DeepAI AI Chat
Log In Sign Up

Power-SLIC: Diagram-based superpixel generation

by   Maximilian Fiedler, et al.
University of Liverpool
Technische Universität München

Superpixel algorithms, which group pixels similar in color and other low-level properties, are increasingly used for pre-processing in image segmentation. Commonly important criteria for the computation of superpixels are boundary adherence, speed, and regularity. Boundary adherence and regularity are typically contradictory goals. Most recent algorithms have focused on improving boundary adherence. Motivated by improving superpixel regularity, we propose a diagram-based superpixel generation method called Power-SLIC. On the BSDS500 data set, Power-SLIC outperforms other state-of-the-art algorithms in terms of compactness and boundary precision, and its boundary adherence is the most robust against varying levels of Gaussian noise. In terms of speed, Power-SLIC is competitive with SLIC.


page 1

page 2

page 6


A linear framework for region-based image segmentation and inpainting involving curvature penalization

We present the first method to handle curvature regularity in region-bas...

SCALP: Superpixels with Contour Adherence using Linear Path

Superpixel decomposition methods are generally used as a pre-processing ...

Regularity of the solution of the scalar Signorini problem in polygonal domains

The Signorini problem for the Laplace operator is considered in a genera...

Wavenumber-explicit hp-FEM analysis for Maxwell's equations with impedance boundary conditions

The time-harmonic Maxwell equations at high wavenumber k in domains with...

A Steklov-spectral approach for solutions of Dirichlet and Robin boundary value problems

In this paper we revisit an approach pioneered by Auchmuty to approximat...

On the Role of Non-Localities in Fundamental Diagram Estimation

We consider the role of non-localities in speed-density data used to fit...

Boundary-weighted logit consistency improves calibration of segmentation networks

Neural network prediction probabilities and accuracy are often only weak...