DIRECTIONAL PROCESSING OF COLOR IMAGES - THEORY AND EXPERIMENTAL RESULTS

The processing of color image data using directional information is st udied in this paper. The class of vector directional filters (VDF), wh ich was introduced by the authors in a previous work, is further consi dered, The analogy of VDF to the spherical median is shown, and their relation to the spatial median is examined, Moreover, their statistica l and deterministic properties are studied, which demonstrate their ap propriateness in image processing, VDF result in optimal estimates of the image vectors in the directional sense; this is very important in the case of color images, where the vectors' direction signifies the c hromaticity of a given color. Issues regarding the practical implement ation of VDF are also considered, In addition, efficient filtering sch emes based on VDF are proposed, which include adaptive and/or double-w indow structures. Experimental and comparative results in image filter ing show very good performance measures when the error is measured in the La*b* space, L*a*b* is known as a space where equal color differe nces result in equal distances, and therefore, it is very close to the human perception of colors, Moreover, an indication of the chromatici ty error is obtained by measuring the error on the Maxwell triangle; t he results demonstrate that VDF are very accurate chromaticity estimat ors.