Title :
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain
Author :
Jian Li ; Levine, Martin D. ; Xiangjing An ; Xin Xu ; Hangen He
Author_Institution :
Inst. of Autom., Nat. Univ. of Defense Technol., Changsha, China
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.
Keywords :
Fourier transforms; Gaussian processes; convolution; frequency-domain analysis; image reconstruction; minimum entropy methods; natural scenes; object detection; visual databases; 2D signal reconstruction; cluttered image; frequency domain analysis; hypercomplex Fourier transform; image amplitude spectrum convolution; image database; image saliency detector; low pass Gaussian kernel; natural images; nonsaliency concept; phase spectrum; saliency map entropy minimization; salient region detection; scale-space analysis; visual saliency detection; Computational modeling; Convolution; Fourier transforms; Frequency domain analysis; Kernel; Strontium; Visualization; Visual attention; eye tracking; hypercomplex Fourier transform; saliency; scale space analysis; Algorithms; Animals; Fourier Analysis; Models, Neurological; Pattern Recognition, Automated; Primates; Signal Processing, Computer-Assisted; Visual Perception;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2012.147