Finding Image Features Associated with High Aesthetic Value by Machine Learning

A major goal of evolutionary art is to get images of high aesthetic value. We assume that some features of images are associated with high aesthetic value and want to find them. We have taken two image databases that have been rated by humans, a photographic database and one of abstract images generated by evolutionary art software. We have computed 55 features for each database. We have extracted two categories of rankings, the lowest and the highest. Using feature extraction methods from machine learning we have identified the features most associated with differences. For the photographic images the key features are wavelet and texture features. For the abstract images the features are colour based features.

[1]  M. Newall.  What is a Picture?: Depiction, Realism, Abstraction , 2010 .

[2]  Ben R. Newell,et al.  Universal aesthetic of fractals , 2003, Comput. Graph..

[3]  W. Chu.  Studying Aesthetics in Photographic Images Using a Computational Approach , 2013 .

[4]  Penousal Machado,et al.  The Art of Artificial Evolution , 2008 .

[5]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[6]  Philip Galanter,et al.  Complexism and the Role of Evolutionary Art , 2008, The Art of Artificial Evolution.

[7]  Ali A. Minai,et al.  Unifying Themes in Complex Systems , 2006 .

[8]  John Tooby,et al.  Does Beauty Build Adapted Minds? Toward an Evolutionary Theory of Aesthetics, Fiction, and the Arts , 2001 .

[9]  Rolf Drechsler,et al.  Applications of Evolutionary Computing, EvoWorkshops 2008: EvoCOMNET, EvoFIN, EvoHOT, EvoIASP, EvoMUSART, EvoNUM, EvoSTOC, and EvoTransLog, Naples, Italy, March 26-28, 2008. Proceedings , 2008, EvoWorkshops.

[10]  Marcus T. Pearce,et al.  The Copenhagen Neuroaesthetics conference: Prospects and pitfalls for an emerging field , 2011, Brain and Cognition.

[11]  Jon McCormack,et al.  Open Problems in Evolutionary Music and Art , 2005, EvoWorkshops.

[12]  Penousal Machado,et al.  The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music , 2007 .

[13]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[14]  Brian J. Ross,et al.  The Evolution of Artistic Filters , 2008, The Art of Artificial Evolution.

[15]  Victor Ciesielski,et al.  Evolving images for entertainment , 2007, IE '07.

[16]  Richard P. Taylor,et al.  The Visual Complexity of Pollock’s Dripped Fractals , 2008 .

[17]  Mengjie Zhang,et al.  Evolution of aesthetically pleasing images without human-in-the-loop , 2010, IEEE Congress on Evolutionary Computation.

[18]  M. Newall.  What is a Picture , 2011 .

[19]  Penousal Machado,et al.  Experiments in Computational Aesthetics , 2008, The Art of Artificial Evolution.

[20]  Antti Oulasvirta,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.