Physics-based edge evaluation for improved color constancy

Edge-based color constancy makes use of image derivatives to estimate the illuminant. However, different edge types exist in real-world images such as shadow, geometry, material and highlight edges. These different edge types may have a distinctive influence on the performance of the illuminant estimation. Therefore, in this paper, an extensive analysis is provided of different edge types on the performance of edge-based color constancy methods. First, an edge-based taxonomy is presented classifying edge types based on their reflectance properties (e.g. material, shadow-geometry and highlights). Then, a performance evaluation of edge-based color constancy is provided using these different edge types. From this performance evaluation, it is derived that certain edge types are more valuable than material edges for the estimation of the illuminant. To this end, the weighted Grey-Edge algorithm is proposed in which certain valuable edge types are more emphasized for the estimation of the illuminant. From the experimental results, it is shown that the proposed weighted Grey-Edge algorithm based on the shadow-shading variant, i.e. assigning higher weights to edges with more energy in the shadow-shading direction, results in the best performance. Moreover, all current state-of-the-art methods, including pixel-based methods and edge-based methods, have been significantly outperformed by the proposed weighted Grey-Edge algorithm, resulting in an improvement of 9% over the current best-performing algorithm