This Paper Provides New Insights into the Formation of One-Dimensional (Line-Scan) Image Autocorrelation Functions. We Model a Line Scan as a Composition of Individual Object-Images that Have Random Positions, Widths and Intensities and that Occlude One Another. We Derive the Autocorrelation Function of This Model as a Function of Object-Image Width and Intensity Distributions. We Show that Any Assumption Regarding the Form of the Autocorrelation Function Places a Constraint on Object-Image Width and Intensity Distributions and We Derive the Object-Image Width Distribution Associated with the Widely Used Symmetric-Exponential Autocovariance Model.
J. A. Stuller, "A Stochastic One-Dimensional Image Model based on Occluding Object Images," Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 18 - 24, article no. 471409, Institute of Electrical and Electronics Engineers, Jan 1994.
The definitive version is available at https://doi.org/10.1109/ACSSC.1994.471409
Electrical and Computer Engineering
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2023 Institute of Electrical and Electronics Engineers, All rights reserved.
01 Jan 1994
National Science Foundation, Grant MIP-9223020