de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

A Transformation-aware Perceptual Image Metric

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons79305

Kellnhofer,  Petr
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45298

Ritschel,  Tobias
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45095

Myszkowski,  Karol
Computer Graphics, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45449

Seidel,  Hans-Peter
Computer Graphics, MPI for Informatics, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Kellnhofer, P., Ritschel, T., Myszkowski, K., & Seidel, H.-P. (2015). A Transformation-aware Perceptual Image Metric. In B. E. Rogowitz, T. N. Pappas, & H. de Ridder (Eds.), Human Vision and Electronic Imaging XX. Bellingham, WA: SPIE/IS&T. doi:10.1117/12.2076754.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-0024-544A-4
Zusammenfassung
Predicting human visual perception of image differences has several applications such as compression, rendering, editing and retargeting. Current approaches however, ignore the fact that the human visual system compensates for geometric transformations, e.g. we see that an image and a rotated copy are identical. Instead, they will report a large, false-positive difference. At the same time, if the transformations become too strong or too spatially incoherent, comparing two images indeed gets increasingly difficult. Between these two extremes, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency and motion parallax. To this end, we first fit local homographies to a given optical flow field and then convert this field into a field of elementary transformations such as translation, rotation, scaling, and perspective. We conduct a perceptual experiment quantifying the increase of difficulty when compensating for elementary transformations. Transformation entropy is proposed as a novel measure of complexity in a flow field. This representation is then used for applications, such as comparison of non-aligned images, where transformations cause threshold elevation, and detection of salient transformations.