Supervised　locally　linear　embedding　method　and　linear　discriminant　analysis　method　are　proposed　in　this　paper　for　face　recognition.　As　face　images　are　regarded　as　a　nonlinear　manifold　in　high-dimensional　space,　supervised　locally　linear　embedding　method　is　utilized　to　nonlinearly　map　high-dimensional　face　images　to　low-dimensional　feature　space.　To　recover　space　structure　of　face　images,　morphable　model　is　utilized　to　derive　multiple　images　of　a　person　from　a　single　image.　Experimental　results　on　ORL　and　UMIST　face　database　show　that　our　method　makes　impressive　performance　improvement　compared　with　conventional　Fisherface　methods.