Spectre: An Improved Phantom Edge Finder

Both edge finders use the topological sum to remove noise from second difference responses, so that zero-crossings in these responses represent reliable boundaries. Spectre applies the same techniques to a combination of first and third differences, producing a new map that reliably distinguishes real boundaries from spurious boundaries appearing in staircase intensity patterns. Similar processing is used to mark response regions not associated with zero-crossings (including roof edges) and to compute boundary strengths.

[1]  D. Huttenlocher.  Three-Dimensional Recognition of Solid Objects from a Two- Dimensional Image , 1988 .

[2]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  Ramesh C. Jain,et al.  Behavior of Edges in Scale Space , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[5]  David Lee,et al.  Edge detection through residual analysis , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Gérard G. Medioni,et al.  Refining edges detected by a LoG operator , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  Achim Hummel,et al.  Representations Based on Zero-Crossing in Scale-Space-M , 2018, CVPR 1986.

[8]  Gérard G. Medioni,et al.  Detection of Intensity Changes with Subpixel Accuracy Using Laplacian-Gaussian Masks , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  John E. W. Mayhew,et al.  Psychophysical and Computational Studies Towards a Theory of Human Stereopsis , 1981, Artif. Intell..

[10]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  James J. Clark.  Singularity Theory and Phantom Edges in Scale Space , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Gérard G. Medioni,et al.  Detection, Localization, and Estimation of Edges , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  James J. Clark.  Authenticating Edges Produced by Zero-Crossing Algorithms , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Margaret M. Fleck.  Boundaries and Topological Algorithms , 1988 .

[15]  H H Bülthoff,et al.  Integration of depth modules: stereo and shading. , 1988, Journal of the Optical Society of America. A, Optics and image science.

[16]  R. Watt,et al.  The recognition and representation of edge blur: Evidence for spatial primitives in human vision , 1983, Vision Research.

[17]  Margaret M. Fleck.  Representing space for practical reasoning , 1988, Image Vis. Comput..

[18]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[19]  R. Watt,et al.  A theory of the primitive spatial code in human vision , 1985, Vision Research.