Biometrics is a means of unique identification of an individual. In retina recognition, the unique structure of the blood vessels in the retina has been used for biometric identification. Color is the perceptual sensation of light in the visible range incident on the retina. When the photons (particle behavior of light) hit the retina, they give rise to electric impulses, which on reaching the brain, are translated into color. A color model is a means of specifying colors in some standard way, a three dimensional coordinate system. In this paper, for retina recognition, the image is first converted to different color space before applying the transform and comparison is made for different color models based on mean square error and Peak signal to noise ratio.