2013 12th International Conference on Document Analysis and Recognition (2003)
Aug. 3, 2003 to Aug. 6, 2003
Lixin Fan , Xerox Research Centre Europe
Liying Fan , National University of Singapore
Chew Lim Tan , National University of Singapore
To distinguish image features from high level noises, we propose to exploit the spatial correlations between wavelet coefficients by replacing the thresholding process with a diffusion process. The proposed smoothing method is more robust to noise when applied to highly corrupted document images.
Lixin Fan, Liying Fan, Chew Lim Tan, "Wavelet Diffusion for Document Image Denoising", 2013 12th International Conference on Document Analysis and Recognition, vol. 02, no. , pp. 1188, 2003, doi:10.1109/ICDAR.2003.1227845