Visual Computing and Image Processing Lab
Oklahoma State University

Imaging, Processing, Inferencing and Learning


Home
News
Members
Equipment
Research
Publications
Projects
Album

 

Bayesian Image Segmentation


We have studied Bayesian image segmentation by addressing two important and inter-related issues under the multi-scale segmentation framework. (1) How to enhance the capability of texture modeling that offers more complete and accurate characterization. (2) How to incorporate appropriate multiscale contextual information to improve the homogeneity and consistency of the segmentation map. Specifically, we have employed wavelet-domain hidden Markov models (HMMs) to address the first issue, and we have developed a joint multi-context and multiscale and  (JMCMS) approach for the second issue. Moreover, we have extended our segmentation methods from the supervised case to un-supervised case. The proposed segmentation methods have been examined in natural images, remote sensing imagery and document images. 


Unsupervised segmentation results

Related Publications

  • X. Fan and G. Fan, "Joint Segmentation and Recognition of License Plate Characters", in Proc. of IEEE International Conference on Image Processing (ICIP), San Antonio, TX, Sept. 2007.

  • X. Song and G. Fan, "Unsupervised Image Segmentation using Wavelet-domain Hidden Markov Models", in Proc. SPIE Wavelet X, Volume 5207, San Diego, CA, August 2003.

  • L. Liu, Y. Dong, X. Song, and G. Fan, "A Entropy-based Segmentation Algorithm for Computer-Generated Document Images", in Proc. IEEE International Conference on Image Processing, Barcelona, Span, September 2003.

  • Y. Dong, L. Liu, X. Song, and G. Fan, "A New Simplified Quantization Rate-Distortion Model for Fast Document Image Segmentation", in Proc. of the 45th IEEE International Midwest Symposium on Circuits and Systems, Tulsa, OK, Aug. 2002.

  • X. Song and G. Fan, "On Capturing Likelihood Disparity for Unsupervised Image Segmentation", in Proc. IEEE Statistical Signal Processing Workshop, St. Louis, MO, September 2003.

  • G. Fan and X.-G. Xia, “Wavelet-based Texture Analysis and Synthesis Using Hidden Markov Models,” IEEE Trans. on Circuits and Systems, Vol. 50, No. 1, pp106-120, Jan. 2003.

  • G. Fan and X.-G. Xia, “A Joint Multi-context and Multiscale Approach to Bayesian Image Segmentation,” IEEE Trans. Geoscience and Remote Sensing, Vol. 39, No. 12, 2001, pp2680-2688.

  • X. Song and G. Fan, “Unsupervised Bayesian Image Segmentation using Wavelet-domain Hidden Markov Models", in Proc. IEEE International Conference on Image Processing, Barcelona, Span, September 2003.

  • X. Song and G. Fan, “A Study of Supervised, Semi-Supervised and Unsupervised Multiscale Bayesian Image Segmentation”, Proc. of the 45th IEEE Int’l Midwest Symposium on Circuits and Systems, Tulsa, OK, Aug. 2002.

 
Copyright © 2008 VCIPL@OSU, All rights reserved.
(Acknowledgements: The template is from Interspire Free Templates, and free pictures are from 3DLuVr.com.)