How to scale hyperparameters for quickshift image segmentation

01/23/2022
by   Damien Garreau, et al.
5

Quickshift is a popular algorithm for image segmentation, used as a preprocessing step in many applications. Unfortunately, it is quite challenging to understand the hyperparameters' influence on the number and shape of superpixels produced by the method. In this paper, we study theoretically a slightly modified version of the quickshift algorithm, with a particular emphasis on homogeneous image patches with i.i.d. pixel noise and sharp boundaries between such patches. Leveraging this analysis, we derive a simple heuristic to scale quickshift hyperparameters when dealing with real images, which we check empirically.

READ FULL TEXT

page 6

page 8

page 31

page 32

page 33

research
10/03/2010

Visual-hint Boundary to Segment Algorithm for Image Segmentation

Image segmentation has been a very active research topic in image analys...
research
05/01/2015

Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph

We present a method for hierarchical image segmentation that defines a d...
research
10/06/2015

A Latent Source Model for Patch-Based Image Segmentation

Despite the popularity and empirical success of patch-based nearest-neig...
research
04/15/2016

Unsupervised Image Segmentation using the Deffuant-Weisbuch Model from Social Dynamics

Unsupervised image segmentation algorithms aim at identifying disjoint h...
research
10/09/2018

Image Segmentation using Unsupervised Watershed Algorithm with an Over-segmentation Reduction Technique

Image segmentation is the process of partitioning an image into meaningf...
research
08/29/2023

Pseudo-Boolean Polynomials Approach To Edge Detection And Image Segmentation

We introduce a deterministic approach to edge detection and image segmen...
research
10/18/2019

Fully Parallel Hyperparameter Search: Reshaped Space-Filling

Space-filling designs such as scrambled-Hammersley, Latin Hypercube Samp...

Please sign up or login with your details

Forgot password? Click here to reset