Detection of highlights is a prominent issue in computer vision, graphics and image processing. Applications that require object properties’ measurement or rendering are affected by specular reflection since the models assume matte diffusing surfaces most of the time. Hence, detection, and sometimes removal, of specular reflection (highlights) in an image may be critical. Proposed work takes the help of global color information of an image to effectively recover specular and diffuse reflection. We take help of a dichromatic reflection model to get insights into specular and diffuse reflection. To detect illumination chromaticity (specular reflection regions) we have effectively used a k-means algorithm. Pixels in an image are spread over the entire image and their distances to the illumination chromaticity give the number of specular reflection components. With such non-local overall information from these color lines, our method can effectively separate specular and diffuse reflection components using the repaint() method. We have taken the help of the Imglib2 library.