In this paper, Multi-View Expectation and Maximization (EM) algorithm for finite mixture models is proposed by us to handle real-world learning problems which have natural feature splits. Multi-View EM does feature split as Co-training and Co-EM, but it considers multi-view learning problems in the EM framework. The proposed algorithm has these impressing advantages comparing with other algorithms in Co-training setting: its convergence is theoretically guaranteed; it can easily deal with more two views learning problems. Experiments on WebKB data demonstrated that Multi-View EM performed satisfactorily well compared with Co-EM, Co-training and standard EM.