Inducing Contextual Classifications With Kernel Functions Into Support Vector Machines

Autor(es)

Negri, Rogerio Galante ^[1] ; da Silva, Erivaldo Antonio ^[2] ; Casaca, Wallace ^[3]

Afiliação do(s) autor(es)

^[1] UNESP, Inst Ciencia & Tecnol, BR-12247004 Sao Jose Dos Campos - Brazil

^[2] UNESP, Fac Ciencia & Tecnol, BR-19060900 Presidente Prudente - Brazil

^[3] Univ Estadual Paulista, Campus Expt Rosana, BR-19274000 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE Geoscience and Remote Sensing Letters; v. 15, n. 6, p. 962-966, JUN 2018.
• Citações Web of Science: 2

Resumo

Kernel functions have revolutionized theory and practice in the field of pattern recognition, especially to perform image classification. Besides giving rise to nonlinear variants of the well-known support vector machine (SVM), these functions have also been successfully used to classify nonvectorial data (e.g., graphs and collection of sets), in which customized metrics are created to precisely measure the similarity among such contextual data entities. This letter introduces two cantext-inspired kernel functions as new SVM-driven methods for remote sensing image classification. In contrast to the existing SVM-based approaches that assume only multiattribute vectors as representative features in a high-dimensional space, the proposed models formally establish comparisons between the entire sets of context-given data, thus employing these contextual measurements to drive the classification. More precisely, stochastic distances as well as hypothesis tests are conveniently handled and ``kernelized{''} to build our models. A complete battery of experiments involving both remote sensing and real-world images is conducted to validate the performance of the proposed kernels against various well-established SVM-based methods. (AU)

• Processo FAPESP: 14/08822-2 - Desenvolvimento de metodologia para a extração de feições cartográficas a partir de imagens digitais das superfícies dos planetas Terra, Marte e Mercúrio
• Beneficiário: Erivaldo Antonio da Silva
• Linha de fomento: Auxílio à Pesquisa - Regular
• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: José Alberto Cuminato
• Linha de fomento: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 17/03595-6 - Desenvolvimento de metodologia para detecção de slope streaks na superfície de Marte
• Beneficiário: Erivaldo Antonio da Silva
• Linha de fomento: Auxílio à Pesquisa - Regular
• Processo FAPESP: 14/14830-8 - Estudo e desenvolvimento de novas funções Kernel com aplicações em classificação de imagens de sensoriamento remoto
• Beneficiário: Rogério Galante Negri
• Linha de fomento: Auxílio à Pesquisa - Regular