Fiber Segmentation in Composite Materials Using Marked Point Processes

Abstract

This paper presents a new method dedicated to unsupervised 2D segmentation of fibers in a section of composite carbon-fiber materials. The framework relies on a marked point process algorithm. We shall create random elliptical objects to fit the fiber distribution in the image. The interaction rules between the objects complete the model. Using a Markov Chain Monte Carlo (MCMC) method, the algorithm converges to a configuration which is close to the fiber distribution in the images. At each step, the configuration is evaluated considering its proximity to the target distribution. In order to achieve this task, we propose a mixed data model using both grey level values and gradients to evaluate the likelihood of the current configuration. This mixed model overcomes the problems of luminance variation, contour discontinuities and high noise level. Finally, the results on the composite material sections illustrate the efficiency of the segmentation and suggest that the marked point processes can be a promising tool for fiber detection.

Authors and Affiliations

Barna KERESZTES, Olivier LAVIALLE, Sorin POP, Monica BORDA

Keywords

Related Articles

Characterization Of Small Cells Networks Deployment Options And Their Impact Upon Macro-Cellular Networks

This paper investigates the effect of small cells networks deployment in a typical traditional macro-cellular mobile communications network. The main deployment options are presented and their impact is shown for the cas...

A Simulation of the Perfectly Matched Layer in the 3-D Case

The Perfectly Matched Layer (PML) technique, introduced by J. P. Berenger in 1994, is used for solving unbounded space problems. In this paper we implemented in Matlab a three dimensional Finite-Difference Time-Domain co...

Maximum Power Point Tracking Simulator In Charging Photovoltaic Systems

The task of Maximum Power Point Tracking (MPPT) is to operate with photovoltaic (PV) modules in a manner that allows them to produce all the power they are capable of. In this paper a system for modeling different MPPT a...

A VLSI Implementation of a New Low Voltage 4th Order Differential Gm-C Band-Pass Filters For Different Approximation In CMOS Technology

In this paper we present a new low voltage 4th order differential Gm-C band-pass filter (BPF) for different approximations (Butterworth or Chebyshev), which has been designed in CMOS technology. This differential BPF is...

TTS Experiments: Romanian Prosody

In a text-to-speech synthesis system, prosody prediction and generation, is one of the most critical tasks. Prosody is composed by the melody, intensity and by the rhythm of speech. The current paper focuses on the Roman...

Download PDF file
  • EP ID EP84698
  • DOI -
  • Views 110
  • Downloads 0

How To Cite

Barna KERESZTES, Olivier LAVIALLE, Sorin POP, Monica BORDA (2009). Fiber Segmentation in Composite Materials Using Marked Point Processes. Acta Technica Napocensis- Electronica-Telecomunicatii (Electronics and Telecommunications), 50(1), 1-6. https://europub.co.uk/articles/-A-84698