红外与激光工程, 2001, 30 (1): 33, 网络出版: 2006-04-28
光电瞄准设备读数图像自动识别系统
Automatic image recognition system of photo-electric aiming equipment
瞄准设备 字符识别 模板匹配 连通域处理 Aiming equipment Character recognition Templet matching Connected area disposal
摘要
该读数图像自动识别系统利用CCD摄取瞄准设备读数图像经采集卡采集,运用软件的方法实现了字符识别与刻线定位,从而完成了瞄准设备方位读数的计算机动态精确自动判读。文中重点介绍了系统的硬件框架组成、软件模块结构、字符识别的连通域处理算法、刻线精确定位的内插细分算法以及系统总读数的合成。系统字符识别的正确率几乎100%,刻线定位精度达1″以上。
Abstract
A new automatic imagerecognition system uses CCD to incept reading image gathered by image gathering card,achieve character recognition and reticle orientation by software way, and accomplishcomputer dynamic precise self-motion decision of azimuth. In this paper, the hardwareconstitution, software module, core process technique including connected area disposalfor character recognition, infielder subdivision arithmetic for azimuth orientation andcompound of overall reading of system are emphatically introduced. The right ratio of thetechnique is nearly 100% and the orientation precision of the reticle under a second.
参考文献
[1] Wei Dongmin, et al. Using WEB grammer to recognize dimensions in engineering drawings. Pattern Recognition[J]. 1993, 26(9):1407~1416.
[2] Kenneth R Castleman著,朱志刚等译. 数字图像处理[M]. 北京:电子工业出版社.
[3] 孔祥玉. 图像自动识别在光电准直经纬仪瞄准读数系统中的应用[D] 西安:第二炮兵工程学院.
郭晓松, 杨必武, 张向东, 左森. 光电瞄准设备读数图像自动识别系统[J]. 红外与激光工程, 2001, 30(1): 33. 郭晓松, 杨必武, 张向东, 左森. Automatic image recognition system of photo-electric aiming equipment[J]. Infrared and Laser Engineering, 2001, 30(1): 33.