Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

TL;DR

This paper introduces a novel frequency domain approach to visual saliency detection using scale-space analysis of the amplitude spectrum, effectively predicting human fixation points and highlighting salient regions of various sizes.

Contribution

It presents a new bottom-up saliency detection paradigm based on amplitude spectrum filtering and phase reconstruction, capable of detecting multiple scales of salient regions.

Findings

Predicts human fixation data accurately.

Highlights both small and large salient regions.

Inhibits distractors in cluttered images.

Abstract

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of {\it non-saliency}. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space analysis of the amplitude spectrum of natural images. We show that the convolution of the {\it image amplitude spectrum} with a low-pass Gaussian kernel of an appropriate scale is equivalent to such an image saliency detector. The saliency map is obtained by reconstructing the 2-D signal using the original phase and the amplitude spectrum, filtered at a scale selected by minimizing saliency map entropy. A Hypercomplex Fourier Transform performs the analysis in the frequency domain. Using available databases, we demonstrate experimentally that the proposed model can predict human fixation data. We also introduce a new image database and use it to show that the saliency detector can highlight both small and large salient regions, as well as inhibit repeated distractors in cluttered images. In addition, we show that it is able to predict salient regions on which people focus their attention.