@InProceedings{Julca-AguilarMaiaHira:2017:TeClCo,
author = "Julca-Aguilar, Frank Dennis and Maia, Ana Lucia Lima Marreiros and
Hirata, Nina Sumiko Tomita",
affiliation = "{University of S{\~a}o Paulo} and State University of Feira de
Santana, University of S{\~a}o Paulo and {University of S{\~a}o
Paulo}",
title = "Text/non-text classification of connected components in document
images",
booktitle = "Proceedings...",
year = "2017",
editor = "Torchelsen, Rafael Piccin and Nascimento, Erickson Rangel do and
Panozzo, Daniele and Liu, Zicheng and Farias, Myl{\`e}ne and
Viera, Thales and Sacht, Leonardo and Ferreira, Nivan and Comba,
Jo{\~a}o Luiz Dihl and Hirata, Nina and Schiavon Porto, Marcelo
and Vital, Creto and Pagot, Christian Azambuja and Petronetto,
Fabiano and Clua, Esteban and Cardeal, Fl{\'a}vio",
organization = "Conference on Graphics, Patterns and Images, 30. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "text segmentation, connected component, convolutional neural
network.",
abstract = "Text segmentation is an important problem in document analysis
related applications. We address the problem of classifying
connected components of a document image as text or non-text.
Inspired from previous works in the literature, besides common
size and shape related features extracted from the components, we
also consider component images, without and with context
information, as inputs of the classifiers. Muli-layer perceptrons
and convolutional neural networks are used to classify the
components. High precision and recall is obtained with respect to
both text and non-text components.",
conference-location = "Niter{\'o}i, RJ, Brazil",
conference-year = "17-20 Oct. 2017",
doi = "10.1109/SIBGRAPI.2017.66",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2017.66",
language = "en",
ibi = "8JMKD3MGPAW/3PFS8CH",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3PFS8CH",
targetfile = "PID4960469.pdf",
urlaccessdate = "2024, Apr. 27"
}