Feature Detection with Automatic Scale Selection
Tony LindebergTechnical report ISRN KTH NA/P--96/18--SE. Department of Numerical Analysis and Computing Science, Royal Institute of Technology, S-100 44 Stockholm, Sweden, May 1996.
International Journal of Computer Vision, vol 30, number 2, pp 77--116, 1998.
AbstractThe fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. Whereas scale-space representation provides a well-founded framework for dealing with this issue by representing image structures at different scales, traditional scale-space theory does not address the problem of how to select local appropriate scales for further analysis.
This article proposes a systematic approach for dealing with this problem---a heuristic principle is presented stating that local extrema over scales of different combinations of gamma-normalized derivatives are likely candidates to correspond to interesting structures. Specifically, it is proposed that this idea can be used as a major mechanism in algorithms for automatic scale selection, which adapt the local scales of processing to the local image structure.
Support is given in terms of a general theoretical investigation of the behaviour of the scale selection method under rescalings of the input pattern and by experiments on real-world and synthetic data. Support is also given by a detailed analysis of how different types of feature detectors perform when integrated with a scale selection mechanism and then applied to characteristic model patterns. Specifically, it is described in detail how the proposed methodology applies to the problems of blob detection, junction detection, edge detection, ridge detection and local frequency estimation.
Keywords: scale, scale-space, scale selection, normalized derivative, feature detection, blob detection, corner detection, frequency estimation, Gaussian derivative, scale-space, multi-scale representation, computer vision
Postscript: (2.8 Mb)
PDF: (3.5 Mb)
Background and related material: (Earlier technical report with general scale selection principle) (First reference to general scale selection principle) (Earlier and closely related scale selection methodology for blob detection) (Application of scale selection principle to junction detection) (Application of scale selection principle to feature tracking) (Scale selection for edge detection and ridge detection) (Scale selection for flow estimation) (Application to edge classification) (Application to shape-from-texture and shape-from-disparity-gradients) (Review paper on principles for automatic scale selection) (Monograph on scale-space theory) (Other publications on scale-space theory)
Responsible for this page: Tony Lindeberg