Title :
Ensemble classification of the VF dataset with limited merging
Author :
Yang, Zhihong ; Greenshieids, I.R.
Author_Institution :
Dept. of Comput. Sci. & Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
Ensemble classification (the concurrent development of K independent classifications) is a common practice in Gibbs classification. In this paper, we describe an adaptation of R. Azencott´s (1992) theorem on finite-time annealing, coupled with a limited merging protocol, which produces a final low-energy Gibbs classification of the Virtual Female (VF) data set
Keywords :
free energy; image classification; medical image processing; merging; simulated annealing; Virtual Female data set; concurrent development; ensemble classification; finite-time annealing; independent classifications; limited merging protocol; low-energy Gibbs classification; medical images; Annealing; Bayesian methods; Computer science; Data engineering; History; Image processing; Merging; Pattern recognition; Probability distribution; Protocols;
Conference_Titel :
Computer-Based Medical Systems, 2001. CBMS 2001. Proceedings. 14th IEEE Symposium on
Conference_Location :
Bethesda, MD
Print_ISBN :
0-7695-1004-3
DOI :
10.1109/CBMS.2001.941707
