The　focus　of　face　recognition　is　a　classifying　problem　based　on　similarity　measurement.　This　paper　presents　a　color　image　correlation　similarity　discriminant　(CICSD)　model　after　defining　within-class　correlation　and　between-class　correlation　for　color　face　recognition.　The　CICSD　model　unifies　the　color　face　image　representation　and　recognition　into　one　framework.　Thus　classifying　performance　while　representing　a　color　face　image　can　be　considered.　Therefore,　the　present　model　involves　in　two　sets　of　variables:　the　color　component　combination　coefficients　for　color　face　image　presentation　and　the　projection　basis　vectors　for　color　face　recognition.　An　iterative　CICSD　algorithm　is　designed　to　find　the　optimal　color　component　combination　coefficients　and　the　optimal　projection　basis　vectors.　Experimental　results　on　the　FERET　and　AR　color　face　database　show　the　effectiveness　of　the　present　model　and　algorithm.