Abstract
Generalized smoothing networks have been developed which enforce smoothness constraints for any arbitrary level of derivative of the input data. Furthermore, discontinuities of any order of derivative can be detected by providing for continuous line processes. which selectively inhibit smoothing. Second- and higher-order networks are required for many problems in early vision; first-order networks are often unsatisfactory. Examples in surface interpolation, edge detection, and image segmentation are shown. Solution of these types of problems typically takes a prohibitive amount of time, even on supercomputers. A significant advantage of these proposed networks is that they can be mapped directly to analog VLSI hardware.
Recommended Citation
S. C. Liu and J. G. Harris, "Generalized Smoothing Networks In Early Vision," Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 184 - 191, Institute of Electrical and Electronics Engineers, Dec 1989.
The definitive version is available at https://doi.org/10.1109/CVPR.1989.37848
Department(s)
Electrical and Computer Engineering
International Standard Book Number (ISBN)
0-8186-1952-x
International Standard Serial Number (ISSN)
1063-6919
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Dec 1989
