Image Segmentation Using Region-Based Latent Variables and Belief Propagation

スポンサーリンク

概要

• 論文の詳細を見る

• We derive a deterministic algorithm that restores and segments an image using belief propagation and a variational Bayesian method based on region-based latent variables and a coupled MRF model. This algorithm estimates two hyperparameters as well as infers the original image and the latent variables. In addition, the algorithm carries out model selection by minimizing the variational free energy. Through experiments using artificial images and a natural image degraded by Gaussian noises, we show that the derived algorithm has the potential ability to restore and segment using a single noisy image.

• 2011-09-15

著者

• Miyoshi Seiji

  Kansai Univ. Osaka

• Okada Masato

  The Univ. Of Tokyo:riken Brain Sci. Inst.

• Okada Masato

  The University of Tokyo, Kashiwa, Chiba 277-8561, Japan

• Miyoshi Seiji

  Kansai University, Suita, Osaka 564-8680, Japan

• Hasegawa Ryota

  Graduate School, Kansai University, Suita, Osaka 564-8680, Japan

• Hasegawa Ryota

  Graduate School of Science and Engineering, Kansai University, Suita, Osaka 564-8680, Japan

関連論文

• Analysis of Ensemble Learning Using Simple Perceptrons Based on Online Learning Theory
• S2f2-2 Itinerancy dynamics of macroscopic states caused by correlated noise(S2-f2: "Dynamism of the Brain States (II): Towards a new paradigm of understanding",Symposia,Abstract,Meeting Program of EABS & BSJ 2006)
• 22pVC-7 Belief propagation as a potential encoder for lossy compression schemes using tree-like non-monotonic multilayer perceptrons
• 26pTE-9 Statistical mechanics of lossy compression for non-monotonic multilayer perceptrons
• Image Segmentation Using Region-Based Latent Variables and Belief Propagation
• Image Segmentation and Restoration Using Switching State-Space Model and Variational Bayesian Method

スポンサーリンク