A New Image Binarization Method Using Histogram and Spectral Clustering
Rui Wu 0, Fang Yin, Jianhua Huang, Xianglong Tang
0Harbin Institute of Technology
Available Online December 2008.
- https://doi.org/10.2991/jcis.2008.73How to use a DOI?
- binarization processing; graph cut; spectral clustering
- A novel approach of binarization for gray images is presented in this paper. The proposed algorithm uses the normalized graph cut(Ncut) as the measure for spectral clustering, and the weighted matrix used in evaluating the graph cuts is based on the gray levels of an image, rather than the image pixels commonly. Thus, the algorithm requires much smaller spatial costs and lower computation complexity. Experiments on text images in natural scene show the superior performance of the proposed method compared to the typical thresholding algorithms.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Rui Wu AU - Fang Yin AU - Jianhua Huang AU - Xianglong Tang PY - 2008/12 DA - 2008/12 TI - A New Image Binarization Method Using Histogram and Spectral Clustering BT - 11th Joint International Conference on Information Sciences PB - Atlantis Press SP - 428 EP - 432 SN - 1951-6851 UR - https://doi.org/10.2991/jcis.2008.73 DO - https://doi.org/10.2991/jcis.2008.73 ID - Wu2008/12 ER -