Color Image Segmentation Using Markov Random Field Models
Versandkostenfrei!
Versandfertig in 6-10 Tagen
36,99 €
inkl. MwSt.
PAYBACK Punkte
18 °P sammeln!
This book focuses on a prime research area in Image Processing i.e. Color Image Segmentation. We have used Stochastic Models more particularly Markov Random Field (MRF) models for the problem of Color Image Segmentation. In order to improve the efficiency of the color model, the notion of controlled correlation among different color planes has been introduced and hence a new MRF model called Compound MRF (COMRF) model has been proposed. The controlled correlation feature has been achieved by controlling the associated MRF model parameter . This notion proved to be effective in modeling color i...
This book focuses on a prime research area in Image Processing i.e. Color Image Segmentation. We have used Stochastic Models more particularly Markov Random Field (MRF) models for the problem of Color Image Segmentation. In order to improve the efficiency of the color model, the notion of controlled correlation among different color planes has been introduced and hence a new MRF model called Compound MRF (COMRF) model has been proposed. The controlled correlation feature has been achieved by controlling the associated MRF model parameter . This notion proved to be effective in modeling color images. In order to model both color texture and scene images, a unifying MRF model called Constrained MRF (CMRF) model has been proposed. The constrained condition has been used to develop Constrained Compound MRF (CCOMRF) model and Double Constrained Compound MRF (DCCOMRF) model. The efficacy of these models have been tested with color image segmentation and it has been found that DCCOMRF model proved to be best for modeling color texture and scene images. The segmentation problem is cast as a pixel labeling problem and the pixel label estimation problem has been formulated using MAP.
Andere Kunden interessierten sich für
