In this paper, we present a novel solution of image segmentation based on positiveness by regarding the segmentation as one of the graph-theoretic clustering problems. On the contrary to spectral clustering methods using eigenvectors, the proposed method tries to find an additive combination of positive components from an originally positive data-driven matrix. By using the positiveness constraint, we obtain sparsely clustered results which are closely related to human perception and thus we call this method sparse clustering. The proposed method adopts a binary tree structure and solves a model selection problem by automatically determining the number of clusters using intra- and inter-cluster measures. We tested our method with various kinds of data such as points, gray-scale, color, and texture images. Experimental results show that the proposed method provides very successful and encouraging segmentations.
Image Segmentation by Unsupervised Sparse Clustering
2005-01-01
630398 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Unsupervised scene segmentation using sparse coding context
British Library Online Contents | 2013
|Unsupervised Fuzzy Clustering and Image Segmentation Using Weighted Neural Networks
British Library Conference Proceedings | 2003
|Unsupervised texture image segmentation using multilayer data condensation spectral clustering
British Library Online Contents | 2010
|Unsupervised Multiscale Image Segmentation
British Library Conference Proceedings | 1999
|