In this work, a novel technique of objective spectral image quality evaluation is presented. The method is based on a Structural Similarity technique. The traditional approach, which deals primarily with gray-scale images, is extended to incorporate spectral data. The novel method has previously been tested against the conventional two-dimensional technique and proven to be more effective. The performance of the threedimensional Structural Similarity Index presented in this paper is tested along with the previously proposed kernel similarity metrics and a subjective technique - Perceptual Image Distortion Map. The tests show that the proposed threedimensional Structural Similarity Index performance is comparable to the rest of the measures in the task of spectral distortion evaluation.
Diana Kalenova, Dobromir Dochev, Vladimir Bochko, Pekka Toivanen, Arto Kaarna, "A Novel Technique of Spectral Image Quality Assessment Based on Structural Similarity Measure" in Proc. IS&T CGIV 2006 3rd European Conf. on Colour in Graphics, Imaging, and Vision, 2006, pp 499 - 502, https://doi.org/10.2352/CGIV.2006.3.1.art00102