Inverse Renormalization Group Transformations in Bayesian Image Processing

by Kazuyuki Tanaka (GSIS, Tohoku University, Japan)

Thursday 24 Sept 2015, 11:30 → 13:30 Europe/Rome

Aula 8 (Dip. di Fisica - Edificio E. Fermi)

First we show a new Bayesian image segmentation algorithm by combining a loopy belief propagation with an inverse real space renormalization group transformation to reduce the computational time. In some results of our experiment, we observe that the proposed method can reduce the computational time to less than one-tenth of that taken by conventional bayesian approaches. Moreover we propose also some other types of inverse renormalization group transformation to the computational time of probabilistic image processing based on Markov random fields. [Reference] K. Tanaka, S Kataoka, M. Yasuda and M. Ohzeki: Inverse Renormalization Group Transformation in Bayesian Image Segmentations, Journal of the Physical Society of Japan, vol.84, no.4, Article ID. 045001, 2015. http://journals.jps.jp/doi/abs/10.7566/JPSJ.84.045001