UNDERSTANDING PHOTOGRAPHIC COMPOSITION THROUGH DATA-DRIVEN APPROACHES

Dansheng Mao, Ramakrishna Kakarala, Deepu Rajan, Shannon Lee Castleman

2010

Abstract

Many elements contribute to a photograph's aesthetic value, include context, emotion, color, lightness, and composition. Of those elements, composition, which is how the arrangement of subjects, background, and features work together, is both highly challenging, and yet amenable, for understanding with computer vision techniques. Choosing famous monochromic photographs for which the composition is the dominant aesthetic contributor, we have developed data-driven approaches to understand composition. We obtain two novel results. The first shows relationships between the composition styles of master photographers based on their works, as obtained by analyzing extracted SIFT features. The second result, which relies on data obtained from eye-tracking equipment on both expert photographers and novices, shows that there are significant differences between them in what is salient in a photograph's composition.

References

  1. Bressan, M., Cifarelli, C., and Perronnin, F. (2008). An analysis of the relationship between painters based on their work. In ICIP, pages 113-116.
  2. Datta, R., Joshi, D., Li, J., and Wang, J. Z. (2006). Studying aesthetics in photographic images using a computational approach. In Proc. ECCV, pages 7-13.
  3. Jaakkola, T. and Haussler, D. (1998). Exploiting generative models in discriminative classifiers. In In Advances in Neural Information Processing Systems 11, pages 487-493. MIT Press.
  4. Jones-Smith, K. and Mathur, H. (2006). Fractal analysis: Revisiting pollock's drip paintings. Nature, pages E9- E10.
  5. Judd, T., Ehinger, K., Durand, F., and Torralba, A. (2009). Learning to predict where humans look. In ICCV.
  6. Kagian, A., Dror, G., Leyvand, T., Cohen-Or, D., and Ruppin, E. (2006). A humanlike predictor of facial attractiveness. In NIPS, pages 649-656.
  7. Lowe, D. G. (2004). Distinctive image features from scaleinvariant keypoints. International Journal of Computer Vision, 60:91-110.
  8. Lyu, S., Rockmore, D., and Farid, H. (2004). A digital technique for art authentication. Proceedings of the National Academy of Sciences, 101(49):17006-17010.
  9. Perronnin, F. and Dance, C. R. (2007). Fisher kernels on visual vocabularies for image categorization. In CVPR.
  10. Taylor, R. P., Micolich, A. P., and Jonas, D. (1999). Fractal analysis of pollock's drip paintings. Nature, 399:422.
  11. van der Heijden, F., Duin, R., de Ridder, D., and Tax, D. M. J. (2004). Classification, Parameter Estimation and State Estimation. Wiley.
  12. Zakia, R. (2007). Perception and imaging: photography-a way of seeing. Elsevier Science Ltd.
Download


Paper Citation


in Harvard Style

Mao D., Kakarala R., Rajan D. and Lee Castleman S. (2010). UNDERSTANDING PHOTOGRAPHIC COMPOSITION THROUGH DATA-DRIVEN APPROACHES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 425-430. DOI: 10.5220/0002842104250430


in Bibtex Style

@conference{visapp10,
author={Dansheng Mao and Ramakrishna Kakarala and Deepu Rajan and Shannon Lee Castleman},
title={UNDERSTANDING PHOTOGRAPHIC COMPOSITION THROUGH DATA-DRIVEN APPROACHES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={425-430},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002842104250430},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - UNDERSTANDING PHOTOGRAPHIC COMPOSITION THROUGH DATA-DRIVEN APPROACHES
SN - 978-989-674-029-0
AU - Mao D.
AU - Kakarala R.
AU - Rajan D.
AU - Lee Castleman S.
PY - 2010
SP - 425
EP - 430
DO - 10.5220/0002842104250430