Abstract: Focused on the numerical geometric distortions of the unmanned aerial vehicle (UAV) remote sensing image, the paper presents a design of a geometric correction algorithm without the ground control point (GCP). Based on the improved corner point matching algorithm, we develop an algorithm for extracting some corner points from the overlap area, which is near the center area of the images. The results demonstrate that the geometric root mean square error (RMSE) of the processed image can be reduced significantly by applying the proposed algorithm.