Colour in Context
Research group
Computer Vision Center

Towards automatic and flexible concept transfer

Naila Murray, Sandra Skaff, Luca Marchesotti, Florent Perronnin
Computers & Graphics - 2012
IF: 0.794. area: COMPUTER SCI., ARTIFICIAL INT.. Quartile: Q3.
Download the publication : p244.pdf [4.2Mo]  
This paper introduces a novel approach to automatic, yet flexible, image concept transfer; examples of concepts are “romantic”, “earthy”, and “luscious”. The presented method modifies the color content of an input image given only a concept specified by a user in natural language, thereby requiring minimal user input. This method is particularly useful for users who are aware of the message they wish to convey in the transferred image while being unsure of the color combination needed to achieve the corresponding transfer. Our framework is flexible for two reasons. First, the user may select one of two modalities to map input image chromaticities to target concept chromaticities, depending on the level of photo-realism required. Second, the user may adjust the intensity level of the concept transfer to his/her liking with a single parameter. The proposed method uses a convex clustering algorithm, with a novel pruning mechanism, to automatically set the complexity of models of chromatic content. Results show that our approach yields transferred images which effectively represent concepts, as confirmed by a user study.

Images and movies

 

BibTex references

@Article\{MSM2012,
  author       = "Naila Murray and Sandra Skaff and Luca Marchesotti and Florent Perronnin",
  title        = "Towards automatic and flexible concept transfer",
  journal      = "Computers \& Graphics",
  year         = "2012",
  note         = "http://dx.doi.org/10.1016/j.cag.2012.01.008",
  key          = "http://dx.doi.org/10.1016/j.cag.2012.01.008",
  abstract     = "This paper introduces a novel approach to automatic, yet flexible, image concept transfer; examples of concepts are \“romantic\”, \“earthy\”, and \“luscious\”. The presented method modifies the color content of an input image given only a concept specified by a user in natural language, thereby requiring minimal user input. This method is particularly useful for users who are aware of the message they wish to convey in the transferred image while being unsure of the color combination needed to achieve the corresponding transfer. Our framework is flexible for two reasons. First, the user may select one of two modalities to map input image chromaticities to target concept chromaticities, depending on the level of photo-realism required. Second, the user may adjust the intensity level of the concept transfer to his/her liking with a single parameter. The proposed method uses a convex clustering algorithm, with a novel pruning mechanism, to automatically set the complexity of models of chromatic content. Results show that our approach yields transferred images which effectively represent concepts, as confirmed by a user study.",
  ifactor      = "0.794",
  quartile     = "Q3",
  area         = "COMPUTER SCI., ARTIFICIAL INT.",
  url          = "http://cat.cvc.uab.es/Public/Publications/2012/MSM2012"
}

Other publications in the database

 © 2008 Colour in context Group | Computer Vision Center. All rights reserved | Contact webmaster |  Last updated: Monday 11 May 2009     eXTReMe Tracker