Face　recognition　is　one　of　the　most　challenging　research　topics　in　the　field　of　pattern　recognition　and　computer　vision.　To　efficiently　deal　with　this　problem,　a　novel　face　recognition　algorithm　is　proposed　by　the　combination　of　local　fisher　discriminant　analysis　(LFDA)　and　least　square　version　of　SVM(LS-SVM).　Experimental　results　on　real　face　databases　have　demonstrated　the　better　performance　of　the　proposed　algorithm.