计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (10): 180-183.DOI: 10.3778/j.issn.1002-8331.2010.10.057

• 图形、图像、模式识别 • 上一篇    下一篇

利用OCR识别技术实现视频中文字的提取

陈 义,李言俊,孙小炜   

  1. 西北工业大学 航天学院,西安 710072
  • 收稿日期:2008-09-24 修回日期:2009-04-09 出版日期:2010-04-01 发布日期:2010-04-01
  • 通讯作者: 陈 义

Text recognition in video using OCR

CHEN Yi,LI Yan-jun,SUN Xiao-wei   

  1. College of Astronautics,Northwestern Polytechnical University,Xi’an 710072,China
  • Received:2008-09-24 Revised:2009-04-09 Online:2010-04-01 Published:2010-04-01
  • Contact: CHEN Yi

摘要: 为了在视频图像中进行字幕信息的实时提取,提出了一套简捷而有效的方法。首先进行文字事件检测,然后进行边缘检测、阈值计算和边缘尺寸限制,最后依据文字像素密度范围进一步滤去非文字区域的视频字幕,提出的叠加水平和垂直方向边缘的方法,加强了检测到的文字的边缘;对边缘进行尺寸限制过滤掉了不符合文字尺寸的边缘。应用投影法最终确定视频字幕所在区域。最后,利用OCR识别技术对提取出来的文字区域进行识别,完成视频中文字的提取。以上方法的结合保证了提出算法的正确率和鲁棒性。

关键词: 光学文字识别, 文字事件检测, 数字视频

Abstract: A simple and effective method is presented for real-time text segmentation and recognition in videos.Firstly,an algorithm is provided which detects text event and gets edges,then makes a size restrict to the edges and eventually wipes off non-text regions according to the textual energy.The overlaying of detected horizontal edges and vertical edges enhances the text edges,the size restrict of edges helps to wipe off the non-text edges.Later,image projection is applied to get text regions.Eventually,the text regions are processed by OCR technology.The combination of these methods guarantees the performance of this algorithm.

Key words: Optical Character Recognition(OCR), detection of text event, digital video

中图分类号: