Conceptualization of seeded region growing by pixels aggregation. Part 3: a wide range of algorithms

TL;DR

This paper presents a library and various algorithms for seeded region growing by pixels aggregation, focusing on flexible partitioning and boundary management, with implementations demonstrating the approach's versatility.

Contribution

It introduces a comprehensive library and multiple algorithms for seeded region growing, emphasizing boundary handling and order invariance, advancing the state of the art.

Findings

Library enables flexible region growing algorithms

Algorithms achieve partition invariance to seed initialization

Demonstrated effectiveness in diverse segmentation tasks

Abstract

In the two previous papers of this serie, we have created a library, called Population, dedicated to seeded region growing by pixels aggregation and we have proposed different growing processes to get a partition with or without a boundary region to divide the other regions or to get a partition invariant about the seeded region initialisation order. Using this work, we implement some algorithms belonging to the field of SRGPA using this library and these growing processes.