在基于机器视觉的多排种体动态检测技术研究中，鉴于播种后种子动态图像的匹配与拼接精度是个需要解决的难题，为此从系统实时性要求出发，在运用模式识别技术进行检测的实践基础上，阐述了检测系统的构建原理，分析了影响图像拼接精度的因素，进而提出了基于标记的图像匹配与拼接方法、重叠区域设置技术等，从而为试验台自动检测奠定了基础。该理论分析经过大量试验验证表明，该方法应用于检测试验台中，检测误差小于等于± 2 mm,可满足系统实时检测技术要求

While research on the new multi-seeder dynamical testing technology based on image techniques, one of the most important problems is the matching and joining of the serial dynamical images of seed kernels. In this paper, a useful method is introduced to solve this problem. Based on the theory of patter recognition, this method successfully meets the requirement of real-time test. The theory of the building of a testing system is explained, factors that influence the precision of image joining is analyzed and methods used to join the serial images is proposed. A universal test-bed system is expounded that can be used to test the performance of precision seeders, grain drills and seeding monomer. This test bed, which is automatically controlled, can measure the seed kernels interval correctly and reliably. Experiments show that theory and method are practical, speedy and reliable. The requirement of real-time test is satisfied. The test error of the system is within 2mm.