A new method for image feature extraction and segmentation is proposed in this paper. Abundant contour feature information of the image is expressed by contourlet transform while texture feature of the image is described by wavelet transform and Gray Level Co-occurrence Matrix (GLCM). The three type feature information compose feature matrix. The presented method describes different image information using different characterization transform and keeps well useful original image information. Then we select spectral mapping to simply the feature matrix and gain distributed datasets. And the images are segmented by fuzzy clustering algorithm with spatial constraints, which can improve the robustness of the proposed method to the images containing noise. Simulation results of the texture images and Synthetic Aperture Radar (SAR) images show the proposed method had higher accuracy compared with traditional spectral clustering.
Image Segmentation Based on Fussing Multi-feature and Spatial Spectral Clustering
2008 Congress on Image and Signal Processing ; 3 ; 667-671
2008-05-01
641941 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Schadstoffarmer Batteriebus - Drei Jahre praktische Erfahrung in Bad Füssing
Tema Archiv | 1997
|Spatial-Feature Parametric Clustering Applied to Motion-Based Segmentation in Camouflage
British Library Online Contents | 2002
|Robust Path-Based Spectral Clustering with Application to Image Segmentation
British Library Conference Proceedings | 2005
|Unsupervised texture image segmentation using multilayer data condensation spectral clustering
British Library Online Contents | 2010
|