作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (01): 204-206. doi: 10.3969/j.issn.1000-3428.2011.01.070

• 图形图像处理 • 上一篇    下一篇

改进的文档图像扭曲校正方法

宋丽丽a,吴亚东a,孙 波b   

  1. (西南科技大学 a. 智能电器与智能系统四川省高校重点实验室;b. 信息工程学院,四川 绵阳 621010)
  • 出版日期:2011-01-05 发布日期:2010-12-31
  • 作者简介:宋丽丽(1981-),女,讲师、硕士研究生,主研方向:机器视觉,图像处理;吴亚东,副教授、博士;孙 波,硕士研究生
  • 基金资助:
    document image distortion correction; image content segmentation; correction baseline

Improved Document Image Distortion Correction Method

SONG Li-li a, WU Ya-dong a, SUN Bo b   

  1. (a. Sichuan Provincial University Key Laboratory on Intelligent Appliance and System; b. School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China)
  • Online:2011-01-05 Published:2010-12-31

摘要: 由照相机拍摄的文档图像可能因扭曲变形导致OCR软件不能正确识别。为解决上述问题,采用图像分割技术进行单词及文本线检测,利用线性拟合得到单词的较低基线和较高基线,根据校正基线对单词进行旋转和垂直位移,得到校正后的图像。实验结果表明,该方法能快速有效地校正扭曲的文档图像,使校正后的图像在光学字符识别阶段的识别率有较大提高。

关键词: 文档图像扭曲校正, 图像内容分割, 校正基线

Abstract: Non-linear warping often appears in document images which is captured by the camera. In order to solve the problem, this paper uses image segmentation technology to detect words and text lines, applies linear fit to get lower baseline and upper baseline of the words, and makes the words rotation and vertical displace according to upper baseline and lower baseline, so that the corrected image can be obtained. Experimental results indicate that the method can rectify distorted images quickly and effectively, and elevate the probability of the rectified image identification in the optics character identification stage.

Key words: document image distortion correction, image content segmentation, correction baseline

中图分类号: