The aim of this study is to realize radar emitter Identification with high-efficiency. In this article, an approach based on naive Bayesian algorithm is introduced. For recognizing radar radiations, this paper utilizes Naive Bayes classifier for radar signal sorting, and selects the pulse parameters (direction of arrival, pulse width, pulse repetition frequency and radar frequency) as features for training the classifier. The paper also compares the method based on naive Bayesian algorithm with the methods based on artificial neural network, K-means algorithm and support vector machine. The performance evaluation shows that naive Bayes classifier can achieve a high recognition accuracy, and the approach presented in this article is proved to be more efficient.