This　paper　presents　a　novel　facial　expression　recognition　approach　in　the　presence　of　partial　occlusion　using　Gabor　filters　and　gray-level　co-occurrence　matrix　(GLCM).　At　first,　we　design　an　algorithm　to　extract　the　block　Gabor　feature　statistics　according　to　the　spatial　distribution　of　the　face　organ.　Then,　GLCM　is　firstly　introduced　into　expression　recognition　field　to　make　up　for　the　deficiency　of　block　Gabor　feature,　in　which　the　association　between　pixels　is　absent.　Finally,　the　block　Gabor　feature　statistics　is　linear　superimposed　with　the　texture　feature　extracted　by　GLCM,　after　Gaussian　normalization　there　generates　a　set　of　lowdimensional　feature　vectors　for　expression　feature　representation.　The　experimental　results　on　JAFFE　and　RaFD　show　the　high　robustness　and　better　recognition　rates　of　the　proposed　novel　approach　under　different　types　of　occlusion.