EXTENDED EXTINCTION PROFILE FOR THE CLASSIFICATION OF HYPERSPECTRAL IMAGES

Autor(es)

Ghamisi, Pedram ; Souza, Roberto ; Benediktsson, Jon A. ; Zhu, Xiao Xiang ; Rittner, Leticia ; Lotufo, Roberto ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2016 8TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS); v. N/A, p. 4-pg., 2016-01-01.

Resumo

In this paper, a novel approach is proposed for the spectralspatial classification of hyperspectral images. The proposed classification approach is based on a novel filtering technique, here entitled as extended extinction profile (EEP). The proposed classification approach is applied on two well-known data sets: Pavia University and Indian Pines; and the obtained results have been compared with one of the strongest filtering approaches in the literature named extended attribute profile (EAP). Results confirm that the proposed approach is able to efficiently extract spatial information for the classification of hyperspectral images. (AU)

• Processo FAPESP: 15/12127-0 - Max-trees aplicadas a segmentação de imagens médicas
• Beneficiário: Roberto Medeiros de Souza
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 13/23514-0 - Árvore Máxima: teoria, algoritmos e aplicações
• Beneficiário: Roberto Medeiros de Souza
• Modalidade de apoio: Bolsas no Brasil - Doutorado