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

  title={Visual Saliency Based on Scale-Space Analysis in the Frequency Domain},
  author={Jian Li and Martin D. Levine and Xiangjing An and Xin Xu and Hangen He},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Jian Li, M. Levine, Hangen He
  • Published 1 April 2013
  • Physics
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
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… 
Spectral saliency via automatic adaptive amplitude spectrum analysis
The proposed method to detect visual saliency, especially with salient objects of different sizes and locations via automatic adaptive amplitude spectrum analysis, outperforms the existing state-of-the-art saliency models for predicting human eye fixations in terms of accuracy and robustness.
Finding the Secret of Image Saliency in the Frequency Domain
It is found that the secret of visual saliency may mainly hide in the phases of intermediate frequencies, and a novel approach to design the saliency detector under the assistance of prior knowledge obtained through both unsupervised and supervised learning processes is proposed.
Fast visual saliency based on multi-scale difference of Gaussians fusion in frequency domain
To reduce the computation required in determining the proper scale of salient object, a fast visual saliency based on multi-scale difference of Gaussians fusion in frequency domain (MDF) is proposed.
Visual saliency based on frequency domain analysis and spatial information
Experimental results show that the proposed model can achieve high performance in terms of the average AUC and F-measure evaluation metrics and outperform state-of-the-art baselines.
Modified Scale-Space Analysis in Frequency Domain Based on Adaptive Multiscale Gaussian Filter for Saliency Detection
The adaptive multiscale Gaussian filter (MSS) for scale-space analysis in the frequency domain is proposed, extended from an adaptive median filter which is a powerful method to remove the noise from the input image.
Visual Saliency via Multiscale Analysis in Frequency Domain and Its Applications to Ship Detection in Optical Satellite Images
This article proposes a bottom-up visual saliency model that uses the wavelet transform to conduct multiscale analysis and computation in the frequency domain. First, we compute the multiscale
Visual Saliency Based on Two-Dimensional Fractional Fourier Transform
A novel visual saliency model based on two-dimensional fractional Fourier transform generates a robust saliency map from the input image with Gaussian or salt-and-pepper noise and provides a concept called the noise sensitivity scale (NSS).
Visual Saliency Detection of Stereoscopic 3D images based on Scale-Space Analysis
Visual saliency alludes to the particular fixation on prominent or significant regions in a scene that have likewise been appeared to relate with vital objects and their relationships. Visual
A Multi-Scale Colour and Keypoint Density-Based Approach for Visual Saliency Detection
This paper proposes a new saliency method based on the combination of the distribution of interest points in the image with multiscale analysis, a centre bias module and a machine learning approach, and uses perceptually uniform colour spaces to study how colour impacts on the extraction of saliency.
Visual saliency detection via image complexity feature
This paper constructs a heuristic framework to systematically combine two different types of saliency detection models, separately using local and global features, in order to predict human fixation points more accurately.


A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression
Extensive tests of videos, natural images, and psychological patterns show that the proposed PQFT model is more effective in saliency detection and can predict eye fixations better than other state-of-the-art models in previous literature.
Saliency Detection: A Spectral Residual Approach
A simple method for the visual saliency detection is presented, independent of features, categories, or other forms of prior knowledge of the objects, and a fast method to construct the corresponding saliency map in spatial domain is proposed.
Bottom-up saliency is a discriminant process
The resulting saliency detector is shown to replicate the fundamental properties of the psychophysics of pre-attentive vision, including stimulus pop-out, inability to detect feature conjunctions, asymmetries with respect to feature presence vs. absence, and compliance with Weber's law.
SUN: A Bayesian framework for saliency using natural statistics.
In the model, saliency is computed locally, which is consistent with the neuroanatomy of the early visual system and results in an efficient algorithm with few free parameters, which provides a straightforward explanation for many search asymmetries observed in humans.
Spatiotemporal Saliency in Dynamic Scenes
The algorithm is inspired by biological mechanisms of motion-based perceptual grouping and extends a discriminant formulation of center-surround saliency previously proposed for static imagery, and yields a robust, versatile, and fully unsupervised spatiotemporal saliency algorithm, applicable to scenes with highly dynamic backgrounds and moving cameras.
The discriminant center-surround hypothesis for bottom-up saliency
In result, discriminant saliency is shown to predict eye fixations better than previous models, and produces background subtraction algorithms that outperform the state-of-the-art in computer vision.
On the plausibility of the discriminant center-surround hypothesis for visual saliency.
The discriminant saliency detectors outperform previously proposed methods from both the saliency and the general computer vision literatures and make accurate quantitative predictions of various psychophysics of human saliency for both static and motion stimuli.
A Nonparametric Approach to Bottom-Up Visual Saliency
The model is rather simplistic and essentially parameter-free, and contrasts recent developments in the field that usually aim at higher prediction rates at the cost of additional parameters and increasing model complexity, and in fact learns image features that resemble findings from several previous studies.
Video processing with scale-aware saliency: Application to Frame Rate Up-Conversion
  • N. Jacobson, Truong Q. Nguyen
  • Computer Science
    2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2011
The ability of the algorithm to detect salient objects at multiple scales allows for class-leading performance both objectively in terms of PSNR/SSIM as well as subjectively.
Frequency-tuned salient region detection
This paper introduces a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects that outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.