基于对比度增强和背景估计的文档图像二值化

针对文档图像存在的退化状况对其二值化处理的影响，文中提出一种基于对比度增强和背景估计的文档图像二值化算法，用于对退化的文档图像进行二值化增强处理。该算法根据不同子区域亮度信息的差异采用不同对比度增强算法对文档图像进行增强处理，通过运用形态学闭运算对增强后的文档图像进行处理来移除文档图像的背景，结合Ostu和Sauvola算法获取文档图像的二值化图像，并通过基于边缘像素邻域灰度值的分布情况进行文本断笔修复。实验结果表明，该算法的F-Measure（FM）为90.47%，峰值信噪比（PSNR）达到19.15 dB，负率指标（NRM）低至0.053 8，分类错误度量（MPM）降至0.000 33，验证了本文提出的二值化算法的有效性。

Document Image Binarization Based on Contrast Enhancement and Background Estimation

Aiming at the impact of degradation of document image on its binarization, this paper presents a binary image algorithm based on contrast enhancement and background estimation, which is used to binarize the degraded document image. The algorithm uses the different contrast enhancement algorithm to enhance the document image according to the difference of the luminance information of the different sub-regions. The background of the document image is removed by processing the enhanced document image by using a morphological closed operation, and the binarized image of the document image is obtained by combining the Ostu and Sauvola algorithms. The broken handwriting repair is performed by the distribution of the neighborhood of the edge pixels gray value.The experimental results show that the F-Measure （FM） is 90.47%, the peak signal-to-noise ratio （PSNR） is 19.15dB, the negative rate index （NRM） is as low as 0.0538, and the classification error measure （MPM） is reduced to 0.00033. The validity of the binarization algorithm proposed in this paper is verified.