@InProceedings{Correa:2021:CoOpCh,
author = "Correa, Iago Louren{\c{c}}o",
affiliation = "{Federal University of Rio Grande (FURG)}",
title = "Combination of Optical Character Recognition Engines for Documents
Containing Sparse Text and Alphanumeric Codes",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "optical character recognition, classifier combination, pattern
recognition, tesseract, median string.",
abstract = "Many companies that buy machines, parts, or tools retain documents
such as notes, receipts, forms, or instruction manuals over the
years, and they may find themselves in need of digitizing these
accumulated documents. Thus, when using optical character
recognition (OCR) systems in these documents, it is possible to
note that these systems can present two main difficulties. The
first is to locate the sparse text in a non-continuous way, and
the second is to match words that are closer to codes and less to
words in human language. Although there are many works in the
literature about sparse texts, such as forms and tables, there is
usually not much concern about the issue with codes in which one
can not rely on dictionaries or even both problems together.
Therefore, to correct this issue without having to search for
extensive databases or conduct training and development of new
models, this work proposed to take advantage of pre-trained models
of OCR such as from the Tesseract engine or the Google Cloud's
Vision API. In order to do so, we proposed the exploration of
combination strategies, including a new one based on median
string. The experimental results achieved up to 3.09% improvement
in character accuracy and 1.16% in word accuracy in comparison to
the best individual performances from the engines when our method
based on string combination was adopted.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00048",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00048",
language = "en",
ibi = "8JMKD3MGPEW34M/45BRTJ8",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45BRTJ8",
targetfile = "Paper ID 28.pdf",
urlaccessdate = "2024, May 06"
}