Comparison of a new algorithm with the supervised classifications


Emrahoglu N. , Yegingil I., Pestemalci V. , Senkal O. , Kandirmaz H.

INTERNATIONAL JOURNAL OF REMOTE SENSING, cilt.24, ss.649-655, 2003 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 24 Konu: 4
  • Basım Tarihi: 2003
  • Doi Numarası: 10.1080/01431160210145597
  • Dergi Adı: INTERNATIONAL JOURNAL OF REMOTE SENSING
  • Sayfa Sayısı: ss.649-655

Özet

In this study, a new classification algorithm in which only the selected pixels have been attempted to be classified (selected pixels classification: SPC) has been introduced and compared with the well known supervised classification methods such as maximum likelihood, minimum distance, nearest neighbour and condensed nearest neighbour. To examine the algorithm, Landsat Thematic Mapper (TM) data have been used to classify the crop cover in the selected region. It is clearly demonstrated that the SPC method has the higher accuracy with comparable CPU times.