A　novel　method　to　pose　variant　face　recognition　that　combines　two　recent　advances　of　component-based　face　recognition　and　3D　morphable　model　is　presented.　3D　components　are　extracted　as　the　feature　of　face　recognition.　Because　of　the　shape　information,　it　reduces　the　effect　of　pose　to　face　recognition.　For　classification,　we　combine　the　local　feature　and　global　feature　of　face　and　the　whole　face　are　used　as　input　to　the　final　classifier,　where　each　component　is　verified　by　its　weight　based　on　its　recognition　rate　in　final　classifier.　Experimental　results　show　that　the　method　is　robust　to　pose　invariant　face　recognition　with　only　one　image　of　each　person　in　the　gallery.