2 Christian Wolf 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Text line detection and localisation is a crucial step for full page document analysis, but still suffers from heterogeneity of real life documents. In this paper, we present a novel approach for text line localisation based on Convolutional Neural Networks and Multidimensional Long Short-Term Memory cells as a regressor in order to predict the coordinates of the text line bounding boxes directly from the pixel values. Targeting typically large images in document image analysis, we propose a new model using weight sharing over local blocks. We compare two strategies: directly predicting the four coordinates or predicting lower-left and upper-right points separately followed by matching. We evaluate our work on the highly unconstrained Maurdor dataset and show that our method outperforms both other machine learning and image processing methods.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01345713
Contributor : Christian Wolf <>
Submitted on : Friday, July 15, 2016 - 12:06:18 PM
Last modification on : Tuesday, February 26, 2019 - 4:35:36 PM

Identifiers

  • HAL Id : hal-01345713, version 1

Citation

Bastien Moysset, Jérôme Louradour, Christopher Kermorvant, Christian Wolf. Learning text-line localization with shared and local regression neural networks. International Conference on Frontiers in Handwriting Recognition, Oct 2016, Shenzhen, China. ⟨hal-01345713⟩

Share

Metrics

Record views

337