Ionospheric clutter is the primary factor that affecting High Frequency Surface Wave Radar (HFSWR) detection performance. In order to draw up an adaptive detection strategy suitable in various environment, a novel algorithm is proposed in this paper to recognize ionospheric clutter. The algorithm firstly extracts a series of features, after that, it takes advantage of Genetic Algorithm (GA) to select effective features. Finally, Support Vector Machine (SVM) is applied to acquire a global ionospheric clutter recognition result. Experiments constructed on the real data show that the proposed method can achieve a better performance with the average recognition accuracy up to 86%.