A Geometrical Active Contour Based on Statistical Shape Prior Model

Abstract

A new geometric active contour based level-sets model combining gradient, region and shape knowledge information cues is proposed to robust object detection boundaries in presence of occlusions and cluttered background. The gradient, region and shape knowledge information are incorporated as energy terms. The a priori shape model is based on statistical learning of the training data distribution where the structure of data distribution is approximated by a probability density model. The obtained probability is treated as Kernel Principal Component Analysis (KPC) by allowing the shapes that are close to the training data as energy term and incorporated a prior knowledge about shapes in a more robust manner into evolving equation model to constrain the further segmentation evolution process. We applied successfully the proposed model to synthetic and real MR images. The results drawn by the newer model are compared to expert segmentation and evaluated in terms of F-mesure.