21 March 2013 Learning probabilistic document template models via interaction
Author Affiliations +
Document aesthetics measures are key to automated document composition. Recently we presented a probabilistic document model (PDM) which is a micro-model for document aesthetics based on a probabilistic modeling of designer choice in document design. The PDM model comes with efficient layout synthesis algorithms once the aesthetic model is defined. A key element of this approach is an aesthetic prior on the parameters of a template encoding aesthetic preferences for template parameters. Parameters of the prior were required to be chosen empirically by designers. In this work we show how probabilistic template models (and hence the PDM cost function) can be learnt directly by observing a designer making design choices in composing sample documents. From such training data our learning approach can learn a quality measure that can mimic some of the design tradeoffs a designer makes in practice.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ildus Ahmadullin, Ildus Ahmadullin, Niranjan Damera-Venkata, Niranjan Damera-Venkata, "Learning probabilistic document template models via interaction", Proc. SPIE 8664, Imaging and Printing in a Web 2.0 World IV, 866408 (21 March 2013); doi: 10.1117/12.2006464; https://doi.org/10.1117/12.2006464

Back to Top