Aesthetic image rating (AIR) algorithm

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Reaves, David: Aesthetic image rating (AIR) algorithm. Ph.D. thesis University of Texas at Austin (2008)



Rapidly advancing technologies offer a greater volume of people the possi- bility to both create and consume information. And, with this widening of opportunity, the volume of digital information has increased in mammoth proportion. Indeed, this age of information is marked by quantity, but what of quality? It has become necessary to formulate a systematic method to sift through the vast amount of data. This paper presents an algorithm that seeks to emulate the manner by which a human might judge an image's aesthetic value. The notion that a machine could imitate human thought processes is not necessarily novel, and, as such, a fair amount of work has been done regarding algorithmic aesthetic digital image rating. Most of these proposed algorithms, however, have been unable to satisfactorily mimic ac- tual human ratings. This paper builds on these past works and yet goes further by significantly improving on these prior accomplishments. The re- sult of our focus on the discovery of an optimal vector of image features is a highly accurate emulation of human ratings

Extended Abstract


Used References

[1] The iLab Neuromorphic Vision C++ Toolkit.

[2] Rudolf Arnheim. Art and Visual Perception: A Psychology of the Cre-ative Eye. University of California Press, 1974.

[3] Chih-Chung Chang and Chih-Jen Lin. LIBSVM: a library for support vector machines, 2001. Software available at

[4] Yi-Wei Chen and Chih-Jen Lin. Combining SVMs with Various Feature Selection Strategies, 2005.

[5] Corbis. Corbis Corporate Fact Sheet.

[6] R. Datta, D. Joshi, J. Li, and J.Z. Wang. Studying aesthetics in photographic images using a computational approach. pages III: 288-301, 2006.

[7] Ritendra Datta, Jia Li, and James Z. Wang. Learning the consensus on visual quality for next-generation image management. In MULTI-MEDIA '07: Proceedings of the 15th international conference on Multimedia, pages 533{536, New York, NY, USA, 2007. ACM.

[8] P. Golland. Discriminative direction for kernel classifiers, 2001.

[9] The Guardian. Together in electric dreams, January 2005.

[10] L. Itti, C. Koch, and E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1254-1259, Nov 1998.

[11] Yan Ke, Xiaoou Tang, and Feng Jing. The design of high-level features for photo quality assessment. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 1, pages 419-426, 2006.

[12] Anthony Santella, Maneesh Agrawala, Doug DeCarlo, David Salesin, and Michael Cohen. Gaze-based interaction for semi-automatic photo cropping. In CHI '06: Proceedings of the SIGCHI conference on Human Factors in computing systems, pages 771{780, New York, NY, USA, 2006. ACM.

[13] Hanghang Tong, Mingjing Li, Hong-Jiang Zhan, Jingrui He, and Changshui Zhang. Classification of digital photos taken by photographers or home users. In Advances in Multimedia Information Processing - PCM 2004, volume 3331/2005. Springer Berlin / Heidelberg, 2004.

[14] Hanghang Tong, Mingjing Li, Hongjiang Zhang, and Changshui Zhang. Blur detection for digital images using wavelet transform. Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on, 1:17{20 Vol.1, 27-30 June 2004.

[15] David Tschumperl�e. The CImg Library  : C++ Template Image Processing Library.

[16] G. Uytterhoeven, F. Van Wulpen, M. Jansen, D. Roose, and A. Bultheel. WAILI: A software library for image processing using integer wavelet transforms. In K.M. Hanson, editor, Medical Imaging 1998: Image Processing, volume 3338, pages 1490{1501. InternationalSociety for Optical Engineering, 1998.

[17] T. W. Whitfield and T. J. Wiltshire. Color psychology: a critical review. Genetic, Social, and General Psycology Monographs, 1990


Full Text

intern file

Sonstige Links