Learning image similarity measures from choice data

Matthias Scheller Lichtenauer1,3, Peter Zolliker1, Ingmar Lissner2, Jens Preiss2, Philipp Urban2
1Empa (Switzerland), 2Technische Universität Darmstadt (Germany), 3Friedrich-Schiller-Universität Jena (Germany)
Download paper

Play (17min)

Download: MP4 | MP3

We present a corpus of experimental data from psychometric studies on gamut mapping and demonstrate its use to develop image similarity measures. We investigate whether similarity measures based on luminance (SSIM) can be improved when features based on chroma and hue are added. Image similarity measures can be applied to automatically select a good image from a sample of transformed images.