Segmentation of Hyperspectral Images via Subtractive Clustering and Cluster Validation Using One-Class Support Vector Machines

BİLGİN G., ERTÜRK S., YILDIRIM T.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, cilt.49, sa.8, ss.2936-2944, 2011 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 49 Sayı: 8
  • Basım Tarihi: 2011
  • Doi Numarası: 10.1109/tgrs.2011.2113186
  • Dergi Adı: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2936-2944
  • Anahtar Kelimeler: Hyperspectral images, one-class support vector (SV) machines (OC-SVMs), phase correlation, segmentation, subtractive clustering, unsupervised classification, FEATURE-EXTRACTION
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

This paper presents an unsupervised hyperspectral image segmentation with a new subtractive-clustering-based similarity segmentation and a novel cluster validation method using one-class support vector (SV) machine (OC-SVM). An estimation of the correct number of clusters is an important task in hyperspectral image segmentation. The proposed cluster validity measure is based on the power of spectral discrimination (PWSD) measure and utilizes the advantage of the inherited cluster contour definition feature of OC-SVM. Hence, this novel cluster validity method is referred to as SV-PWSD. SVs found by OC-SVM are located at the minimum distance to the hyperplane in the feature space and at the arbitrarily shaped cluster contours in the input space. SV-PWSD guides the segmentation/clustering process to find the optimal number of clusters in hyperspectral data. Because of the high computational load of subtractive clustering and OC-SVM, a subset of the image (only ground-truth data) is initially used in the clustering and validation phases. Then, it is proposed to use K-nearest neighbor classification, with the already clustered subset being used as training data, to project the initial clustering results onto the entire data set.