Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  A Transformation-aware Perceptual Image Metric

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.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-544A-4 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-002E-262D-4
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Kellnhofer, Petr1, Autor           
Ritschel, Tobias1, Autor           
Myszkowski, Karol1, Autor           
Seidel, Hans-Peter1, Autor           
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 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.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 201420152015
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: Kellnhofer2015
DOI: 10.1117/12.2076754
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Human Vision and Electronic Imaging XX
Veranstaltungsort: San Francisco, CA, USA
Start-/Enddatum: 2015-02-08 - 2015-02-12

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Human Vision and Electronic Imaging XX
  Untertitel : Proceedings ; 9–12 February 2015 San Francisco, California, United States
  Kurztitel : HVEI 2015
Genre der Quelle: Konferenzband
 Urheber:
Rogowitz, Bernice E.1, Herausgeber
Pappas, Thrasyvoulos N.1, Herausgeber
de Ridder, Huib1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Bellingham, WA : SPIE/IS&T
Seiten: - Band / Heft: - Artikelnummer: 939408 Start- / Endseite: - Identifikator: ISBN: 9781628414844

Quelle 2

einblenden:
ausblenden:
Titel: Proceedings of SPIE
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 9394 Artikelnummer: - Start- / Endseite: - Identifikator: -