Title :
MAP segmentation of color images using constraint satisfaction neural network
Author :
Kurugollu, F. ; Sankur, B.
Author_Institution :
TUBITAK Marmara Res. Centre, Gebze-KOCAELI, Turkey
Abstract :
An improved segmentation algorithm is proposed, which implements the MAP estimation of the label field using a Constraint Satisfaction Neural Network (CSNN). It uses the advantages of stochastic relaxation with those of Gauss-Markov Random Field (GMRF) models. The performance of the algorithm is compared vis-a-vis alternate relaxation schemes using both synthetic and real images
Keywords :
image colour analysis; image segmentation; neural nets; MAP estimation; color images; constraint satisfaction neural network; segmentation algorithm; stochastic relaxation; Cellular neural networks; Color; Context modeling; Gaussian processes; Hopfield neural networks; Image segmentation; Layout; Neural networks; Neurons; Stochastic processes;
Conference_Titel :
Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-5467-2
DOI :
10.1109/ICIP.1999.817108
