Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/58881
Type: Artigo
Title: Rank aggregation for pattern classifier selection in remote sensing images
Author: Faria, Fabio A.
Pedronette, Daniel C. G.
Santos, Jefersson A. dos
Rocha, Anderson
Torres, Ricardo da S.
Abstract: In the past few years, segmentation and classification techniques have become a cornerstone of many successful remote sensing algorithms aiming at delineating geographic target objects. One common strategy relies on using multiple complex features to guide the delineation process with the objective of gathering complementary information for improving classification results. However, a persistent problem in this approach is how to combine different and noncorrelated feature descriptors automatically. In this regard, one solution is to combine them through multiple classifier systems (MCSs) in which the diversity of simple/non-complex classifiers is an essential issue in the definition of appropriate strategies for classifier fusion. In this paper, we propose a novel strategy for selecting classifiers (whereby a classifier is taken as a pair of learning method plus image descriptor) to be combined in MCS. In the proposed solution, diversity measures are used to assess the degree of agreement/disagreement between pairs of classifiers and ranked lists are created to sort them according to their diversity score. Thereafter, the classifiers are also sorted according to their performance through different evaluation measures (e. g., kappa and tau indices). In the end, a rank aggregation method is proposed to select the most suitable classifiers based on both the diversity and the effectiveness performance of classifiers. The proposed fusion framework has targeted at coffee crop classification and urban recognition but it is general enough to be used in a variety of other pattern recognition problems. Experimental results demonstrate that the novel strategy yields good results when compared to several baselines while using fewer classifiers and being much more efficient.
In the past few years, segmentation and classification techniques have become a cornerstone of many successful remote sensing algorithms aiming at delineating geographic target objects. One common strategy relies on using multiple complex features to guid
Subject: Medidas de diversidade
Classificação de imagem
Café - Sensoriamento remoto
Fusão de classificadores
Country: Estados Unidos
Editor: Institute of Electrical and Electronics Engineers
Citation: Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Ieee-inst Electrical Electronics Engineers Inc, v. 7, n. 4, n. 1103, n. 1115, 2014.
Rights: Fechado
Identifier DOI: 10.1109/JSTARS.2014.2303813
Address: https://ieeexplore.ieee.org/document/6742729
Date Issue: 2014
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000335390000010.pdf2.1 MBAdobe PDFView/Open


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