An Image Segmentation Model with Transformed Total Variation

Elisha Dayag, Kevin Bui, Fredrick Park, Jack Xin
6/1/2024
cs.CVeess.IVmath.NA

No official code found. Best implementation: JimTheBarbarian/Official-TTV-Segmentation (0 stars, last commit 2024-06-01).

Abstract

Based on transformed $\ell_1$ regularization, transformed total variation (TTV) has robust image recovery that is competitive with other nonconvex total variation (TV) regularizers, such as TV$^p$, $0<p<1$. Inspired by its performance, we propose a TTV-regularized Mumford--Shah model with fuzzy membership function for image segmentation. To solve it, we design an alternating direction method of multipliers (ADMM) algorithm that utilizes the transformed $\ell_1$ proximal operator. Numerical experiments demonstrate that using TTV is more effective than classical TV and other nonconvex TV variants in image segmentation.

View on arXivView PDF

Code Implementations(1)

JimTheBarbarian/Official-TTV-SegmentationCommunity100%
00MATLABJun 1, 20242 years ago

Similar Papers

Multispectral Image Restoration by Generalized Opponent Transformation Total Variation

79% match2024

Unsupervised learning of spatially varying regularization for diffeomorphic image registration

77% match1 repo112024

Adaptive Mix for Semi-Supervised Medical Image Segmentation

77% match1 repo92024

ERD: Exponential Retinex decomposition based on weak space and hybrid nonconvex regularization and its denoising application

76% match2024

LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation

76% match1 repo142026

An ICTM-RMSAV Framework for Bias-Field Aware Image Segmentation under Poisson and Multiplicative Noise

76% match2025

Cite this paper

@article{dayag2024image,
  title  = {An Image Segmentation Model with Transformed Total Variation},
  author = {Elisha Dayag and Kevin Bui and Fredrick Park and Jack Xin},
  year   = {2024},
  eprint = {2406.00571},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.00571v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.00571.svg)](https://codeofpaper.com/paper/2406.00571)

Discussion