Face　recognition　involves　computer　recognition　of　personal　identity　based　on　geometric　or　statistical　features　derived　from　face　images.　Even　though　humans　can　detect　and　identify　faces　in　a　scene　with　little　or　no　effort,　getting　a　computer　to　accomplish　such　objectives　is　very　challenging.　Researchers　have　been　always　investigating　simple,　accurate,　and　convenient　approach　to　achieve　face　recognition.　In　this　paper,　we　propose　a　novel　multiple　kernels　method,　which　is　based　on　cycle　kernel　and　gray　kernels.　Experimental　results　indicate　that　multiple　kernels　method　gets　good　performance.　©2010　IEEE.