A new segmentation algorithm is proposed for touching character images for the automatic recognition of characters on monitor screen.
针对监控画面采样图像中数字的自动识别问题,提出一种新的粘连字符图像分割方法。
参考来源 - 一种新的粘连字符图像分割方法·2,447,543篇论文数据,部分数据来源于NoteExpress
在印刷体数学公式识别中,不能很好地切分粘连字符是造成识别错误的主要原因。
To solve this problem, a technique which is based on sliding window technique is presented for the segmentation of touching characters in mathematical expressions.
该方法对印刷质量较差的粘连字符效果更好,可以作为常用的最短路径法的一个很好的补充算法,以提高分割成功率。
This proposed segmentation method behaves particularly good for poorly printed characters, and it can make a good supplement of the most often used shortest path method.
分析了图书索书号字符串经过二值化后,字符及其笔划发生变形和粘连的主要原因。
This paper analyzed the main cause of the stroke deformation and character touching when performing binarization process of call number image.
应用推荐