Extração de características e aprendizado não-supervisionados em imagens hiperespectrais

• Ano de defesa: 2020
• Autor(a) principal: Nakao, Eduardo Kazuo
• Orientador(a): Levada, Alexandre Luís Magalhães
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos; Câmpus São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação - PPGCC
• Palavras-chave em Português: Sensoriamento remoto; Imagens hiperespectrais; Reconhecimento de padrões; Extração de características; Métodos não-supervisionados
• Palavras-chave em Inglês: Remote sensing; Hyperspectral imagery; Pattern recognition; Feature extraction; Unsupervised methods
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAO
• Link de acesso: https://repositorio.ufscar.br/handle/ufscar/12826

Hyperspectral imagery have hundreds of bands and greater subtle differences discrimination capacity in compariosion with multispectral imagery, which benefits precision applications. However, inherent high spectral resolution and high band correlation in these imagery suggests curse of dimensionality occurrence possibility in pattern recognition processes. So, study of the effects of dimensionality reduction is relevant for this kind of image. Additionaly, is relevant to compare the behavior between linear and non linear reduction methods. In this scenario, the purpose of the present work is to analyze how unsupervised feature extraction and its different approaches affect an unsupervised learning task in hyperspectral imagery. In order to conduct such analysis, the algorithms Principal Component Analysis, Isometric Feature Mapping and Locally Linear Embedding were executed in a set of seven images. Clusterings by K-Means and Expectation Maximization algorithms were built under each execution. Performances were measured by Rand, Jaccard, Kappa, Entropy and Purity indexes and compared by Friedman and Nemenyi statistical tests. Hypothesis tests results have shown that, for 70% of the images, feature extraction deployment raised clustering performance significantly and, in 60% of those cases, nonlinear extraction yielded better results than linear