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

Citations Over TimeTop 1% of 2012 papers

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 nonsaliency. 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 image amplitude spectrum with a low-pass Gaussian kernel of an appropriate scale is equivalent to an image saliency detector. The saliency map is obtained by reconstructing the 2D 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.

Related Papers

• → A Color Saliency Model for Salient Objects Detection in Natural Scenes(2009)7 cited
• → Recognizing actions using salient features(2011)6 cited
• → Quaternion-based salient region detection using scale space analysis(2015)5 cited
• → Scale and Rotation Invariant Salient Point Detection on 3D Mesh(2011)1 cited
• Local Invariant Feature Extraction Base on Salient Measurement of Second Moment Matrix(2009)