Color image edge detection by parallel coordinates-based color distance

Although simple and based on physical realizable color primaries, the RGB color space cannot allow the direct definition of a topology-preserving, perceptually-compatible inter-color distance. The classical normalized inter-color distances are rather complex to implement and tune. We propose the use of a planar color representation plot, derived from multivariate data visualization using parallel coordinates, which allows the introduction of a luminance-invariant, geometry-based inter-color distance. We show that the new distance is used with good results in the implementation of distance-based color filters and edge detectors.