Discovering relevant spatial filterbanks for VHR image classification

Devis Tuia*, Mauro Dalla Mura, Michele Volpi, Remi Flamary, Alain Rakotomamonjy

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

2 Citations (Scopus)

Abstract

In very high resolution (VHR) image classification it is common to use spatial filters to enhance the discrimination among landuses related to similar spectral properties but different spatial characteristics. However, the filters types that can be used are numerous (e.g. textural, morphological, Gabor, wavelets, etc.) and the user must pre-select a family of features, as well as their specific parameters. This results in features spaces that are high dimensional and redundant, thus requiring long and suboptimal feature selection phases. In this paper, we propose to discover the relevant filters as well as their parameters with a sparsity promoting regular-ization and an active set algorithm that iteratively adds to the model the most promising features. This way, we explore the filters/parameters input space efficiently (which is infinitely large for continuous parameters) and construct the optimal filterbank for classification without any other information than the types of filters to be used.

Original languageEnglish
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages3212-3215
Number of pages4
ISBN (Electronic)9784990644109
Publication statusPublished - Dec 2012
Externally publishedYes
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference/symposium

Conference/symposium21st International Conference on Pattern Recognition, ICPR 2012
Country/TerritoryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Dive into the research topics of 'Discovering relevant spatial filterbanks for VHR image classification'. Together they form a unique fingerprint.

Cite this