Adaptive Binarization for Degraded Document Images
Landu Jiang, Kai Chen, Shibo Yan, Yi Zhou, Haibing Guan · 2009
Various types of degradations such as uneven illumination, shadows, low contrast, smears and heavy noise densities often make thresholding of the document images a difficult job. In this paper, we describe a new adaptive approach for degraded-document binarization. We use the dilation and erosion in gray-scale image processing; as a result get a new image in which the shadow levels and noise densities will be greatly reduced. After that we design the binarization technique combined the method which improved Niblack and the local thresholding using the small neighbourhood which influenced the mean value of the areas. The experimental result has shown that the proposed method performed as superior in comparison with other four contemporary and well-known adaptive binarization techniques on the document images with noises and complex backgrounds.