Learning to detect, localize and recognize many text objects in document images from few examples

Autor: Christopher Kermorvant, Christian Wolf, Bastien Moysset

Publikováno v: International Journal on Document Analysis and Recognition
International Journal on Document Analysis and Recognition, Springer Verlag, In press, ⟨10.1007/s10032-018-0305-2⟩

International audience; The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa543f6bd41126a6edaa4eaa8c33bf11
https://doi.org/10.1007/s10032-018-0305-2

Adversarial Generation of Handwritten Text Images Conditioned on Sequences

Autor: Eloi Alonso, Bastien Moysset, Ronaldo Messina

Publikováno v: ICDAR

We propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. W

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::855bfcdd154ab7d87434f6c21c45d7c2

Full-Page Text Recognition: Learning Where to Start and When to Stop

Autor: Christopher Kermorvant, Bastien Moysset, Christian Wolf

Publikováno v: International Conference on Document Analysis and Recognition
International Conference on Document Analysis and Recognition, Nov 2017, Kyoto, Japan
ICDAR
14th IAPR International Conference on Document Analysis and Recognition
14th IAPR International Conference on Document Analysis and Recognition, Nov 2017, Kyoto, France. pp.871-876, ⟨10.1109/ICDAR.2017.147⟩

International audience; Text line detection and localization is a crucial step for full page document analysis, but still suffers from heterogeneity of real life documents. In this paper, we present a new approach for full page text recognition. Loca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7edf1190a903913bfc70f9eb74c7624e
http://arxiv.org/abs/1704.08628

Paragraph text segmentation into lines with Recurrent Neural Networks

Autor: Jérôme Louradour, Christopher Kermorvant, Bastien Moysset, Christian Wolf

Publikováno v: International Conference on Document Analysis and Recognition (ICDAR)
International Conference on Document Analysis and Recognition
International Conference on Document Analysis and Recognition, Aug 2015, Tunisia, Tunisia
ICDAR

International audience; The detection of text lines, as a first processing step, is critical in all Text Recognition systems. State-of-the-art methods to locate lines of text are based on handcrafted heuristics fine-tuned by the Image Processing Comm

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c75f213519032e97ffff8be8589f44da
https://hal.archives-ouvertes.fr/hal-01151760

A Comparison of Recognition Strategies for Printed/Handwritten Composite Documents

Autor: Christopher Kermorvant, Ronaldo Messina, Bastien Moysset

Publikováno v: ICFHR

Full-page segmentation and recognition of real-world documents is a challenging task, involving the segmentation of the images (graphics, text) and the subsequent recognition of the detected text-zones. Often those documents present zones with both w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3d074b436cad1ff66d0d899fa283dc90
https://doi.org/10.1109/icfhr.2014.34