| 多个数字仪表字符串区域的定位和识别研究 |
| |
| 引用本文： | 申小阳,姜伯军. 多个数字仪表字符串区域的定位和识别研究[J]. 苏州科技学院学报(自然科学版), 2005, 22(4): 42-45,49 |
| |
| 作者姓名： | 申小阳 姜伯军 |
| |
| 作者单位： | 苏州科技学院,应用物理系,江苏,苏州,215009 |
| |
| 摘 要： | 根据待识别图像中多个仪表的特点,运用边缘检测技术、数学形态学方法、连通域标记法等来定位出多个仪表待识别字符串区域,并运用BP神经网络来识别.经过试验,能准确定位出各个仪表字符串区域,其识别率也达到了95%.
|
| 关 键 词： | 边缘检测 数学形态学 连通域标记 BP神经网络 |
| 文章编号： | 1672-0687（2005）04-0042-04 |
| 收稿时间： | 2005-09-12 |
| 修稿时间： | 2005-09-12 |
A Research on String Region Location and Recognition of Multi-Numeral Instruments |
| |
| SHEN Xiao-yang,JIANG Bo-jun. A Research on String Region Location and Recognition of Multi-Numeral Instruments[J]. Journal of University of Science and Technology of Suzhou, 2005, 22(4): 42-45,49 |
| |
| Authors: | SHEN Xiao-yang JIANG Bo-jun |
| |
| Affiliation: | Dept. of Applied Physics, USTS, Suzhou 215009, China |
| |
| Abstract: | According to the features of multi-instrument regions in the images to be recognized, we have located the multi-string regions with the methods of edge checking, mathematic morphology and connected-through field mark and employed BP NN to recognize them. By experimentation, the result shows that each string region can be accurately located and that the recognition rate has reached 95%. |
| |
| Keywords: | edge checking mathematic morphology connected-through field mark BP NN |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
