Coarse image region segmentation using region-and boundary-based coupled MRF models and their PWM VLSI implementation

  • Authors:

  • Yusuke Kawashima;Daisuke Atuti;Kazuki Nakada;Masato Okada;Takashi Marie

  • Affiliations:

  • Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu-shi, Japan;Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu-shi, Japan;Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu-shi, Japan;Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa-shi, Japan;Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu-shi, Japan

  • Venue:
  • IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a novel region-based coupled Markov Random Field (MRF) model for coarse image region segmentation on silicon platforms. Coupled MRF models are classified into boundary- and region-based models, in which hidden variables are referred to as a line process and a label process, respectively. These hidden variables are crucial for detecting discontinuities in motion, intensity, color, and depth in visual scenes. For a coarse image region segmentation task, we address a region-based coupled MRF model with hidden phase variables. It is shown that the region-based coupled MRF model has an advantage over the resistive-fuse network, which is a boundary-based coupled MRF model, in dealing with the hidden variables explicitly. These models work complementarily for a coarse image region segmentation task. For real-time region segmentation operation, we have designed a merged analog/digital CMOS circuit implementing both functions of the boundary- and region-based coupled MRF models using a pulse modulation approach.