| 基于连通区域的标志牌文本提取方法 |
| |
| 引用本文： | 乔甜,付庆,尹茂东,方漪,赵志刚. 基于连通区域的标志牌文本提取方法[J]. 青岛大学学报(自然科学版), 2006, 19(4): 41-44 |
| |
| 作者姓名： | 乔甜 付庆 尹茂东 方漪 赵志刚 |
| |
| 作者单位： | 青岛大学信息工程学院,青岛,266071;青岛大学信息工程学院,青岛,266071;青岛大学信息工程学院,青岛,266071;青岛大学信息工程学院,青岛,266071;青岛大学信息工程学院,青岛,266071 |
| |
| 摘 要： | 在对各种文本定位与提取方法分析比较的基础上,针对标志牌文本的具体特点,提出了一种基于连通区域的标志牌文本提取方法———在灰度图像中定位标志牌区域,二值图像中提取标志牌文本,并用VC 编程实现对采集的自然场景下的标志牌文本图像进行了实验,结果证明,该方法能够准确定位并提取自然场景下的标志牌文本,获得文本字符。
|
| 关 键 词： | 标志牌文本 标志牌定位 标志牌文本提取 基于连通区域的方法 |
| 文章编号： | 1006-1037（2006）04-0041-04 |
| 收稿时间： | 2006-09-06 |
| 修稿时间： | 2006-09-06 |
Connecting Area-based Approach to Sign Text Extraction |
| |
| QIAO Tian,FU Qing,YIN Mao-dong,FANG Yi,ZHAO Zhi-gang. Connecting Area-based Approach to Sign Text Extraction[J]. Journal of Qingdao University(Natural Science Edition), 2006, 19(4): 41-44 |
| |
| Authors: | QIAO Tian FU Qing YIN Mao-dong FANG Yi ZHAO Zhi-gang |
| |
| Affiliation: | College of Information Engineering, Qingdao University, Qingdao 266071, China |
| |
| Abstract: | Based on the analysis and comparison of various methods locating and extracting sign text,we present an effective connecting area-based method to extract sign texts according to its special characteristics,which is locating sign areas in gray images and extracting sign texts in binary images. Then,we programmed in Visual C and did experiments on sign text images captured in nature scene.Experimental results illustrate that the proposed method can accurately locate the sign area and extract the texts in natural scene images, and then get text characters. |
| |
| Keywords: | sign text image sign locating sign text extraction connecting area-based approach |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
