| Hi-index | 0.00 |
We aim at using color information to classify the physicalnature of edges in video. To achieve physics-based edgeclassification, we first propose a novel approach to coloredge detection by automatic noise-adaptive thresholdingderived from sensor noise analysis. Then, we present a taxonomyon color edge types. As a result, a parameter-freeedge classifier is obtained labeling color transitions intoone of the following types: (1) shadow-geometry, (2) highlightedges, (3) material edges. The proposed method isempirically verified on images showing complex real worldscenes.