Stochastic search approach to object location

Author

Cohen, Harvey A. ; Harvey, Alan L.

Author_Institution

Dept. of Comput. Sci. & Comput. Eng., La Trobe Univ., Melbourne, Vic., Australia

Volume

3

fYear

1994

fDate

2-5 Oct 1994

Firstpage

2237

Abstract

Object location within an image involves establishing a location within an image for which a particular error function is minimised, and thus is essentially an optimization problem. Within the content of location via template matching, a random search approach, called a cluster search, based on an extension of mathematical methods due to Matyas has been studied to determine the most appropriate parameter β. For well chosen β the cluster search has been shown to be on average significantly faster than the fastest deterministic search schemes, notably coarse fine approaches

Keywords

computer vision; image matching; object recognition; search problems; stochastic processes; Matyas algorithm; cluster search; coarse fine approaches; grey scale template; image procesing; object location; optimization; random search; stochastic search; template matching; Australia; Character recognition; Computer errors; Computer science; Convergence; Image coding; Image recognition; Machine vision; Shape; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-2129-4

Type

conf

DOI

10.1109/ICSMC.1994.400197

Filename

400197