A Study of Color Image Segmentation Based on a Multi-dimensional Histogram
Details
A deta-driven segmentation algorithm based on a multi-dimensional histogram is proposed for color images. An image is observed as a mixture of multi-variate data, but the number of clusters in the mixture is generally unknown. The proposed algorithm determines the width of a histogram to use and then obtains the number of clusters according to the observed multivariate data. Next, the statistics for each cluster are computed, since this is a requisite for clustering all of the other elements. The proposed clustering method can be applied to various kinds of images, because it is not restricted by an image model used in model-based approaches. The effectiveness of the algorithm is evaluated by computer simulation, and the algorithm is applied to real color image clustering.
