Title :
A general parameter updating approach to image classification
Author :
Jiang, Hongtao ; Bølviken, Erik
Author_Institution :
Dept. of Inf., Oslo Univ., Norway
Abstract :
This paper presents an EM approach to parameter updating in supervised image classification based on the maximum aposteriori (MAP) estimation. By specifying suitable prior distribution in the form of constraint on the differences between class mean vectors, the new algorithm generally gives better estimates of the class means than the maximum likelihood-EM algorithm, as shown by results with MR images of human brain
Keywords :
image classification; EM approach; NMR imaging; class mean vectors; human brain image; image classification; maximum aposteriori estimation; maximum likelihood estimation; parameter updating; Bayesian methods; Covariance matrix; Humans; Image classification; Informatics; Iterative methods; Maximum likelihood estimation; Parameter estimation; Stochastic processes; Testing;
Conference_Titel :
Pattern Recognition, 1994. Vol. 1 - Conference A: Computer Vision & Image Processing., Proceedings of the 12th IAPR International Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6265-4
DOI :
10.1109/ICPR.1994.576417
