Various edge detection techniques for color images that have been proposed in the last tworndecades showed that color images contain 10% additional edge information as compared to theirrngray scale counterparts. For color image edge detection, the traditional methods used for grayscalernimagesrnarernusuallyrnextendedrnandrnappliedrntornthernthree-colorrnchannelsrnseparately.rnThisrnleadsrnrntornrnlose the intrinsic inter-correlation information embedded in color image components inrnaddition to computational complexity incurred. Efficient and accurate edge detection leads tornincreased performance of subsequent image processing and analysis techniques including imagernsegmentation and quantification. rnIn this thesis, an edge detection algorithm has been proposed that treats color value triplets asrnvectors based on higher dimensional algebra. A human perception-based color space has beenrnused due to its importance in color image edge detection. The trinion based algorithm hasrnprovided an efficient method to represent the color information vectorally. Color edge featuresrnare extracted based on a second order statistical technique using the weibull distribution method.rnA suitable color space transformation and a way of extracting robust higher order features arernincluded in the method. Performance of the proposed scheme is compared against classical andrnother vectorial approaches which have been proposed in the literature based on objective criteria.rnResults showed that the proposed approach wins the other techniques available in the literature.rnApplication of the proposed method has been shown in edge detection applied on color imagesrntaken from patients treated for diabetic retinopathy acquired from publicly available databasesrnand St. Paulâ€™s Hospital Millennium Medical College. The algorithm performs well in detectingrnexudates, hemorrhages, optical disc and blood vessels.