Homogeneity of a region in the logarithmic image processing framework: application to region growing algorithms

TL;DR

This paper introduces new homogeneity criteria based on Logarithmic Image Processing operators to improve region growing algorithms, making them more robust to contrast variations and reducing chaining effects.

Contribution

It proposes novel heterogeneity criteria using LIP addition and scalar multiplication, enhancing Revol's region growing method for better contrast invariance.

Findings

Improved robustness to contrast variations

Reduced chaining effect in region growing

Enhanced homogeneity evaluation using LIP operators

Abstract

The current paper deals with the role played by Logarithmic Image Processing (LIP) operators for evaluating the homogeneity of a region. Two new criteria of heterogeneity are introduced, one based on the LIP addition and the other based on the LIP scalar multiplication. Such tools are able to manage Region Growing algorithms following the Revol's technique: starting from an initial seed, they consist of applying specific dilations to the growing region while its inhomogeneity level does not exceed a certain level. The new approaches we introduce are significantly improving Revol's existing technique by making it robust to contrast variations in images. Such a property strongly reduces the chaining effect arising in region growing processes.