Title :
A novel two-tier Bayesian based method for hair segmentation
Author :
Wang, Dan ; Shan, Shiguang ; Zeng, Wei ; Zhang, Hongming ; Chen, Xilin
Abstract :
In this paper, a novel two-tier Bayesian based method is proposed for hair segmentation. In the first tier, we construct a Bayesian model by integrating hair occurrence prior probabilities (HOPP) with a generic hair color model (GHCM) to obtain some reliable hair seed pixels. These initial seeds are further propagated to their neighborhood pixels by utilizing segmentation results of mean shift, to obtain more seeds. In the second tier, all of these selected seeds are used to train a hair-specific Gaussian model, which are combined with HOPP to build the second Bayesian model for pixel classification. Mean shift results are further utilized to remove holes and spread hair regions. The experimental results illustrate the effectiveness of our approach.
Keywords :
Bayes methods; Gaussian processes; image classification; image segmentation; probability; generic hair color model; hair occurrence prior probability; hair segmentation; hair-specific Gaussian model; mean shift; pixel classification; two-tier Bayesian based method; Bayesian methods; Computers; Content addressable storage; Diversity reception; Face detection; Hair; Image segmentation; Information processing; National electric code; Pixel; GMM; Gaussian Model; Hair Segmentation; Mean Shift; Two-tier Bayesian Model;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5414215