It is more difficult to eliminate noise in color image than in gray image. In this paper

a method of color vector is described. Using this method

the noise in color image

which is made up of many monochromatic targets

can be restrained. Firstly

color vector is defined

and then the average of color vector is also defined. Secondly

a new analytical method of color vector is introduced. By calculating Euclidean distance between pixel

of which is analyzed

and averages of color vector of trained district

it is possible to segment rapidly the different monochromatic targets

which have been polluted. Thirdly

the images of monochromatic targets are smoothed separately. Finally

by combining the images of monochromatic targets that are processed and one of background

it is can eliminate noise in the color image greatly. The results of the method show that it is satisfy. The method is applicable to eliminate noise in image

which is made up of many monochromatic targets and complex background.