In　this　work,　we　proposed　an　emotional　face　evoked　EEG　signal　recognition　framework,　within　this　framework　the　optimal　statistic　features　were　extracted　from　original　signals　according　to　time　and　space,　i.e.,　the　span　and　electrodes.　First,　the　EEG　signals　were　collected　using　noise　suppression　methods,　and　principal　component　analysis　(PCA)　was　used　to　reduce　dimension　and　information　redundant　of　data.　Then　the　optimal　statistic　features　were　selected　and　combined　from　different　electrodes　based　on　the　classification　performance.　We　also　discussed　the　contribution　of　each　time　span　of　EEG　signals　in　the　same　electrodes.　Finally,　experiments　using　Fisher,　Bayes　and　SVM　classifiers　show　that　our　methods　offer　the　better　chance　for　reliable　classification　of　the　EEG　signal.　Moreover,　the　conclusion　is　supported　by　physiological　evidence　as　follows:　a)　the　selected　electrodes　mainly　concentrate　in　temporal　cortex　of　the　right　hemisphere,　which　relates　with　visual　according　to　previous　psychological　research;　b)　the　selected　time　span　shows　that　consciousness　of　the　face　picture　has　a　trend　from　posterior　brain　regions　to　anterior　brain　regions.