Abstract
A deep convolutional neural network (CNN) trained on millions of images forms a very high-level abstract overview of an image. Our primary goal is to use this high-level content information a given target image to guide the automatic evolution of images using genetic programming. We investigate the use of a pre-trained deep CNN model as a fitness guide for evolution. Two different approaches are considered. Firstly, we developed a heuristic technique called Mean Minimum Matrix Strategy (MMMS) for determining the most suitable high-level CNN nodes to be used for fitness evaluation. This pre-evolution strategy determines the common high-level CNN nodes that show high activation values for a family of images that share an image feature of interest. Using MMMS, experiments show that GP can evolve procedural texture images that likewise have the same high-level feature. Secondly, we use the highest-level fully connected classifier layers of the deep CNN. Here, the user supplies a high-level classification label such as “peacock” or “banana”, and GP tries to evolve an image that maximizes the classification score for that target label. Experiments evolved images that often achieved high confidence scores for the supplied labels. However, the images themselves usually display some key aspect of the target required for CNN classification, rather than the entire subject matter expected by humans. We conclude that deep learning concepts show much potential as a tool for evolutionary art, and future results will improve as deep CNN models are better understood.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dawkins, R.: The Blind Watchmaker. Norton & Company, Inc. (1986)
Sims, K.: Artificial evolution for computer graphics. In: Proceedings of the 18th Annual Conference on Computer Graphics and Interactive Techniques, vol. 25, no. 4, pp. 319–328, July 1991
Rooke, S.: Eons of genetically evolved algorithmic images. In: Bentley, P., Corne, D. (eds.) Creative Evolutionary Systems, pp. 339–365. Morgan Kaufmann, San Francisco (2002)
Todd, S., Latham, W.: Evolutionary Art and Computers. Academic Press, London (1992)
Bentley, P.: Creative Evolutionary Systems. Morgan Kaufmann, San Francisco (2002)
Romero, J., Machado, P.: The Art of Artificial Evolution. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-72877-1
Graf, J., Banzhaf, W.: Interactive evolution of images. In: Proceedings 4th Evolutionary Programming, pp. 53–65. MIT Press (1995)
den Heijer, E., Eiben, A.E.: Comparing aesthetic measures for evolutionary art. In: Di Chio, C., et al. (eds.) EvoApplications 2010. LNCS, vol. 6025, pp. 311–320. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12242-2_32
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647–655 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Proceedings 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097–1105. Curran Associates Inc. (2012)
Gatys, L., Ecker, A., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings Computer Vision and Pattern Recognition, pp. 2414–2423. IEEE, June 2016
Lowe, D.: Object recognition from local scale-invariant features. In: Proceedings 7th IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157. IEEE (1999)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings Computer Vision and Pattern Recognition, pp. 886–893. IEEE (2005)
Bay, H., Tuytelaars, T., Van Gool, L.: Speeded up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346–359 (2008)
Tanjil, F.: Deep learning concepts for evolutionary art. Master’s thesis, Department Computer Science, Brock U. (2018)
Koza, J.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)
Poli, R., Langdon, W., McPhee, N.: A Field Guide to Genetic Programming. Lulu Enterprises UK Ltd. (2008)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Gooch, B., Gooch, A.: Non-photorealistic Rendering. A. K. Peters (2001)
Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 427–436, June 2015
Bontrager, P., Lin, W., Togelius, J., Risi, S.: Deep interactive evolution. In: Liapis, A., Romero Cardalda, J.J., Ekárt, A. (eds.) EvoMUSART 2018. LNCS, vol. 10783, pp. 267–282. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-77583-8_18
Stanley, K.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program. Evolvable Mach. 8(2), 131–162 (2007)
Baluja, S., Pomerleau, D., Jochem, T.: Towards automated artificial evolution for computer-generated images. Connection Sci. 6(2–3), 325–354 (1994)
Agapitos, A., et al.: Deep evolution of image representations for handwritten digit recognition. In: Proceedings CEC 2015, Sendai, Japan, 25–28 May 2015, pp. 2452–2459. IEEE (2015)
Gircys, M.: Image evolution using 2D power spectra. Master’s thesis, Brock University, Department of Computer Science (2018)
Luke, S.: ECJ: a Java-based evolutionary computation research system. https://cs.gmu.edu/~eclab/projects/ecj/. Accessed 16 Sept 2017
Chintala, S.: Pytorch documentation. http://pytorch.org/docs/master/. Accessed 16 Sept 2017
Chintala, S.: PyTorch: tensors and dynamic neural networks in python with strong GPU acceleration. http://pytorch.org/. Accessed 16 Sept 2017
Acknowledgements
This research was supported by NSERC Discovery Grant RGPIN-2016-03653.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Tanjil, F., Ross, B.J. (2019). Deep Learning Concepts for Evolutionary Art. In: Ekárt, A., Liapis, A., Castro Pena, M.L. (eds) Computational Intelligence in Music, Sound, Art and Design. EvoMUSART 2019. Lecture Notes in Computer Science(), vol 11453. Springer, Cham. https://doi.org/10.1007/978-3-030-16667-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-16667-0_1
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-16666-3
Online ISBN: 978-3-030-16667-0
eBook Packages: Computer ScienceComputer Science (R0)