SVM active learning approach for image classification using spatial information

Edoardo Pasolli, Farid Melgani, Devis Tuia, Fabio Pacifici, William J. Emery

Research output: Contribution to journalArticleAcademicpeer-review

140 Citations (Scopus)


In the last few years, active learning has been gaining growing interest in the remote sensing community in optimizing the process of training sample collection for supervised image classification. Current strategies formulate the active learning problem in the spectral domain only. However, remote sensing images are intrinsically defined both in the spectral and spatial domains. In this paper, we explore this fact by proposing a new active learning approach for support vector machine classification. In particular, we suggest combining spectral and spatial information directly in the iterative process of sample selection. For this purpose, three criteria are proposed to favor the selection of samples distant from the samples already composing the current training set. In the first strategy, the Euclidean distances in the spatial domain from the training samples are explicitly computed, whereas the second one is based on the Parzen window method in the spatial domain. Finally, the last criterion involves the concept of spatial entropy. Experiments on two very high resolution images show the effectiveness of regularization in spatial domain for active learning purposes.

Original languageEnglish
Article number6531640
Pages (from-to)2217-2223
Number of pages7
JournalIEEE Transactions on Geoscience and Remote Sensing
Issue number4
Publication statusPublished - Apr 2014
Externally publishedYes


  • Active learning
  • Image classification
  • Spatial information
  • Support vector machine (SVM)
  • Very high resolution (VHR)


Dive into the research topics of 'SVM active learning approach for image classification using spatial information'. Together they form a unique fingerprint.

Cite this