Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documents

Bastien Moysset 1, 2 Pierre Adam 2 Christian Wolf 1 Jérôme Louradour 2
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : We describe a new method for detecting and localizing multiple objects in an image using context aware deep neural networks. Common architectures either proceed locally per pixel-wise sliding-windows, or globally by predicting object localizations for a full image. We improve on this by training a semi-local model to detect and localize objects inside a large image region, which covers an object or a part of it. Context knowledge is integrated, combining multiple predictions for different regions through a spatial context layer modeled as an LSTM network. The proposed method is applied to a complex problem in historical document image analysis, where we show that is capable of robustly detecting text lines in the images from the ANDAR-TL competition. Experiments indicate that the model can cope with difficult situations and reach the state of the art in Vision such as other deep models.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01178342
Contributor : Christian Wolf <>
Submitted on : Sunday, July 19, 2015 - 12:42:35 PM
Last modification on : Tuesday, February 26, 2019 - 4:35:36 PM

Identifiers

  • HAL Id : hal-01178342, version 1

Citation

Bastien Moysset, Pierre Adam, Christian Wolf, Jérôme Louradour. Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documents. ICDAR 2015 Workshop on Historical Document Imaging and Processing, Aug 2015, Nancy, France. ⟨hal-01178342⟩

Share

Metrics

Record views

257