Image Segmentation based on Tree Equipartition, Bayesian Flooding and Region Merging

Our image segmentation framework involves feature extraction and classification in feature space, followed by flooding in spatial domain, based on the computed local measurements and distances from the distribution of features describing the different classes. The globalism of the description ensures spatial coherence using the properties of the label dependent distances. The distribution of the features for the different classes are obtained by block-based unsupervised clustering based on the construction of the minimum spanning tree of the blocks' grid using the Mallows distance and the equipartition of the resulting tree. The final clustering is obtained by using the k-centroids algorithm. With high probability and under topological constraints, connected components of the maximum likelihood classification map are used to compute a map of initially labelled pixels. An efficient flooding algorithm, namely, Priority Multi-Class Flooding Algorithm (PMCFA), assigns pixels to labels using Bayesian dissimilarity criteria. A new region merging method, which incorporates boundary information, is the last step for obtaining the final segmentation map. Below are given the segmentation results on the whole Berkeley benchmark data set.

Click on the thumbnail to view the image and the segmentation result