Radar target echo recognition is a key research direction in military field, and its research methods have become more intelligent in recent years. As a strong ability to adapt to the intelligent algorithm, the characteristics of large-scale parallel processing, strong fault tolerance made it easy to be used in radar target recognition.The research of this paper is based on Kohonen neural network. Proposed a method with high accuracy named S-Kohonen_bayes.First, according to the radar to identify the specific problems encountered by the proposed method using Kohonen neural network to resolve the cluster, and simulation. Then,based on the results improved Kohonen network. This paper introduces two more practical filter. The simulation experiments show that the filter has proved very useful, and the median filter is better.In the fourth part, raised S-Kohonen Bayes methods to improve results. In addition, the added Adboost strong classifier in simulation experiments in this chapter, have better results.Finally, experiments to test S-Kohonen_bayes approach. Experimental results show that the method used in this paper has a high accuracy rate in identifying the radar target echo, and has good generalization performance. |