TY  - GEN
N1  - 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.
AV  - public
Y1  - 2015/04/10/
TI  - A transformation-aware perceptual image metric
T3  - SPIE Proceedings
A1  - Kellnhofer, P
A1  - Ritschel, T
A1  - Myszkowski, K
A1  - Seidel, HP
KW  - Image metric
KW  -  Motion
KW  -  Optical flow
KW  -  Homography
KW  -  Saliency
UR  - http://dx.doi.org/10.1117/12.2076754
PB  - Society of Photo-Optical Instrumentation Engineers
SN  - 1605-7422
N2  - 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.
ID  - discovery1524336
ER  -