Motor imagery electroencephalogram(EEG）is produced by imaging limb movements without actual action. Signal processing and pattern classification are the key technologies of motor imagery EEG and the BCI system. The recognition algorithm based on motor imagery EEG is overviewed in this paper. Various methods for feature extraction and classification of motor imagery EEG are presented with their advantages and disadvantages. Combinations of typical algorithms for feature extraction and recognition are listed and analyzed. The present situation and prospect of feature extraction and classification of motor imagery EEG are summarized.