arash abadpour - sharif university of technology tehran
shohreh kasaei

finding the region similar to a given query region has many applications incomputer vision and computer graphics the first step towards an efficient query region extraction is to have a proper likelihood measure this issue has been neglected in the computer vision community and the researchers commonly used the euclidean distance for query region extraction in some standard color spaces in this paper we analyze the performance of the euclidean distancein 12 standard color spaces each one examined in 7 distinct possible representations. also we investigate the mahalanobis distance and the linear partial reconstruction error LPRE.