Variational shape prior segmentation with an initial curve based on image registration technique

• Published in: Image and vision computing Vol. 94; p. 103865
• Main Authors: Yeo, Doyeob, Lee, Chang-Ock
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2020
• Subjects: Free-form deformation; Hierarchical image segmentation; Image registration; Shape prior segmentation; Free-form deformation; Image registration; Hierarchical image segmentation; Shape prior segmentation
• ISSN: 0262-8856; 1872-8138
• DOI: 10.1016/j.imavis.2019.103865

In general images, it is practically hard to distinguish only the desired object using the conventional image segmentation methods. In many cases, we can segment the desired object by using the shape information of the object in addition to the standard image segmentation. Chan and Zhu's model is not robust to the intensity changes of objects. In this paper, we propose a novel model for the shape prior segmentation that produces robust results using the hierarchical image segmentation and an attraction term. Moreover, we adopt an image registration technique and a multi-region image segmentation to get an initial for a given shape prior. Finally, we consider the free-form deformation in obtaining the shape function from the reference shape prior for real-world images. Numerical experiments demonstrate the results independent of intensities of objects and the location of the reference shape prior. All numerical calculations are automatic and progress without any user input. •Attraction term attracts a shape prior function from the background into the object.•Image registration with multi-region segmentation provides a proper initial curve.•FFD with cubic B-spline of a shape prior function allows more precise segmentation.