Abstract | ||
---|---|---|
The use of visual representations in which pixel-size and local neighbor- hood topology are not constant is termed space-variant vision. This is the dominant visual architecture in all higher vertebrate visual systems, and is coming to play an important role in real-time active vision applications in the form of log-polar, foveating pyramid, and related approaches to machine vision. The breaking of translation symmetry that is unavoidably associated with space-variant vision presents a major algorithmic complication for im- age processing. In this paper we use a Lie group approach to derive a kernel which provides a generalization of the Fourier Transform that provides a quasi-shift invariant template matching capability in the distorted (range) coordinates of the space-variant mapping. We work out the special case of the log-polar mapping, which is the principle space-variant mapping in use; in this case, we call the associated integral transform the ìexponential chirp |
Year | DOI | Venue |
---|---|---|
1997 | 10.1006/rtim.1996.0054 | Real-Time Imaging |
Keywords | Field | DocType |
fourier analysis,cortical architecture,lie group,fourier transform,integral transforms,machine vision,template matching,shift invariant,real time,visual system,active vision | Computer vision,Active vision,Fourier analysis,Invariant (physics),Computer science,Image processing,Fourier transform,Invariant (mathematics),Artificial intelligence,Matched filter,Integral transform | Journal |
Volume | Issue | ISSN |
3 | 3 | Real-Time Imaging |
Citations | PageRank | References |
3 | 1.00 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Giorgio Bonmassar | 1 | 159 | 33.51 |
E L Schwartz | 2 | 563 | 78.66 |