Affordable Access

Uso de algoritmos genéticos no ajuste de parâmetros da segmentação de imagens

Authors
  • Espindola, Giovana Mira de
Publication Date
Jan 01, 2009
Source
Biblioteca Digital da Memória Científica do INPE
Keywords
Language
Portuguese
License
Unknown
External links

Abstract

Methods of image segmentation are important for remote sensing image analysis. Image segmentation tries to divide an image into spatially continuous, disjunctive and homogenous regions. Segmentation algorithms have many advantages over pixel-based image classifiers. Among the image segmentation techniques in the literature, region-growing techniques are being widely used for remote sensing applications, because they guarantee creating closed regions. Since most region-growing segmentation algorithms for remote sensing imagery need user-supplied parameters, one of the challenges for using these algorithms is selecting suitable parameters to ensure best quality results. This scientific research addresses this problem, proposing the use of genetic algorithms to select the best parameter settings of segmentation results. / Pages: 6861-6868

Report this publication

Statistics

Seen <100 times