An Image Segmentation Model Based on a Variational Formulation

TL;DR

This paper introduces a novel image segmentation model based on a variational formulation that integrates region statistics and edge information, enhancing flexibility across diverse image types.

Contribution

The paper presents a new variational model for image segmentation that combines region and edge data, improving adaptability over existing purely region- or edge-based models.

Findings

Model demonstrates versatility on real images

Effective segmentation across various image types

Identifies potential for further improvements on pathological images

Abstract

Starting from a variational formulation, we present a model for image segmentation that employs both region statistics and edge information. This combination allows for improved flexibility, making the proposed model suitable to process a wider class of images than purely region-based and edge-based models. We perform several simulations with real images that attest to the versatility of the model. We also show another set of experiments on images with certain pathologies that suggest opportunities for improvement.