Edge-texture 2D image quality metrics suitable for evaluation of image interpolation algorithms

A new objective, full-reference metrics of image quality is proposed in this paper. It should match perceptual (subjective) image quality assessment in a better way. The proposed method consists of two quality measures which separately indicate image quality on edges and in texture areas which are calculated in a three-step algorithm. The “soft mask” is initially found for separation in edge and texture areas. Then, two MSEs (mean square error) with corresponding two PSNRs (peak signal-to-noise ratio) for edge and texture are calculated using soft mask as the weighting factor. Finally, the obtained two PSNRs are re-calculated into the two quality indices for edges and texture. Additionally, the separation factor, defined as percentage of edge areas in image, is considered, describing the influence of the image content on perceptual assessment. The proposed 2D metrics is especially suited for evaluations of different interpolation and compression algorithms.