Saliency Detection: A Spectral Residual Approach

  title={Saliency Detection: A Spectral Residual Approach},
  author={Xiaodi Hou and Liqing Zhang},
  journal={2007 IEEE Conference on Computer Vision and Pattern Recognition},
  • Xiaodi HouLiqing Zhang
  • Published 17 June 2007
  • Computer Science
  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyzing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast… 

Figures and Tables from this paper

Saliency Detection: A Divisive Normalization Approach

The key idea is to exploit a computational process of divisive normalization that simulates the similar feature suppression in human primary visual cortex, and thereby is capable of generating visual saliency.

Visual saliency detection with center shift

Saliency Detection Based on Scale Selectivity of Human Visual System

A novel bottom-up saliency mechanism through scale space analysis is proposed, which is able to quickly extract salient regions which are consistent with human visual perception, both qualitatively and quantitatively.

Visual saliency detection using local patches contrast

Different from context-aware saliency algorithm, this method for saliency detection, not only uses basic properties of visual attention but also introducing local patches contrast cues, thus it can effectively improve the accuracy of visualSaliency detection with relatively low computational complexity.

A Model for Saliency Detection Using NMFsc Algorithm

This paper addresses an information theoretic model for visual saliency detection using the Non-negative Matrix Factorization with sparseness constraints (NMFsc) algorithm to generate the saliency map by the Salient Information (SI) which is calculated from the coefficients represented by basis functions.

Hybrid Saliency Detection for Images

This letter presents a hybrid saliency detection method for images by which it automatically predict the saliency regions based on low-level and high-level cues, and compares its algorithm to several state-of-the-art saliency Detection methods based on the well-known 1000 image EPFL database.

A saliency detection model based on sparse features and visual acuity

Experimental results show that the proposed saliency detection algorithm outperforms other existing schemes tested with a large public image database.

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.

Incremental sparse saliency detection

A new visual saliency detection model for both image and video is proposed, Inspired by biological vision, where saliency is defined locally and lossy compression is adopted.


A novel saliency detection model is presented to capture visual selective attention of images that does not require prior knowledge of salient regions as well as manual labeling and achieves the best performance in terms of visual and quantitative evaluations compared to existing state-of-the-art saliency Detection models.



A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented, which breaks down the complex problem of scene understanding by rapidly selecting conspicuous locations to be analyzed in detail.

Statistics of natural image categories

Results show how visual categorization based directly on low-level features, without grouping or segmentation stages, can benefit object localization and identification.

A saliency-based search mechanism for overt and covert shifts of visual attention

Computational modelling of visual attention

Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment, providing a framework for a computational and neurobiological understanding of visual attention.

Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.

Attentional Selection for Object Recognition - A Gentle Way

A combined model for spatial attention and object recognition in which the recognition system monitors the entire visual field, but attentional modulation by as little as 20% at a high level is sufficient to recognize multiple objects.

Segmentation of objects from backgrounds in visual search tasks

The statistics of natural images

Recently there has been a resurgence of interest in the properties of natural images. Their statistics are important not only in image compression but also for the study of sensory processing in

Depth Estimation from Image Structure

It is demonstrated that, by recognizing the properties of the structures present in the image, one can infer the scale of the scene and, therefore, its absolute mean depth.

Object class recognition by unsupervised scale-invariant learning

The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).