Image Segmentation with Multidimensional Refinement Indicators

TL;DR

This paper introduces a novel image segmentation method based on optimal control, which iteratively estimates pixel colors to produce robust and flexible segmentations driven by error minimization.

Contribution

It adapts optimal control techniques to image segmentation, providing a new iterative parameter estimation approach for partitioning images.

Findings

The method produces accurate segmentations with robust error minimization.

It offers a flexible framework adaptable to various image types.

The approach inherits properties like soundness and robustness from optimal control theory.

Abstract

We transpose an optimal control technique to the image segmentation problem. The idea is to consider image segmentation as a parameter estimation problem. The parameter to estimate is the color of the pixels of the image. We use the adaptive parameterization technique which builds iteratively an optimal representation of the parameter into uniform regions that form a partition of the domain, hence corresponding to a segmentation of the image. We minimize an error function during the iterations, and the partition of the image into regions is optimally driven by the gradient of this error. The resulting segmentation algorithm inherits desirable properties from its optimal control origin: soundness, robustness, and flexibility.