Active detection and classification of junctions by foveation with a head-eye system guided by the scale-space primal sketch

Kjell Brunnstrom, Tony Lindeberg and Jan-Olof Eklundh

Technical report ISRN KTH/NA/P--91/31--SE.

Shortened version in Proc. of the 2nd European Conference on Computer Vision, (Santa Margherita Ligure, Italy), May. 1992, Vol. 588 of Lecture Notes in Computer Science, pages 701--709, Springer-Verlag.

Abstract

We consider how junction detection and classification can be performed in an active visual system. This is to exemplify that feature detection and classification in general can be done by both simple and robust methods, if the vision system is allowed to look at the world rather than at prerecorded images. We address issues on how to attract the attention to salient local image structures, as well as on how to characterize those.

Full paper: (PDF 0.5Mb)

See also: (Focus of attention)