Pattern Recognition Letters
Digital Image Processing
Hi-index | 0.00 |
Physical interpretation of polarization-encoded images is not obvious since the information content is intricately combined in the channels of this imaging modality. Thus, the need for a proper tool that allows the analysis and understanding of polarization-encoded images is of prime interest. In this paper, a novel mapping is proposed between the Poincaré space and a parametric color space where an adequate distance is defined and used in the fuzzy C-means clustering algorithm for classification issues. Moreover, the obtained label map is used as a priori information to provide an ad hoc colour display, which allows a proper interpretation of the resulting colored image at a glance.