Adaptive Eigenspace Segmentation
This work addresses the critical issue of parameter sensitivity in regularization-based segmentation, offering a parameter-free, efficient solution for general image segmentation tasks.
The paper introduces an adaptive eigenspace framework for image segmentation that eliminates the need for parameter tuning and optimization, solving a symmetric positive definite sparse system with reduced computational cost. The method achieves accurate and robust segmentation across various images and organs without training.
Image segmentation is an inherently ill-posed problem and thus requires regularization in order to limit the search space to reasonable solutions. A majority of segmentation methods integrates these regularization terms in one way or the other in an energy functional using a balancing term. The tuning of this parameter that either favours more the regularization or the data conformity is critical and, unfortunately, the success of the optimization process strongly depends on it. Often the optimal settings change from image to image. In this paper we propose a novel general framework based on an adaptive eigenspace that was first proposed for solving inverse problems. The resulting method proves accurate and yields robust results, without the need for optimization techniques or being sensitive to the parameter choice. In fact, the method solves a symmetric positive definite sparse system and hence, uses only a fraction of the computational cost. The method is very versatile and does not need parameter-tuning, when segmenting objects from any kind of an image or when segmenting different organs. As the adaptive eigenspace is determined directly from the image to segment, the approach also does not need a tedious training phase.