彩色文档图像的倾斜自动校正算法

An Efficient Algorithm for Automatic Skew-Correction of Color Document Image

对彩色扫描文档进行倾斜校正是对其进行OCR等处理所必须首先经历的步骤,为了对彩色倾斜文档图像进行准确、高效校正,提出了一种新的彩色文档图像的倾斜自动校正算法,该算法包括倾斜检测算法和倾斜校正算法。其中,倾斜检测算法解决了准确获得图像的倾斜角的问题;而倾斜校正算法则除了完成图像的旋转变换外,还通过色彩补偿解决了由于整数运算所造成的“锯齿”现象。倾斜检测是通过纹理复杂性分析实现的,而色彩补偿则是基于颜色线性相关的双线性插值算法。实验表明,该算法较好地解决了彩色文档图像的倾斜自动校正问题,它对于具有单一背景的彩色文档图像是准确、高效、实用的。

The automatic skew-correction of scanned color document image is a necessary step undergone before some processing such as OCR（ optical character recognition）. For the purpose of accurate and efficient automatic correction, two algorithms, namely skew-detection and skew-adjustment, are proposed. The skew-detection algorithm, which is based on the analysis of texture complexity of document image with homogeneous background, solves the problem of how the accurate skew angle can be found. Besides the rotation transform, the skew-adjustment algorithm includes a dual linear interpolation algorithm for color compensation based on linear dependence among the colors in the neighborhood to accomplish the skew- correction of a color image and the elimination of the ＂Saw tooth＂ phenomenon resulted from the integer-operation during the coordinates transformation. In the end, the authors illustrate their experimental results, which show that the presented algorithm is exact, efficient, and practical for color documents whose background are not complex.