Automatic　digital　video　classification　is　emerging　as　an　important　problem　in　the　fields　of　video　analysis　and　multimedia　database.　Decision　tree　method　is　used　to　do　the　automatic　video　classification　in　the　paper.　At　first,　video　clips　are　segmented　into　shots,　features　of　the　video　clips　are　generated　and　a　video　features　database　is　created　in　the　same　time.　After　that,　decision　tree　method　is　used　to　classify　the　videos　as　different　genres　and　a　set　of　decision　rules　are　produced.　And　then,　the　discovered　decision　rules　are　used　to　predicate　the　genre　of　a　new　video.　The　experimental　results　show　that　the　decision　tree　method　is　promising　for　video　genre　recognition.