eprintid: 1524336 rev_number: 24 eprint_status: archive userid: 608 dir: disk0/01/52/43/36 datestamp: 2016-11-02 14:59:18 lastmod: 2021-12-21 23:16:00 status_changed: 2016-11-02 14:59:18 type: proceedings_section metadata_visibility: show creators_name: Kellnhofer, P creators_name: Ritschel, T creators_name: Myszkowski, K creators_name: Seidel, HP title: A transformation-aware perceptual image metric ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Image metric, Motion, Optical flow, Homography, Saliency note: Copyright © 2015 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic electronic or print reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. abstract: Predicting human visual perception 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 extrema, we propose a system to quantify the effect of transformations, not only on the perception of image differences, but also on saliency. 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. date: 2015-04-10 date_type: published publisher: Society of Photo-Optical Instrumentation Engineers official_url: http://dx.doi.org/10.1117/12.2076754 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1189410 doi: 10.1117/12.2076754 isbn_13: 9781628414844 lyricists_name: Ritschel, Tobias lyricists_id: TRITS30 actors_name: Ritschel, Tobias actors_name: Flynn, Bernadette actors_id: TRITS30 actors_id: BFFLY94 actors_role: owner actors_role: impersonator full_text_status: public series: SPIE Proceedings publication: http://dx.doi.org/10.1117/12.2076754 volume: 9394 pagerange: 939408 event_title: Human Vision and Electronic Imaging XX, 9-12 February 2015, San Francisco, CA, USA event_location: San Francisco, CA event_dates: 09 February 2015 - 12 February 2015 institution: Human Vision and Electronic Imaging XX issn: 1605-7422 book_title: Human Vision and Electronic Imaging XX editors_name: Rogowitz, BE editors_name: Pappas, TN editors_name: de Ridder, H citation: Kellnhofer, P; Ritschel, T; Myszkowski, K; Seidel, HP; (2015) A transformation-aware perceptual image metric. In: Rogowitz, BE and Pappas, TN and de Ridder, H, (eds.) Human Vision and Electronic Imaging XX. (pp. p. 939408). Society of Photo-Optical Instrumentation Engineers Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1524336/1/Kellnhofer%20A%20transformation-aware%20perceptual%20image%20metric%20CONF%20PROC%20VoR.pdf