A dense subgraph based algorithm for compact salient image region detection

TL;DR

This paper introduces a graph-based saliency detection algorithm that combines random walks and dense subgraph detection to identify visually salient regions in images, improving local structure representation.

Contribution

The novel approach integrates dense subgraph detection with random walk-based saliency to enhance the identification of salient image regions.

Findings

Performs comparably to established saliency detection algorithms.

Utilizes dense subgraphs to better capture local graph structures.

Effective on benchmark image datasets.

Abstract

We present an algorithm for graph based saliency computation that utilizes the underlying dense subgraphs in finding visually salient regions in an image. To compute the salient regions, the model first obtains a saliency map using random walks on a Markov chain. Next, k-dense subgraphs are detected to further enhance the salient regions in the image. Dense subgraphs convey more information about local graph structure than simple centrality measures. To generate the Markov chain, intensity and color features of an image in addition to region compactness is used. For evaluating the proposed model, we do extensive experiments on benchmark image data sets. The proposed method performs comparable to well-known algorithms in salient region detection.