A　novel　facial　expression　recognition　method　based　on　Gabor　features　and　fuzzy　classifier　is　proposed.　Gabor　wavelet　is　employed　for　feature　extraction　because　it　has　good　characteristics,　which　make　it　very　suitable　for　the　area　of　facial　expression　recognition.　Because　high-dimensional　Gabor　features　are　quite　redundant,　DCT　and　2DPCA　are　respectively　used　to　reduce　dimensions　and　select　valid　features.　Finally,　expressions　are　recognized　with　fuzzy　k-nearest　neighbor　classifier,　which　is　demonstrated　to　be　a　more　effective　classifier.　The　experimental　results　show　that　the　proposed　method　has　high　computational　speed　and　good　recognition　rate.　©　(2012)　Trans　Tech　Publications,　Switzerland.