The multiscale veto model: A two-stage analog network for edge detection and image reconstruction

This article presents the theory behind a model for a two-stage analog network for edge detection and image reconstruction to be implemented in analog VLSI. Edges are detected in the first stage using the multiscale veto rule, which states that an edge exists only if it can pass a threshold test for each of a set of smoothing filters of decreasing bandwidth. The image is reconstructed in the second stage from the brightness values at the pixels between which edges occur. The effect of the multiscale veto rule is that noise is removed with the efficiency of the narrowest-band smoothing filter, while edges are well-localized to feature boundaries without having to identify maxima in the magnitude of the gradient. Unlike previous analog models for edge detection and reconstruction, there are no problems of local minima, and for any given set of parameters, there is a unique solution. The reconstructed images appear natural and are very similar visually to the originals.

[1]  Granino A. Korn,et al.  Mathematical handbook for scientists and engineers , 1961 .

[2]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[3]  Berthold K. P. Horn,et al.  Determining lightness from an image , 1974, Comput. Graph. Image Process..

[4]  B. Logan.  Information in the zero crossings of bandpass signals , 1977, The Bell System Technical Journal.

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

[6]  John Batali.  A Vision Chip , 1981 .

[7]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[8]  Thomas F. Knight,et al.  Design of an integrated optical sensor with on-chip preprocessing , 1983 .

[9]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Andrew Blake,et al.  Boundary conditions for lightness computation in Mondrian World , 1985, Comput. Vis. Graph. Image Process..

[11]  Tomaso A. Poggio,et al.  On Edge Detection , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[13]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[14]  Alan V. Oppenheim,et al.  Reconstruction of Multidimensional Signals from Zero Crossings* , 1986, Topical Meeting On Signal Recovery and Synthesis II.

[15]  Thomas J. Richardson,et al.  Scale independent piecewise smooth segmentation of images via variational methods , 1990 .

[16]  P. W. Jones,et al.  Digital Image Compression Techniques , 1991 .

[17]  Hae-Seung Lee,et al.  CMOS resistive fuse circuits , 1991, 1991 Symposium on VLSI Circuits.

[18]  John L. Wyatt,et al.  CMOS resistive fuses for image smoothing and segmentation , 1992 .

[19]  Lewis Keast Craig.  An integrated image acquisition, smoothing and segmentation focal plane processor , 1992 .