基于Radon变换的倾斜彩色图像自动矫正方法

An Efficient Method Based on Radon Transformation for Automatic Skew-Correction of Color Image

在图像处理系统中,通过采集设备获得的图像如彩色扫描文档不可避免地会出现倾斜现象,虽然文档图像处理技术已经取得很多进展,但是,对于倾斜图像的矫正还存在困难。本文根据图像的结构特征,给出了基于Canny边缘检测和Radon变换相结合的算法,根据Radon变换取得的倾斜角度进行图像的倾斜矫正。实验表明,算法对彩色图像进行自动矫正是准确、高效的。

In a digital image processing system, the images from acquisition devices, for example the output images of desktop scanners, inevitably introduce skew, although the study of color document image processing has achieved much progress, the method of skew image corretct is still difficult, ln this paper, according to the structure of images, a method based on Canny edge detection and Radon transformation is proposd. The maximum inclination angle is detected by Radon transformation, so the skew image is automatically corrected. The results of experiment show that the method presented by the paper is accurately and efficiently.