An automatic registering system is presented in the paper, which can be utilized to register two sequences of video images. In a traditional security system, operators must pay their great attention on viewing scenes captured by cameras and displayed on monitors. The task is very hard especially when the number of cameras is large due to the discontinuity of the monitoring views. Another problem of the traditional system is that there will be places where the cameras cannot reach if the number of the camera installed in the system is few. In the paper, we develop methods to solve the above problems by registering the monitoring views together. The cameras used in this study are limited to two, but the concept can be easily modified to registering more than two camera views. The proposed method consists of the learning stage as well as the operation stage. In the first stage, the registering parameters and the transformation matrix are learned and stored in the table. In the latter stage, the registering process is in progress for registering the image sequences of the two cameras using the matrix created before. Experiments are arranged for demonstrating the feasibility of the proposed approach.