# Saliency detection based on structural dissimilarity induced by image quality assessment model

## TL;DR

This paper introduces a novel saliency detection method that measures structural dissimilarity based on image quality assessment principles, outperforming existing models by focusing on structural features like contrast and gradient.

## Contribution

The paper proposes a new saliency detection approach using structural dissimilarity derived from IQA models, emphasizing structural features over traditional feature difference methods.

## Key findings

- Outperforms 11 state-of-the-art models on three databases
- Uses structural features like contrast and gradient magnitude
- No postprocessing needed for high performance

## Abstract

The distinctiveness of image regions is widely used as the cue of saliency. Generally, the distinctiveness is computed according to the absolute difference of features. However, according to the image quality assessment (IQA) studies, the human visual system is highly sensitive to structural changes rather than absolute difference. Accordingly, we propose the computation of the structural dissimilarity between image patches as the distinctiveness measure for saliency detection. Similar to IQA models, the structural dissimilarity is computed based on the correlation of the structural features. The global structural dissimilarity of a patch to all the other patches represents saliency of the patch. We adopt two widely used structural features, namely the local contrast and gradient magnitude, into the structural dissimilarity computation in the proposed model. Without any postprocessing, the proposed model based on the correlation of either of the two structural features outperforms 11 state-of-the-art saliency models on three saliency databases.