Publication:
A survey of handwritten character recognition with MNIST and EMNIST

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorBaldominos Gómez, Alejandro
dc.contributor.authorSáez Achaerandio, Yago
dc.contributor.authorIsasi, Pedro
dc.contributor.funderMinisterio de Educación, Cultura y Deporte (España)es
dc.date.accessioned2023-09-14T09:38:00Z
dc.date.available2023-09-14T09:38:00Z
dc.date.issued2019-08-01
dc.descriptionThis article belongs to the Special Issue Computer Vision and Pattern Recognition in the Era of Deep Learning.en
dc.description.abstractThis paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST's. In this paper, EMNIST is explained and some results are surveyed.en
dc.format.extent16
dc.identifier.bibliographicCitationBaldominos, A., Saez, Y., & Isasi, P. (2019). A survey of handwritten character recognition with MNIST and EMNIST. Applied sciences, 9(15), 3169en
dc.identifier.doihttps://doi.org/10.3390/app9153169
dc.identifier.issn2076-3417
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue15, 3169
dc.identifier.publicationlastpage16
dc.identifier.publicationtitleApplied Sciencesen
dc.identifier.publicationvolume9
dc.identifier.urihttps://hdl.handle.net/10016/38329
dc.identifier.uxxiAR/0000023979
dc.language.isoengen
dc.publisherMDPIen
dc.relation.projectIDGobierno de España. FPU13/03917es
dc.rights© 2019 by the authors.en
dc.rightsAtribución 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subject.ecienciaInformáticaes
dc.subject.ecienciaRobótica e Informática Industriales
dc.subject.otherArtificial intelligenceen
dc.subject.otherCharacter recognitionen
dc.subject.otherComputer visionen
dc.subject.otherImage classificationen
dc.subject.otherMnisten
dc.subject.otherSurveyen
dc.titleA survey of handwritten character recognition with MNIST and EMNISTen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Survey_AS_2019.pdf
Size:
587.08 KB
Format:
Adobe Portable Document Format
Download
Collections