A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
Scale-Space Theory in Computer Vision
Although traditional scale-space theory provides a well-founded framework for dealing with image structures at di erent scales, it does not directly address the problem of how t o select appropriate scales for further analysis. This paper introduces a new tool for dealing with this problem. A heuristic principle is proposed stating that local extrema over scales of di erent c o m binations of normalized s c ale invariant derivatives are likely candidates to correspond to interesting structures.doi:10.1007/978-1-4757-6465-9_13 fatcat:y5wwueoimzb4lixmk5i5wtaewi