Title :
Markov random field based image labeling with parameter estimation by error backpropagation
Author :
Kim, Y., II ; Yang, Hyun S.
Author_Institution :
Dept. of Comput. Sci., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea
Abstract :
The authors investigate a method of efficiently labeling images using the Markov random field (MRF). The MRF model is defined on the region adjacency graph and the labeling is then optimally determined using simulated annealing. The MRF model parameters are automatically estimated using an error backpropagation network. The proposed method is analyzed through experiments using real natural scene images
Keywords :
Markov processes; neural nets; parameter estimation; pattern recognition; simulated annealing; Markov random field based image labeling; error backpropagation; error backpropagation network; neural nets; parameter estimation; pattern recognition; real natural scene images; region adjacency graph; simulated annealing; Backpropagation; Computer errors; Image recognition; Image segmentation; Indexing; Labeling; Layout; Markov random fields; Parameter estimation; Simulated annealing;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170524
