1 April 1997 Image segmentation by multigrid MRF and perceptual optimization
Author Affiliations +
This paper describes a Markov random field (MRF) approach to image segmentation. Unlike most previous MRF techniques, which are based on pixel-classification, this approach groups pixels that are similar. This removes the need to know the number of image classes. Mean field theory and multigrid processing are used in the subsequent optimization to find a good segmentation and to alleviate local minimum problems. Variations of the MRF approach are investigated by incorporating features/schemes motivated by characteristics of the human vision system (HVS). Preliminary results are promising and indicate that multi-grid and HVS based features/schemes can significantly improve segmentation results.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Zhang, Jun Zhang, Dongyan Wang, Dongyan Wang, Jianhua Liu, Jianhua Liu, } "Image segmentation by multigrid MRF and perceptual optimization", Proc. SPIE 3030, Applications of Artificial Neural Networks in Image Processing II, (1 April 1997); doi: 10.1117/12.269774; https://doi.org/10.1117/12.269774

Back to Top