枪械射击准确度是枪械验收的一项重要指标。为提高验收精度、降低验收成本,针对现有验收方法的不足,提出了光电成像并结合图像处理的验收方法。根据成像的图像特点和验收的实际要求,采用模板匹配算法识别代表瞄准线的十字分划,拟合枪管轴线并用十字分划表示,通过检验两十字之间的角度关系来进行射击准确度的验收。研究结果表明,采用模板匹配算法,十字分划的识别精度小于1个像素,射击准确度验收系统的精度约为0.26 mil。 Gun shooting accuracy is an important indicator of gun acceptance. In order to improve the accuracy of acceptance and reduce the acceptance cost, aiming at the shortcomings of the existing acceptance methods, the acceptance method of electro-optical imaging combined with image processing is proposed. According to the image characteristics of the image and the acceptance of the actual requirements, the use of template matching algorithm to identify the line of sight of the cross-line division, fitting the barrel axis and the cross-divided representation, by examining the angle between the two characters to shoot accuracy acceptance. The results show that the recognition accuracy of the cross-division is less than 1 pixel by using the template matching algorithm, and the accuracy of the shooting accuracy acceptance system is about 0.26 mil.