Feature extraction is a central processing in the automatic target recognition system, and noise filter is an important step in the feature extraction. A lot of research in noise filter has been proposed and used in image processing. In this paper, a noise filter algorithm based on area feature for vehicle recognition system is presented. Discussing the feature of vehicle for the recognition system, and the problem of the vehicle contour feature obtained from the traffic video. Analyzing the principle of the solve approach of the area-feature-based noise filter for vehicle recognition system. Implementing the program of the algorithm proposed in the following. Experiments have been conducted by many real vehicle images obtained from a real-time video produced by a monitor. The result shows that the new proposed method can remove the noise of the image signal for the vehicle recognition efficiently.