相控阵雷达T/R组件字符识别系统的研究与应用  

Research and Application of Phased Array Radar T/R Component Character Recognition System

作　　者：康钲坤 欧阳锋 满志平 KANG Zhengkun;OU YANG Feng;MAN Zhiping(Nanjing Research Institute of Electronics Technology,Nanjing 210039,China)

机构地区：[1]南京电子技术研究所,江苏南京210039

出　　处：《电子质量》2025年第3期11-16,共6页Electronics Quality

摘　　要：随着有源相控阵雷达市场需求井喷式增长,T/R组件需求量持续攀升。其表面字符包含厂商名称、图号、批次号和地址码,其中批次号与地址码对组件控制、监测和维护至关重要。提出了基于MATLAB平台的字符检测方案。通过高精度相机获取目标图像,经灰度化、滤波、二值化预处理后,应用Radon变换校正字符倾斜,结合边界像素检测算法实现定位分割,构建独立匹配模板库,采用相关系数算法完成模板匹配与记录表自动生成。实验表明,该方法识别正确率达99%,显著提升了检测效率。With the explosive growth of the active phased array radar market demand,the demand for T/R compo-nents continues to rise.Its surface characters include manufacturer name,drawing number,batch number,and address code,among which batch number and address code are crucial for component control,monitoring,and maintenance.A character detection scheme based on MATLAB is proposed.After the target image is obtained by a high-precision camera and pre-processed by gray-scale,filter and binarization,the character tilt is corrected by Radon transform,and the location and segmentation are achieved by combining the boundary pixel detection algo-rithm.An independent matching template library is constructed,and the template matching and record table are automatically generated by the correlation coefficient algorithm.The experiment shows that the accuracy of the method is 99%,which significantly improves the detection efficiency.

关 键 词：T/R组件 字符识别 模板匹配 RADON变换 相关系数法 

分 类 号：TN958.92[电子电信—信号与信息处理] TP311[电子电信—信息与通信工程]