Publication Details
Title: Stochastic Model-Based Image Segmentation Using Markov Random Fields and Multi-Layer Perceptrons
Author: J. Zhang and N. Morgan
Group: ICSI Technical Reports
Date: November 1990
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-90-061.pdf
Overview:
Recently, there has been much interest in Markov random field (MRF) model-based techniques for image (texture) segmentation. MRF models are used to enforce reasonable physical constraints on segmented regions, such as the continuity of the regions, and have been shown to improve segmentation results. However, in these techniques, parametric probability models which do not have sufficient physical justifications are often used to model observed image data because they are computationally tractable. In this paper, we outline an MRF approach to image segmentation in which the probability distribution of observed image data is modeled by using a multi-layer perceptron (MLP) which can "learn" the distribution from training data. Furthermore, we propose a technique to achieve unsupervised image segmentation using this approach. We hope that this will improve the current MRF image segmentation techniques by providing a better model for observed image data.
Bibliographic Information:
ICSI Technical Report TR-90-061
Bibliographic Reference:
J. Zhang and N. Morgan. Stochastic Model-Based Image Segmentation Using Markov Random Fields and Multi-Layer Perceptrons. ICSI Technical Report TR-90-061, November 1990
Author: J. Zhang and N. Morgan
Group: ICSI Technical Reports
Date: November 1990
PDF: http://www.icsi.berkeley.edu/pubs/techreports/tr-90-061.pdf
Overview:
Recently, there has been much interest in Markov random field (MRF) model-based techniques for image (texture) segmentation. MRF models are used to enforce reasonable physical constraints on segmented regions, such as the continuity of the regions, and have been shown to improve segmentation results. However, in these techniques, parametric probability models which do not have sufficient physical justifications are often used to model observed image data because they are computationally tractable. In this paper, we outline an MRF approach to image segmentation in which the probability distribution of observed image data is modeled by using a multi-layer perceptron (MLP) which can "learn" the distribution from training data. Furthermore, we propose a technique to achieve unsupervised image segmentation using this approach. We hope that this will improve the current MRF image segmentation techniques by providing a better model for observed image data.
Bibliographic Information:
ICSI Technical Report TR-90-061
Bibliographic Reference:
J. Zhang and N. Morgan. Stochastic Model-Based Image Segmentation Using Markov Random Fields and Multi-Layer Perceptrons. ICSI Technical Report TR-90-061, November 1990