Some Pyramid Techniques for Image Segmentation
This paper describes a collection of multiresolution, or “pyramid”, techniques for rapidly extracting global structures (features, regions, patterns) from an image. If implemented in parallel on suitable cellular pyramid hardware, these techniques require processing times on the order of the logarithm of the image diameter.
KeywordsRoot Node Gray Level Image Block Endpoint Data Optical Flow Field
Unable to display preview. Download preview PDF.
- (1).D. Marr, Vision, Freeman, San Francisco, 1982, p. 95.Google Scholar
- (2).M. Wertheimer, Principles of perceptual organization, in Readings in Perception ( D.C. Beardslee and M. Wertheimer, eds.), Van Nostrand, Princeton, NJ, 1958, pp. 115–135.Google Scholar
- (4).P. Burt, Hierarchically derived piecewise polynomial approximations to waveforms and images, TR-838, Computer Vision Laboratory, University of Maryland, November 1979.Google Scholar
- (5).T.H. Hong, M.O. Shneier, R.L. Hartley, and A. Rosenfeld, Using pyramids to detect good continuation, IEEE Trans. SMC-13, 631–635, 1983.Google Scholar
- (6).R.L. Hartley and A. Rosenfeld, Hierarchical line linking for corner detection, in Integrated Technology for Parallel Image Processing ( S. Levialdi, ed.), Academic Press, New York, 1985, pp. 101–119.Google Scholar
- (8).L.G. Minor and J. Sklansky, The detection and segmentation of blobs in infrared images, IEEE Trans. SMC-11, 194–201, 1981.Google Scholar
- (9).T.N. Cornsweet, Visual Perception, Academic Press, New York, 1970, p. 27Google Scholar
- (10).J.M. Brady and H. Asada, Smoothed local symmetries and their implementation, AIM 757, Artificial Intelligence Laboratory, MIT, February 1984.Google Scholar
- (11).A.D. Gross, Multiresolution object detection and delineation, TR-1613, Center for Automation Research, University of Maryland, January 1986.Google Scholar
- (12).E.S. Baugher and A. Rosenfeld, Boundary localization in an image pyramid, TR-1488, Computer Vision Laboratory, University of Maryland, May 1985.Google Scholar
- (13).R.M. Bolle and D.B. Cooper, Bayesian recognition of local 3-D shape by approximating image intensity functions with quadric polynomials, IEEE Trans. PAMI-6, 418–429, 1984.Google Scholar