Image labeling is a process of recognizing each segmented region properly exploiting the properties of the regions and the spatial relationsships between regions. In some sense, image labeling is an optimization process of indexing regions using the constraints as to the scene knowledge. In this paper, we further investigate a method of efficiently labeling images using the Markov Random Field (MRF). MRF model is defined on the region adjacency graph and the labeling is then optimally determined using the simulated annealing. To endow the adaptability to the MRF-based image labeling, we have proposed a parameter estimation technique based on error backpropagation. We analyze the proposed method through experiments using the real natural scene images.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Il Young KIM, Hyun Seung YANG, "Markov Random Field Based Image Labeling with Parameter Estimation by Error Backpropagation" in IEICE TRANSACTIONS on Information,
vol. E74-D, no. 10, pp. 3513-3521, October 1991, doi: .
Abstract: Image labeling is a process of recognizing each segmented region properly exploiting the properties of the regions and the spatial relationsships between regions. In some sense, image labeling is an optimization process of indexing regions using the constraints as to the scene knowledge. In this paper, we further investigate a method of efficiently labeling images using the Markov Random Field (MRF). MRF model is defined on the region adjacency graph and the labeling is then optimally determined using the simulated annealing. To endow the adaptability to the MRF-based image labeling, we have proposed a parameter estimation technique based on error backpropagation. We analyze the proposed method through experiments using the real natural scene images.
URL: https://global.ieice.org/en_transactions/information/10.1587/e74-d_10_3513/_p
Copy
@ARTICLE{e74-d_10_3513,
author={Il Young KIM, Hyun Seung YANG, },
journal={IEICE TRANSACTIONS on Information},
title={Markov Random Field Based Image Labeling with Parameter Estimation by Error Backpropagation},
year={1991},
volume={E74-D},
number={10},
pages={3513-3521},
abstract={Image labeling is a process of recognizing each segmented region properly exploiting the properties of the regions and the spatial relationsships between regions. In some sense, image labeling is an optimization process of indexing regions using the constraints as to the scene knowledge. In this paper, we further investigate a method of efficiently labeling images using the Markov Random Field (MRF). MRF model is defined on the region adjacency graph and the labeling is then optimally determined using the simulated annealing. To endow the adaptability to the MRF-based image labeling, we have proposed a parameter estimation technique based on error backpropagation. We analyze the proposed method through experiments using the real natural scene images.},
keywords={},
doi={},
ISSN={},
month={October},}
Copy
TY - JOUR
TI - Markov Random Field Based Image Labeling with Parameter Estimation by Error Backpropagation
T2 - IEICE TRANSACTIONS on Information
SP - 3513
EP - 3521
AU - Il Young KIM
AU - Hyun Seung YANG
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E74-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1991
AB - Image labeling is a process of recognizing each segmented region properly exploiting the properties of the regions and the spatial relationsships between regions. In some sense, image labeling is an optimization process of indexing regions using the constraints as to the scene knowledge. In this paper, we further investigate a method of efficiently labeling images using the Markov Random Field (MRF). MRF model is defined on the region adjacency graph and the labeling is then optimally determined using the simulated annealing. To endow the adaptability to the MRF-based image labeling, we have proposed a parameter estimation technique based on error backpropagation. We analyze the proposed method through experiments using the real natural scene images.
ER -