Header logo is

Recent trends in classification of remote sensing data: active and semisupervised machine learning paradigms

2010

Conference Paper

ei


This paper addresses the recent trends in machine learning methods for the automatic classification of remote sensing (RS) images. In particular, we focus on two new paradigms: semisupervised and active learning. These two paradigms allow one to address classification problems in the critical conditions where the available labeled training samples are limited. These operational conditions are very usual in RS problems, due to the high cost and time associated with the collection of labeled samples. Semisupervised and active learning techniques allow one to enrich the initial training set information and to improve classification accuracy by exploiting unlabeled samples or requiring additional labeling phases from the user, respectively. The two aforementioned strategies are theoretically and experimentally analyzed considering SVM-based techniques in order to highlight advantages and disadvantages of both strategies.

Author(s): Bruzzone, L. and Persello, C.
Pages: 3720-3723
Year: 2010
Month: July
Day: 0
Publisher: IEEE

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/IGARSS.2010.5651236
Event Name: IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2010)
Event Place: Honolulu, HI, USA

Address: Piscataway, NJ, USA
Digital: 0
ISBN: 978-1-4244-9565-8

Links: Web

BibTex

@inproceedings{BruzzoneP2010_2,
  title = {Recent trends in classification of remote sensing data: active and semisupervised machine learning paradigms },
  author = {Bruzzone, L. and Persello, C.},
  pages = {3720-3723 },
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2010},
  doi = {10.1109/IGARSS.2010.5651236  },
  month_numeric = {7}
}