Focused on the problems that it′s difficult to obtain high precision mosaic image of object having duplicate texture in the automatic visual inspection system, a new two-dimensional (2D) image mosaic method based on sub-pixel grating positioning is presented. The method uses grating to record positions of object and calibration plate to accurately calibrate angles of X and Y axes between platform and camera, and build a 2D stitching model based on global Cartesian coordinate system to complete image stitching. Experimental results show that the method′s calibration repeatability reaches 10-4 rad order of magnitude, with average physical error of 8 μm, and stitching precision increases nearly 8 times than that of not correction, 2 times better than the method that has been reported. The method has been successfully used in the online automatic inspection equipment for ceramic substrate of navigation satellite′s receiving antenna circuit. The research result can be widely applied in machine vision automated inspection fields that require sub-pixel level detection precision.