维吾尔文扫描页的倾斜校正

Skew detection and correction of Uighur character scanned page

为了方便维文图像的切分和识别工作,提出将基于凸多边形的最小面积外接矩形法和基线拟合法相结合的检测和校正图像方法。首先提取边缘像素生成凸多边形,利用基于凸多边形的最小面积外接矩形法实现初步的倾斜校正,再根据维文沿基线书写的特点,将图像细化后采用基线拟合的方法完成维文文本的精确校正。实验结果表明,该方法能够精确地检测出文本图像的倾斜角并校正,是行之有效的方法。

In order to facilitate the segmentation and recognition of Uighur character scanning, this paper proposed one ap- proach that combining minimum-area bounding rectangle method based on the convex polygon with baseline fitting method to detect and correct text. Firstly, it extracted the edge pixels to generate a convex polygon, and used the minimum-area boun- ding rectangle method based on the convex polygon to realize the initial correction. Then according to the characteristics of Ui- ghur character written along the baseline, thinned the image and used baseline fitting method to finish the exact detection and correction of Uighur text. The experimental results show that this method can detect text skew and correct it accurately and ef- fectively.