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. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TPAMI.2012.147 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | Field | DocType |
cluttered image,nonsaliency concept,image amplitude spectrum convolution,visual saliency,gaussian processes,visual saliency detection,fourier transforms,natural images,minimum entropy methods,visual databases,saliency map,salient region,convolution,frequency-domain analysis,2d signal reconstruction,saliency map entropy minimization,salient region detection,saliency map entropy,image saliency detector,saliency detection,image reconstruction,amplitude spectrum,phase spectrum,eye tracking,visual attention,hypercomplex fourier transform,frequency domain analysis problem,object detection,frequency domain,frequency domain analysis,saliency,natural scenes,scale-space analysis,low pass gaussian kernel,image database,scale space analysis,saliency detector,visual perception,kernel,strontium,fourier analysis,algorithms,visualization,computational modeling | Kernel (linear algebra),Frequency domain,Computer vision,Object detection,Pattern recognition,Kadir–Brady saliency detector,Computer science,Convolution,Salience (neuroscience),Scale space,Artificial intelligence,Gaussian function | Journal |
Volume | Issue | ISSN |
abs/1605.01999 | 4 | Pattern Analysis and Machine Intelligence, IEEE Transactions on
35.4 (2013): 996-1010 |
Citations | PageRank | References |
161 | 3.78 | 23 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jian Li | 1 | 161 | 3.78 |
Martin D. Levine | 2 | 2039 | 454.84 |
Xiangjing An | 3 | 226 | 12.15 |
Xin Xu | 4 | 1365 | 100.22 |
Hangen He | 5 | 307 | 23.86 |