Saliency Detection: A Spectral Residual Approach

  title={Saliency Detection: A Spectral Residual Approach},
  author={Xiaodi Hou and L. Zhang},
  journal={2007 IEEE Conference on Computer Vision and Pattern Recognition},
  • Xiaodi Hou, L. Zhang
  • Published 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… CONTINUE READING
    3,006 Citations

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Saliency Detection: A Divisive Normalization Approach
    • 1
    Saliency Detection Based on Scale Selectivity of Human Visual System
    • 2
    • Highly Influenced
    • PDF
    A Model for Saliency Detection Using NMFsc Algorithm
    • 4
    • Highly Influenced
    Hybrid Saliency Detection for Images
    • 17
    • Highly Influenced
    • PDF
    Visual saliency detection with center shift
    • 20
    • PDF
    Visual saliency detection using local patches contrast
    Incremental sparse saliency detection
    • 71
    • Highly Influenced
    • PDF
    A saliency detection model based on sparse features and visual acuity
    • 1
    Visual saliency detection via image complexity feature
    • 5


    A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
    • 8,940
    • PDF
    Statistics of natural image categories
    • 805
    • PDF
    A saliency-based search mechanism for overt and covert shifts of visual attention
    • 2,791
    • PDF
    Modeling global scene factors in attention.
    • A. Torralba
    • Physics, Medicine
    • Journal of the Optical Society of America. A, Optics, image science, and vision
    • 2003
    • 273
    • PDF
    Computational modelling of visual attention
    • 3,794
    • PDF
    Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
    • 6,121
    • PDF
    Attentional Selection for Object Recognition - A Gentle Way
    • 243
    • PDF
    Segmentation of objects from backgrounds in visual search tasks
    • 136
    • PDF
    Seeing, sensing, and scrutinizing
    • 486
    • PDF
    Origins of scaling in natural images
    • D. Ruderman
    • Psychology, Computer Science
    • Vision Research
    • 1997
    • 212
    • PDF