A Registration-Based Star-Shape Segmentation Model and Fast Algorithms

2025-08-11

AI Summary

Accurate segmentation of star-shaped objects remains challenging under severe degradation such as occlusion, motion blur, or noise. Method: This paper proposes a variational segmentation model integrating image registration with level-set evolution, centered on a deformable star-shaped prior that supports both single- and multi-center configurations as well as complete or partial star structures. A landmark-point constraint is incorporated to enforce precise boundary alignment with user-specified fiducial points. Crucially, the deformable level-set function is embedded into the registration framework for the first time, and the resulting optimization is efficiently solved via the Alternating Direction Method of Multipliers (ADMM). Results: Extensive experiments on synthetic and real-world images demonstrate that the method achieves high accuracy and strong robustness even under severe degradation, significantly outperforming state-of-the-art star-shaped segmentation approaches.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Image segmentation plays a crucial role in extracting objects of interest and identifying their boundaries within an image. However, accurate segmentation becomes challenging when dealing with occlusions, obscurities, or noise in corrupted images. To tackle this challenge, prior information is often utilized, with recent attention on star-shape priors. In this paper, we propose a star-shape segmentation model based on the registration framework. By combining the level set representation with the registration framework and imposing constraints on the deformed level set function, our model enables both full and partial star-shape segmentation, accommodating single or multiple centers. Additionally, our approach allows for the enforcement of identified boundaries to pass through specified landmark locations. We tackle the proposed models using the alternating direction method of multipliers. Through numerical experiments conducted on synthetic and real images, we demonstrate the efficacy of our approach in achieving accurate star-shape segmentation.

Problem

• Segments star-shaped objects in corrupted images
• Handles occlusions and noise using registration framework
• Enforces boundaries through specified landmark locations

Innovation

• Registration-based star-shape segmentation model
• Level set representation with registration framework
• Alternating direction method multipliers algorithm