Edge detection in multispectral remote sensing images

SIRIN T., SAGLAM M., Erer I., GOKMEN M., ERSOY O.

2nd International Conference on Recent Advances in Space Technologies, İstanbul, Türkiye, 9 - 11 Haziran 2005, ss.529-533 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/rast.2005.1512625
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.529-533
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

In this paper, we discuss edge detection by first using a clustering algorithm followed by a known edge detection filter such as Canny or Generalized Edge Detector (GED). We developed a new clustering method called Self-Organizing Global Ranking (SOGR). Comparative results with multispectral satellite images including SOGR, SOM and K-Means clustering methods are discussed. The results show that the two-stage algorithms are better than single stage edge detector algorithms.