【作者】 陈亦彬； 齐敏；

【Author】 CHEN Yibin;QI Min;School of Electronics and Information,Northwestern Polytechnical University;

【机构】 西北工业大学电子信息学院；

【摘要】 在工业生产中,由于印刷电路板(Printed Circuit Board,PCB)上需要识别的元素具有不确定性,选择了能较好满足这种需求的无监督模板匹配识别技术。结合图像预处理方面的相关算法,研究设计了面向PCB的快速无监督模板匹配算法,对存在旋转角度的PCB图像,利用多次旋转匹配策略取得最优结果,较好地解决工业生产中存在的非标准角度的PCB图像匹配识别。通过图像识别定位系统测试,证明该系统能够满足PCB快速匹配识别的要求。更多还原

【Abstract】 In the industrial production,due to the uncertainty of the elements to be recognized on the PCB,the unsupervised template matching recognition algorithm that can better meet the needs of recognition is selected.Combined with the algorithms of image preprocessing,a PCB-oriented fast unsupervised template matching algorithm is studied and designed.For PCB images with non-standard angles,use multiple rotation matching strategies to obtain the best results,and better solve the problems of matching and recognition.The system experimental results show that it can meet the requirements of PCB fast matching and recognition.更多还原