This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain
April 2013 (vol. 35 no. 4)
pp. 996-1010
Jian Li, Inst. of Autom., Nat. Univ. of Defense Technol., Changsha, China
M. D. Levine, Dept. of Electr. & Comput. Eng., McGill Univ., Montreal, QC, Canada
Xiangjing An, Inst. of Autom., Nat. Univ. of Defense Technol., Changsha, China
Xin Xu, Inst. of Autom., Nat. Univ. of Defense Technol., Changsha, China
Hangen He, Inst. of Autom., Nat. Univ. of Defense Technol., Changsha, China
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.
Index Terms:
visual databases,convolution,Fourier transforms,frequency-domain analysis,Gaussian processes,image reconstruction,minimum entropy methods,natural scenes,object detection,cluttered image,visual saliency detection,frequency domain analysis,nonsaliency concept,salient region detection,scale-space analysis,natural images,image amplitude spectrum convolution,low pass Gaussian kernel,image saliency detector,2D signal reconstruction,phase spectrum,saliency map entropy minimization,hypercomplex Fourier transform,image database,Strontium,Visualization,Frequency domain analysis,Fourier transforms,Kernel,Computational modeling,Convolution,scale space analysis,Visual attention,saliency,hypercomplex Fourier transform,eye tracking
Citation:
Jian Li, M. D. Levine, Xiangjing An, Xin Xu, Hangen He, "Visual Saliency Based on Scale-Space Analysis in the Frequency Domain," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 4, pp. 996-1010, April 2013, doi:10.1109/TPAMI.2012.147
Usage of this product signifies your acceptance of the Terms of Use.