General ࡁp constrained approach for colour constancy

In this work we seek to advance the state of art of colour constancy by fusing two approaches which have recently been presented in the literature and which we believe are complementary in nature. First, we review and then extend the Minkowski p-norm approach so that it incorporates, in a mathematically rigorous way, a constraint on illumination. Second, we incorporate the idea of image derivatives into the Constrained Minkowski norm problem formulation (since there is evidence that colour constancy on derivatives seems to work better than on the colours themselves). Rather than laboriously tune our algorithm by choosing the kind of derivatives we use (order and scale) we instead propose a simple combination of first and second derivative information. Across five benchmark data sets and in comparison to competing algorithms our new simple algorithm offers generally good and often best-in-class performance.