With　the　aim　to　solve　the　problems　such　as　low　classification　accuracy　and　weak　anti-disturbances　in　brain-　computer　interfaces　(BCIs)　of　imaging　movement,　a　new　method　for　the　recognition　of　electroencephalography　(EEG)　was　proposed　in　this　work,　which　combined　the　discrete　wavelet　transform　(DWT)　and　BP　neural　network　(DWT-BP)　.　A　rational　time　window　was　set　by　calculating　the　average　power　of　C3　electrode　and　C4　electrode　in　imaging　left　or　right　hand　movement.　Then　the　average　power　within　the　time　window　was　taken　into　DWT.　The　combinational　signal　of　approximation　coefficient　A6　on　the　sixth　level　was　selected　as　EEG　feature,　and　BP　neural　network　was　used　as　classifier.　The　obtained　EEG　data　was　analyzed　by　the　BP　network.　The　experimental　results　showed　that　the　proposed　method　could　accurately　extract　substantial　features　of　EEG　and　display　better　anti-disturbances　and　classification　performance.　The　method　is　effective　for　EEG　recognition　of　imaging　movements,　which　provides　a　basis　for　realizing　on-line　BCI　systems　of　imaging　movements.