Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/329519
Type: Artigo
Title: Optimum-path Forest Based On K-connectivity: Theory And Applications
Optimum-path forest based on k-connectivity : theory and applications
Author: Papa, João Paulo
Nachif Fernandes, Silas Evandro
Falcao, Alexandre Xavier
Abstract: Graph-based pattern recognition techniques have been in the spotlight for many years, since there is a constant need for faster and more effective approaches. Among them, the Optimum-Path Forest (OPF) framework has gained considerable attention in the last years, mainly due to the promising results obtained by OPF-based classifiers, which range from unsupervised, semi-supervised and supervised learning. In this paper, we consider a deeper theoretical explanation concerning the supervised OPF classifier with k-neighborhood (OPFk), as well as we proposed two different training and classification algorithms that allow OPFk to work faster. The experimental validation against standard OPF and Support Vector Machines also validates the robustness of OPFk in real and synthetic datasets. (C) 2016 Elsevier B.V. All rights reserved.
Graph-based pattern recognition techniques have been in the spotlight for many years, since there is a constant need for faster and more effective approaches. Among them, the Optimum-Path Forest (OPF) framework has gained considerable attention in the las
Subject: Pattern Classification
Optimum-path Forest
Supervised Learning
Reconhecimento de padrões
Floresta de caminhos ótimos
Aprendizado de máquina
Inteligência artificial
Country: Países Baixos
Editor: Elsevier
Citation: Pattern Recognition Letters. Elsevier Science Bv, v. 87, p. 117 - 126, 2017.
Rights: fechado
Fechado
Identifier DOI: 10.1016/j.patrec.2016.07.026
Address: https://www.sciencedirect.com/science/article/pii/S0167865516302057
Date Issue: 2017
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000395616700015.pdf1.66 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.