Abstract
An approach to evaluating the sizes of round microparticles in a digitized image was proposed. It is based on preliminary localization of particles followed by refinement of their parameters (coordinates and size) by optimal approximation of the brightness function by the rms criterion Attention was focused on optimization which relies on stochastic approximation with averaging. Results of a numerical experiment were presented.
Similar content being viewed by others
REFERENCES
Pyt'ev, Yu.P. and Chulichkov, A.I., Computer Analyzes Image Form, Mat., Kibern., 1988, no. 5, pp. 3-46.
Ermakov, S.M., Metod Monte-Carlo i smezhnye voprosy, (Monte Carlo Method and Related Problems), Moscow: Nauka, 1975.
Polyak, B.T., A New Method of Stochastic Approximation Type, Avtom.Telemekh., 1990, no. 7, pp. 98-107.
Polyak, B.T. and Juditsky, A.B., Acceleration of Stochastic Approximation by Averaging, SIAM J.Contr.Optimiz., 1992, vol. 30, no. 4, pp. 838-855.
Nazin, A.V., Metod stokhasticheskoi approksimatsii s usredneniem (Method of Stochastic Approximation with Averaging), Moscow: Mosk. Aviats. Inst., 2001.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Nazin, A.V., Piterskaya, E.V. Method of Stochastic Approximation with Averaging for Evaluating Sizes of Microparticles in Digital Image. Automation and Remote Control 63, 1853–1859 (2002). https://doi.org/10.1023/A:1020919818455
Issue Date:
DOI: https://doi.org/10.1023/A:1020919818455