Extending Image Quality Models

Image quality is known to be multivalued with some visual attributes or "nesses." One example of a "ness" is colorfulness. Published research has shown that the image quality versus colorfulness function reaches a maximum and increasing colorfulness beyond the optimum level actually degrades image quality. The present formulations of image quality models—e.g. Minkowski metrics and the Generalized Weighted Mean Hypothesis—implicitly assume that a monotonic relationship exists between image quality and the values of the independent "nesses." This paper proposes an extension to these popular image quality model formulations to represent the non-monotonic case. The new image quality model extension is compared to results of image quality versus colorfulness scaling of printed images.