The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Bookmark and Share
A Text Region Location Method Based on Connected Component
Pages: 325-331
Year: Issue:  2
Journal: Pattern Recognition and Artificial Intelligence

Keyword:  文本定位 Adaboost K-means聚类 文档图像识别;
Abstract: 文本区域定位对复杂背景图像中的字符识别和检索具有重要意义.已有方法取得高的定位准确率和召回率,但效率较低,难以应用于实际的系统中.文中提出一种基于连通分量过滤和K-means聚类的文本区域定位方法.该方法首先对图像进行自适应分割,对字符颜色层提取连通分量.然后提取连通分量的特征,并用Adaboost分类器过滤非字符连通分量.最后,对候选的字符连通分量根据其位置和颜色层进行K-means聚类来定位文本区域.实验结果显示该方法具有与当前方法相当的准确率和召回率,同时具有较低的计算复杂度.
Related Articles
No related articles found