Still Image Segmentation Tools for Content-based Multimedia Applications

In this paper, a novel color image segmentation algorithm and a novel approach to large-format image segmentation are presented, both focused on usage for image segmentation in content-based multimedia applications. The novel color image segmentation algorithm uses the Discrete Wavelet Frames decomposition to extract texture features and performs pixel classification using a novel initial clustering procedure and applying a novel variant of the K-Means-with-connectivity-constraint algorithm in the combined intensity and texture feature space. This novel scheme enables the unsupervised operation of the proposed segmentation algorithm. The novel large-format image segmentation scheme employs the aforementioned segmentation algorithm and exploits spatial redundancy to provide an elegant framework for the fast segmentation of large-format images. As shown by experimental evaluation, these novel algorithms provide fast segmentation with high perceptual segmentation quality.