基于区域对比度增强的二值化算法

Binarization Method Based on Local Contrast Enhancement

降质文档图像二值化问题是图像处理领域的一个难点。该文通过分析图像不同区域灰度对比度的差异,为降质文档图像提出了新的二值化算法。首先利用四叉树原理自适应划分区域,再对不同灰度对比度区域采用不同对比度增强法以调整局部区域内的灰度对比度,最后根据灰度值出现的频率确定局部阈值。该文测试了随机拍摄的降质图像及DIBCO(Document Image Binarization COntest)图像集中的50幅图像。与4种经典算法比较,所提算法处理的降质图像具有最高F-measure值和峰值信噪比(PSNR值)。

Binarization for degraded document images is a difficult point in image processing. This paper presents a new binarization method for the degraded document images by analyzing the differences of image grayscale contrast in different areas. Firstly, theory of quadtree is used to divide areas adaptively. Secondly, various contrast enhancements are selected to adjust local grayscale contrast for different contrast areas. Lastly, the frequency of gray value is utilized to calculate threshold. The proposed algorithm is tested on random shooting degraded images and datasets of Document Image Binarization COntest （DIBCO）. Compared with other four classical algorithms, the binaried images using the proposed algorithm gain the highest F-measure and PSNR （Peak Signal-to-Noise Ratio）.