Image Segmentation Using Markov Random Field Model in Fully Parallel Cellular Network Architectures

✍ Scribed by Tamás Szirányi; Josiane Zerubia; LászLó Czúni; David Geldreich; Zoltán Kato

• Publisher: Elsevier Science
• Year: 2000
• Tongue: English
• Weight: 669 KB
• Volume: 6
• Category: Article
• ISSN: 1077-2014
• DOI: 10.1006/rtim.1998.0159

✦ Synopsis

arkovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. Herein, we show that the Markovian labeling approach can be implemented in fully parallel cellular network architectures, using simple functions and data representations. This makes possible to implement our model in parallel imaging VLSI chips.

As an example, we have developed a simpli®ed statistical image segmentation algorithm for the Cellular Neural/Nonlinear Networks Universal Machine (CNN-UM), which is a new image processing tool, containing thousands of cells with analog dynamics, local memories and processing units. The Modi®ed Metropolis Dynamics (MMD) optimization method can be implemented into the raw analog architecture of the CNN-UM. We can introduce the whole pseudo-stochastic segmentation process in the CNN architecture using 8 memories/cell. We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw). With this architecture, the proposed VLSI CNN chip can execute a pseudo-stochastic relaxation algorithm of about 100 iterations in about 100 ms.

In the suggested solution the segmentation is unsupervised, where a pixel-level statistical estimation model is used. We have tested dierent monogrid and multigrid architectures.

In our CNN-UM model several complex preprocessing steps can be involved, such as texture-classi®cation or anisotropic diusion. With these preprocessing steps, our fully parallel cellular system may work as a high-level image segmentation machine, using only simple functions based on the close-neighborhood of a pixel.