# Interactive Image Segmentation using Label Propagation through Complex Networks

## TL;DR

This paper introduces a two-stage graph-based interactive image segmentation method that uses complex networks for fast, accurate, and efficient segmentation, especially effective with minimal user input.

## Contribution

It proposes a novel two-stage approach combining small-world network construction and grid refinement, improving speed and accuracy over existing methods.

## Key findings

- High segmentation accuracy comparable to state-of-the-art methods
- Faster processing than competing approaches
- Effective with minimal user input such as scribbles

## Abstract

Interactive image segmentation is a topic of many studies in image processing. In a conventional approach, a user marks some pixels of the object(s) of interest and background, and an algorithm propagates these labels to the rest of the image. This paper presents a new graph-based method for interactive segmentation with two stages. In the first stage, nodes representing pixels are connected to their $k$-nearest neighbors to build a complex network with the small-world property to propagate the labels quickly. In the second stage, a regular network in a grid format is used to refine the segmentation on the object borders. Despite its simplicity, the proposed method can perform the task with high accuracy. Computer simulations are performed using some real-world images to show its effectiveness in both two-classes and multi-classes problems. It is also applied to all the images from the Microsoft GrabCut dataset for comparison, and the segmentation accuracy is comparable to those achieved by some state-of-the-art methods, while it is faster than them. In particular, it outperforms some recent approaches when the user input is composed only by a few "scribbles" draw over the objects. Its computational complexity is only linear on the image size at the best-case scenario and linearithmic in the worst case.