SUSAN—A New Approach to Low Level Image Processing

@article{Smith2004SUSANANA,
  title={SUSAN—A New Approach to Low Level Image Processing},
  author={Stephen M. Smith and Michael Brady},
  journal={International Journal of Computer Vision},
  year={2004},
  volume={23},
  pages={45-78}
}
This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction.Non-linear filtering is used to define which parts of the image are closely related to each individual pixel; each pixel has associated with it a local image region which is of similar brightness to that pixel. The new feature detectors are based on the minimization of this local image region, and the noise reduction method uses this region as the… 
A Novel Window-Based Corner Detection Algorithm for Gray-Scale Images
TLDR
A new approach to corner detection in a digital image based on the assumption that corners are image points with high information content, and hence corners in an image exist in the regions having considerably high intensity variations is described.
AN IMPROVED DETECTION ALGORITHM FOR LOCAL FEATURES IN GRAY-LEVEL IMAGES
TLDR
A template feature is built for the current location and the template is compared to the content of the image to determine the actual presence of the feature and an improvement in the second step is reported.
An Improved Detection Algorithm for Local Features in Gray-Level Images
TLDR
A template feature is built for the current location and the template is compared to the content of the image to determine the actual presence of the feature and an improvement in the second step is reported.
Image Feature Detection and Matching Based on SUSAN Method
  • Weng Muyun, He Mingyi
  • Physics
    First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06)
  • 2006
A new approach to image edge detection and feature matching is proposed. In which, the edge detection employs SUSAN (small univalue segment assimilating nucleus) method at low level image processing.
New advances in digital image processing
TLDR
New image processing techniques are introduced in the non-linear filters, feature extraction, high dynamic range imaging methods based on soft computing models, thus contributing to the variety of advantageous possibilities to be applied.
Visual Attention Detection By Adaptive Non-Local Filter
TLDR
This paper presents the contrast analysis of image patches located in a whole image but not nearby with assistance of the adaptive filter for estimation of non-local divergence and allows extraction of signified regions with texture of images of wild life.
Offset Smoothing Using the USAN's Principle
TLDR
A new technique based on the USAN principle, which swaps the pixel value at each image point with a new value, which is more representative of the region where the point lies, is described.
Low-Level Vision Based Super-Resolution Image Reconstruction
TLDR
A variable threshold for the allowed variation in brightness within the USAN area is proposed and a new adaptive interpolation approach based on circular-area is presented, which makes corner well-distributed and can reduce lost and false corners relatively.
A Steady Corner Detection of Gray Level Images Based on Improved Harris Algorithm
TLDR
A method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and has better corner localization for synthetic, standard and natural images with rotation and noise.
A new approach to detecting the corners in digital images
  • E. Sojka
  • Computer Science
    Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
  • 2003
TLDR
A new corner detector is presented that is based on a theory that takes into account relatively complicated situations that may occur in the neighbourhoods of the corner candidates and was better in the tests than the other algorithms used for comparison.
...
...

References

SHOWING 1-10 OF 123 REFERENCES
Digital image smoothing and the sigma filter
  • Jong-Sen Lee
  • Computer Science
    Comput. Vis. Graph. Image Process.
  • 1983
Scale-Space and Edge Detection Using Anisotropic Diffusion
TLDR
A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.
Edge preserving smoothing
Detecting and localizing edges composed of steps, peaks and roofs
TLDR
A two-dimensional version of the approach is developed which has the property of being able to represent multiple edges at the same location and determine the orientation of each to any desired precision, which permits junctions to be localized without rounding.
Adaptive Smoothing: A General Tool for Early Vision
TLDR
The authors present a method to smooth a signal-whether it is an intensity image, a range image, or a contour-which preserves discontinuities and thus facilitates their detection and makes it possible to derive a novel scale-space representation of a signal using a small number of scales.
On Detecting Edges
TLDR
The results indicate that the proposed operator is superior with respect to detection, localization, and resolution.
Theory of edge detection
  • D. Marr, E. Hildreth
  • Mathematics
    Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1980
TLDR
The theory of edge detection explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround ∇2G filters acting on the image forms the basis for a physiological model of simple cells.
...
...