A two-stage method for spectral–spatial classification of hyperspectral images

Raymond H. CHAN*, Kelvin K. KAN, Mila NIKOLOVA, Robert J. PLEMMONS

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

19 Citations (Scopus)


We propose a novel two-stage method for the classification of hyperspectral images. Pixel-wise classifiers, such as the classical support vector machine (SVM), consider spectral information only. As spatial information is not utilized, the classification results are not optimal and the classified image may appear noisy. Many existing methods, such as morphological profiles, superpixel segmentation, and composite kernels, exploit the spatial information. In this paper, we propose a two-stage approach inspired by image denoising and segmentation to incorporate the spatial information. In the first stage, SVMs are used to estimate the class probability for each pixel. In the second stage, a convex variant of the Mumford–Shah model is applied to each probability map to denoise and segment the image into different classes. Our proposed method effectively utilizes both spectral and spatial information of the data sets and is fast as only convex minimization is needed in addition to the SVMs. Experimental results on three widely utilized real hyperspectral data sets indicate that our method is very competitive in accuracy, timing, and the number of parameters when compared with current state-of-the-art methods, especially when the inter-class spectra are similar or the percentage of training pixels is reasonably high.

Original languageEnglish
Pages (from-to)790-807
Number of pages18
JournalJournal of Mathematical Imaging and Vision
Issue number6-7
Early online date3 Mar 2020
Publication statusPublished - Jul 2020
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.


  • Alternating direction method of multipliers
  • Hyperspectral image classification
  • Image denoising
  • Image segmentation
  • Mumford–Shah model
  • Support vector machine


Dive into the research topics of 'A two-stage method for spectral–spatial classification of hyperspectral images'. Together they form a unique fingerprint.

Cite this