With　the　aim　to　solve　the　problems　such　as　weak　anti-disturbances　and　low　recognition　rate　in　signal　processing　and　feature　extraction　of　visual　evoked　potential　(VEP),　a　method　based　on　the　B-spline　wavelet　transform　and　BP　neural　network　was　proposed　to　extract　and　recognize　the　features　of　VEP.　VEP　was　preprocessed　by　a　few　times　of　average　to　enhance　the　signal-noise　ratio;　Then　based　on　the　B-spline　wavelet　transform,　features　were　extracted　and　classified　with　BP　neural　network　classifier.　Compared　with　existing　methods,　the　experimental　results　showed　that　the　proposed　method　could　accurately　extract　the　features　of　VEP,　and　display　better　performance　on　anti-disturbances　and　classification.　The　experiment　results　demonstrated　that　the　method　based　on　B-spline　wavelet　transform　combined　with　BP　neural　network　had　an　average　recognition　rate　of　90.4%,　displaying　the　feasibility　and　the　effectiveness　of　the　proposed　method.