Face　Recognition　has　been　recognized　as　a　major　research　field　in　pattern　recognition　and　computer　vision.　This　technique　is　widely　adopted,　because　of　its　unique　convenience,　economy　and　high　accuracy　compared　to　other　biological　recognition　techniques.　An　interesting　and　important　challenge　is　thus　to　investigate　high-efficient　recognition　algorithm.　The　introduction　of　kernel　methods　in　pattern　recognition　has　been　received　significant　attentions　in　the　recent　several　years,　and　gray　kernel　and　graph　kernel　are　two　popular　approaches.　The　paper　proposes　maximum　spanning　tree　kernel　and　region　histogram　intersection　kernel;　moreover,　experiments　demonstrate　that　higher　face　recognition　accuracy　can　be　achieved　by　multiple　kernels　which　are　the　combination　of　them.　©　(2014)　Trans　Tech　Publications,　Switzerland.