We survey the state of the art in multiscale segmentation and identify some drawbacks in the traditional approach to multiscale segmentation - image pyramids and quadtree decomposition, especially in typical applications that make use of the segmented results. We then introduce the idea of multiscale segmentation within the context of the segmented regions themselves instead of, as is traditional, working in the context of the original image. It is shown that this new multiscale approach can be incorporated into the K-Means clustering technique as a steady relaxation of inter-cluster distances.
We also develop a way of objectively evalutating texture segmentation algorithms on natural and synthetic texture patches. Finally, our multiscale segmentation approach is demonstrated on several families of real-world images. It is shown that quality of the segmented results at the different scales is significantly improved.
We show that surface rendering and interactive perspective view computations may be done efficiently on suitably pre-processed data. We discuss the preprocessing steps that need to be done on the original set of echocardiogram images to place them in a format that enables interactive viewing. We discuss the advantages of this 4D format for the data and show that the pre-processing steps are quite general. Finally, we compare the surfaces extracted by our algorithm with the leaflet surfaces as identified by a cardiologist.