Neural Computing and Applications

, Volume 30, Issue 6, pp 1957–1969 | Cite as

Distinguishing paintings from photographs by complexity estimates

  • Adrian Carballal
  • Antonino SantosEmail author
  • Juan Romero
  • Penousal Machado
  • João Correia
  • Luz Castro
Original Article


This study is aimed at exploring the ability of complexity-based metrics to distinguish between paintings and photographs. The proposed features resort to edge detection, compression and entropy estimate methods that are highly correlated with artwork complexity. Artificial neural networks based on these features were trained for this task. The relevance of various combinations of these complexity metrics is also analyzed. The results of the current study indicate that different estimates related to image complexity achieve better results than state-of-the-art feature sets based on color, texture and perceptual edges. The classification success rate achieved is 94.82% on a dataset of 5235 images.


Artificial neural networks Complexity estimates Edge detection Feature extraction Image retrieval 



We are very grateful for the reviewers suggestions. This work was supported by the General Directorate of Culture, Education and University Management of Xunta de Galicia (Ref. GRC2014/049) and the European Fund for Regional Development (FEDER) in the European Union, the Portuguese Foundation for Science and Technology in the scope of project SBIRC (Ref. PTDC/EIA EIA/115667/2009), Xunta de Galicia (Ref. XUGA - PGIDIT - 10TIC105008-PR) and the Spanish Ministry for Science and Technology (Ref. TIN2008-06562/TIN).


  1. 1.
    Aks DJ, Sprott JC (1996) Quantifying aesthetic preference for chaotic patterns. Empir Stud Arts 14(1):1–16CrossRefGoogle Scholar
  2. 2.
    Arnheim R (1954) Art and visual perception: a psychology of the creative eye. Univ of California Press, CaliforniaGoogle Scholar
  3. 3.
    Arnheim R (1966) Towards a psychology of art/entropy and art? An essay on disorder and order. The Regents of the University of California, CaliforniaGoogle Scholar
  4. 4.
    Athitsos V, Swain MJ, Frankel C (1997) Distinguishing photographs and graphics on the world wide web. Content-Based Access of Image and Video Libraries, 1997. Proceedings. IEEE Workshop on, IEEE, pp 10–17Google Scholar
  5. 5.
    Birkhoff GD (1933) Aesthetic measure. Mass, CambridgeCrossRefzbMATHGoogle Scholar
  6. 6.
    Blum A (1992) Neural networks in C++: an object-oriented framework for building connectionist systems. Wiley, New YorkGoogle Scholar
  7. 7.
    Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRefGoogle Scholar
  8. 8.
    Cutzu F, Hammoud R, Leykin A (2003) Estimating the photorealism of images: distinguishing paintings from photographs. In: Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, IEEE, 2: II–305Google Scholar
  9. 9.
    Cutzu F, Hammoud R, Leykin A (2005) Distinguishing paintings from photographs. Comput Vision Image Underst 100(3):249–273CrossRefGoogle Scholar
  10. 10.
    Datta R, Joshi D, Li J, Wang JZ (2006) Studying aesthetics in photographic images using a computational approach. In: Leonardis A, Bischof H, Pinz A (eds) Computer Vision – ECCV 2006. Lecture notes in computer science, vol 3953. Springer, Berlin, Heidelberg, pp 288–301CrossRefGoogle Scholar
  11. 11.
    Eysenck HJ (1941) The empirical determination of an aesthetic formula. Psychol Rev 48(1):83CrossRefGoogle Scholar
  12. 12.
    Eysenck HJ (1942) The experimental study of the’good gestalt’? A new approach. Psychol Rev 49(4):344CrossRefGoogle Scholar
  13. 13.
    Fisher Y (1994) Fractal image compression. Fractals 2(03):347–361CrossRefzbMATHGoogle Scholar
  14. 14.
    Forsythe A, Nadal M, Sheehy N, Cela-Conde CJ, Sawey M (2011) Predicting beauty: fractal dimension and visual complexity in art. Br J Psychol 102(1):49–70CrossRefGoogle Scholar
  15. 15.
    Greenfield G, Machado P (2009) Simulating artist and critic dynamics—an agent-based application of an evolutionary art system. In: Dourado A, Rosa AC, Madani K (eds) IJCCI 2009—Proceedings of the international joint conference on computational intelligence. INSTICC Press, Funchal, Madeira, pp 190–197Google Scholar
  16. 16.
    Huttenlocher DP, Klanderman GA, Rucklidge WJ (1993) Comparing images using the hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850–863CrossRefGoogle Scholar
  17. 17.
    Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. IJCAI Morgan Kaufmann, Burlington, pp 1137–1145Google Scholar
  18. 18.
    Machado P, Cardoso A (1998) Computing aesthetics. In: de Oliveira FM (ed) Advances in artificial intelligence. SBIA 1998. Lecture notes in computer science, vol 1515. Springer, Berlin, Heidelberg, pp 219–228Google Scholar
  19. 19.
    Machado P, Cardoso A (2002) All the truth about nevar. Appl Intell 16(2):101–118CrossRefzbMATHGoogle Scholar
  20. 20.
    Machado P, Romero J, Santos ML, Cardoso A, Manaris B (2004) Adaptive critics for evolutionary artists. In: Raidl GR et al (eds) Applications of evolutionary computing. EvoWorkshops 2004. Lecture notes in computer science, vol 3005. Springer, Berlin, Heidelberg, pp 437–446Google Scholar
  21. 21.
    Machado P, Romero J, Manaris B (2008) Experiments in computational aesthetics. In: The art of artificial evolution, Springer, pp 381–415Google Scholar
  22. 22.
    Machado P, Romero J, Nadal M, Santos A, Correia J, Carballal A (2015) Computerized measures of visual complexity. Acta Psychol 160:43–57. doi: 10.1016/j.actpsy.2015.06.005,
  23. 23.
    Manaris B, Purewal T, McCormick C (2002) Progress towards recognizing and classifying beautiful music with computers-midi-encoded music and the Zipf-Mandelbrot law. SoutheastCon, 2002. Proceedings IEEE, IEEE, pp 52–57Google Scholar
  24. 24.
    Manaris B, Romero J, Machado P, Krehbiel D, Hirzel T, Pharr W, Davis RB (2005) Zipf’s law, music classification, and aesthetics. Comput Music J 29(1):55–69CrossRefGoogle Scholar
  25. 25.
    Manaris B, Roos P, Machado P, Krehbiel D, Pellicoro L, Romero J (2007) A corpus-based hybrid approach to music analysis and composition. In: Proceedings of the 22nd National Conference on Artificial Intelligence, Vol 1, AAAI Press, AAAI’07, pp 839–845Google Scholar
  26. 26.
    Meier NC (1942) Art in human affairs; an introduction to the psychology of art. McGraw-Hill, New YorkGoogle Scholar
  27. 27.
    Moles AA (1957) Théorie de l’information et perception esthétique. Rev Philos de la France et de l’Étranger 147:233–242Google Scholar
  28. 28.
    Nadal Roberts M (2007) Complexity and aesthetic preference for diverse visual stimuli. Ph.D. thesis, Universitat de les Illes BalearsGoogle Scholar
  29. 29.
    Powers DM (1998) Applications and explanations of Zipf’s law. In: Proceedings of the Joint Conferences on New Methods in Language Processing and Computational Natural Language Learning, Association for Computational Linguistics, pp 151–160Google Scholar
  30. 30.
    Rigau J, Feixas M, Sbert M (2005) An information-theoretic framework for image complexity. In: Proceedings of the First Eurographics conference on Computational Aesthetics in Graphics. Visualization and Imaging, Eurographics Association, pp 177–184Google Scholar
  31. 31.
    Romero J, Machado P, Carballal A, Osorio O (2011) Aesthetic classification and sorting based on image compression. In: Di Chio C et al (eds) Applications of evolutionary computation. EvoApplications 2011. Lecture notes in computer science, vol 6625. Springer, Berlin, Heidelberg, pp 394–403CrossRefGoogle Scholar
  32. 32.
    Romero J, Machado P, Carballal A, Correia J (2012a) Computing aesthetics with image judgement systems, Springer, Berlin, pp 295–322. doi: 10.1007/978-3-642-31727-9_11.
  33. 33.
    Romero J, Machado P, Carballal A, Santos A (2012b) Using complexity estimates in aesthetic image classification. J Math Arts 6(2–3):125–136MathSciNetCrossRefGoogle Scholar
  34. 34.
    Rumelhart DE, Hinton GE, Williams RJ (1988) Neurocomputing: foundations of research. MIT Press, Cambridge. chap Learning representations by back-propagating errors, pp 696–699Google Scholar
  35. 35.
    Salingaros NA, West BJ (1999) A universal rule for the distribution of sizes. Environ Plan B 26:909–924CrossRefGoogle Scholar
  36. 36.
    Saunders R, Gero JS (2001) Artificial creativity: a synthetic approach to the study of creative behaviour. Computational and cognitive models of creative design V, Key Centre of Design Computing and Cognition. University of Sydney, Sydney, pp 113–139Google Scholar
  37. 37.
    Schiffmann W, Joost M, Werner R (1994) Optimization of the backpropagation algorithm for training multilayer perceptrons. Technical report, University of Koblenz, Institute of Physics, RheinauGoogle Scholar
  38. 38.
    Sobel I (1990) An isotropic 3 \(\times\) 3 image gradient operator. Mach Vision Three Dimens Sci 3:376–379Google Scholar
  39. 39.
    Spehar B, Clifford CW, Newell BR, Taylor RP (2003) Universal aesthetic of fractals. Comput Gr 27(5):813–820CrossRefGoogle Scholar
  40. 40.
    Svangård N, Nordin P (2004) Automated aesthetic selection of evolutionary art by distance based classification of genomes and phenomes using the universal similarity metric. In: Raidl GR et al (eds) Applications of evolutionary computing. Lecture notes in computer science, vol 3005. Springer, Berlin, Heidelberg, pp 447–456CrossRefGoogle Scholar
  41. 41.
    Taylor RP, Micolich AP, Jonas D (1999) Fractal analysis of pollock’s drip paintings. Nature 399(6735):422–422CrossRefGoogle Scholar
  42. 42.
    Voss RF, Clarke J (1978) “1/f noise” in music: music from 1/f noise. J Acoust Soc Am 63:258CrossRefGoogle Scholar
  43. 43.
    Zipf GK (1949) Human behavior and the principle of least effort. Addison-Wesley press, BostonGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Adrian Carballal
    • 1
  • Antonino Santos
    • 1
    Email author
  • Juan Romero
    • 1
  • Penousal Machado
    • 2
  • João Correia
    • 2
  • Luz Castro
    • 1
  1. 1.Artificial Neural Networks and Adaptive Systems LABUniversity of A CoruñaA CoruñaSpain
  2. 2.CISUC, Department of Informatics EngineeringUniversity of CoimbraCoimbraPortugal

Personalised recommendations