Álvaro Muñoz, F.; Sánchez Peiró, JA.; Benedí Ruiz, JM. (2014). Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks. IEEE. https://doi.org/10.1109/ICPR.2014.507
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10251/68388
Title:
|
Offline Features for Classifying Handwritten Math Symbols with Recurrent Neural Networks
|
Author:
|
Álvaro Muñoz, Francisco
Sánchez Peiró, Joan Andreu
Benedí Ruiz, José Miguel
|
UPV Unit:
|
Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació
|
Issued date:
|
|
Abstract:
|
In mathematical expression recognition, symbol
classification is a crucial step. Numerous approaches for recognizing
handwritten math symbols have been published, but most
of them are either an online approach or a ...[+]
In mathematical expression recognition, symbol
classification is a crucial step. Numerous approaches for recognizing
handwritten math symbols have been published, but most
of them are either an online approach or a hybrid approach.
There is an absence of a study focused on offline features for
handwritten math symbol recognition. Furthermore, many papers
provide results difficult to compare. In this paper we assess the
performance of several well-known offline features for this task.
We also test a novel set of features based on polar histograms and
the vertical repositioning method for feature extraction. Finally,
we report and analyze the results of several experiments using
recurrent neural networks on a large public database of online
handwritten math expressions. The combination of online and
offline features significantly improved the recognition rate.
[-]
|
Subjects:
|
Handwritten Math Symbols
,
Recurrent Neural Networks
|
Copyrigths:
|
Reserva de todos los derechos
|
ISBN:
|
9781479952083
|
Source:
|
International Conference on Pattern Recognition. (issn:
1051-4651
)
|
DOI:
|
10.1109/ICPR.2014.507
|
Publisher:
|
IEEE
|
Publisher version:
|
http://dx.doi.org/10.1109/ICPR.2014.507
|
Conference name:
|
22nd International Conference on Pattern Recognition (ICPR 2014)
|
Conference place:
|
Stockholm, Sweden
|
Conference date:
|
August 24-28, 2015
|
Project ID:
|
info:eu-repo/grantAgreement/MINECO//TIN2012-37475-C02-01/ES/SEARCH IN TRANSCRIBED MANUSCRIPTS AND DOCUMENT AUGMENTATION/
info:eu-repo/grantAgreement/EC/FP7/600707/EU/tranScriptorium/
info:eu-repo/grantAgreement/ME//AP2009-4363/ES/AP2009-4363/
info:eu-repo/grantAgreement/Generalitat Valenciana//PROMETEO09%2F2009%2F014/ES/Adaptive learning and multimodality in pattern recognition (Almapater)/
|
Thanks:
|
This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through ...[+]
This work was partially supported by the Spanish MEC under the STraDA research project (TIN2012-37475-C02-01) and the FPU grant (AP2009-4363), by the Generalitat Valenciana under the grant Prometeo/2009/014, and through the EU 7th Framework Programme grant tranScriptorium (Ref: 600707).
[-]
|
Type:
|
Comunicación en congreso
|