Image mosaic is an important research content in digital image processing, and could be used to solve the problem of observing large objects with narrow view, such as 360 degree panorama stitching. Microscopic observation of liver biopsy is a commonly used method in diagnosing liver diseases, which are always rely on the whole liver slice. Therefore, the liver pathological microscopic image mosaic is the best way to formulate it. This paper proposes a liver image mosaicing system based on scale invariant feature transform and point set matching method, which includes the feature point selection and location process to find the extremum point, screen them, and precisely position them. This system takes the affine transformation as the motion model, and adopts a new matching algorithm for the rigid transformation to accelerate solving the motion parameter. The design and implementation of the liver image mosaicing system have completed more than 100 cases successfully, which shows the effectiveness and robustness of our algorithms.