Image Segmentation by Hierarchical Spatial and Color Spaces Clustering

1IntroductionI mage segmentation, as a basic building block formany high-level i mage analysis problems ,such as objectrecognition[1], i mage retrieval[2], etc , has attractedmany research attentions over years .I mage segmenta-tionis to decompose the i mage into homogenous regionswiththe ai mof extractingthe major color andregionin-formationfromthe original i mage . The result of i magesegmentationis a set of non-overlapping regions whereeach regionis characterized by a chosen color and a con…

Image Segmentation by Hierarchical Spatial and Color Spaces Clustering

Image segmentation, as a basic building block for many high-level image analysis problems, has attracted many research attentions over years. Existing approaches, however, are mainly focusing on the clustering analysis in the single channel information, i.e., either in color or spatial space, which may lead to unsatisfactory segmentation performance. Considering the spatial and color spaces jointly, this paper proposes a new hierarchical image segmentation algorithm, which alternately clusters the image regions in color and spatial spaces in a fine to coarse manner. Without losing the perceptual consistence, the proposed algorithm achieves the segmentation result using only very few number of colors according to user specification.