Aesthetic Assessment for Digital Portrait Photos

Abstract

Abstract: Computational aesthetic evaluation is a challenging research. With the widespread use of digital products, it needs to improve the intelligence of digital products. How are these photos judged good or bad? The traditional photo aesthetic quality evaluation mainly is done based on subjective judgment or experts or the photographer's understanding for beauty. It is not only slow, but also with highly subjective. The results of face detect and eye detect were used to calculate visual balance of digital portrait based on face proportion and other features for aesthetic assessment of digital portrait photo were extracted too. The computer aesthetic score were compared with the subjective evaluation. The results show that, although the computer aesthetic score are different from the subjective evaluation, the computer aesthetic assessment has clear and objective evaluation criteria.

Key words: computational aesthetics, aesthetic quality assessment, photo structure, face detection, human eye opening

CLC Number:

TP391.9

Tao Zeen, Pu Yuanyuan, Xu Dan, Liu Yiwei. Aesthetic Assessment for Digital Portrait Photos[J]. Journal of System Simulation, 2016, 28(10): 2298-2303.

References 14

[1]	Shao J, Zhou Y.Photo Quality Assessment in Different Categories[J]. Journal of Computational Information Systems (S0887-4417), 2013, 9(8): 3209-3217.
[2]	Battiato S, Moltisanti M, Ravì F, et al. Aesthetic scoring of digital portraits for consumer applications [C]// IS&T/SPIE Electronic Imaging. USA: International Society for Optics and Photonics, 2013: 866008-866008-10.
[3]	Ravì F, Battiato S.A novel computational tool for aesthetic scoring of digital photography[C]// Conference on Colour in Graphics, Imaging, and Vision. USA: Society for Imaging Science and Technology, 2012, 2012(1): 349-354.
[4]	Bhattacharya S, Sukthankar R, Shah M.A framework for photo-quality assessment and enhancement based on visual aesthetics[C]// Proceedings of the international conference on Multimedia. USA: ACM, 2010: 271-280.
[5]	Li C, Gallagher A, Loui A C, et al.Aesthetic quality assessment of consumer photos with faces[C]// The 17th IEEE International Conference on Image Processing (ICIP), 2010. USA: IEEE, 2010: 3221-3224.
[6]	Huang X, Han X, Eckert C.OPARS: objective photo aesthetics ranking system[M]// Advances in Information Retrieval. Germany: Springer Berlin Heidelberg, 2013: 861-864.
[7]	Khan S S, Vogel D.Evaluating visual aesthetics in photographic portraiture[C]// Proceedings of the Eighth Annual Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging. Annecy, France: Eurographics Association, 2012: 55-62.
[8]	Chu W T, Chen Y K, Chen K T.Size does matter: how image size affects aesthetic perception[C]// Proceedings of the 21st ACM international conference on Multimedia. USA: ACM, 2013: 53-62.
[9]	Redi M, Rasiwasia N, Aggarwal G, et al.The beauty of capturing faces: Rating the quality of digital portraits[C]// IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. USA: IEEE, 2015:1-8.
[10]	Nilsson M, Nordberg J, Claesson I. Face detection using local SMQT features and split up snow classifier [C]// IEEE International Conference on Acoustics, Speech and Signal Processing, 2007, ICASSP 2007. USA: IEEE, 2007: II/589-II/592.
[11]	Nilsson M, Dahl M, Claesson I. The successive mean quantization transform [C]// Proceedings of IEEE International Conference on Acoustics, Speech,Signal (ICASSP '05), USA: IEEE, 2005: IV/429-IV/432.
[12]	吴冰, 陈步威, 李富贵, 等. 基于Hough 变换的人眼检测方法研究[J]. 河南理工大学学报(自然科学版), 2009, 27(5): 556-559.
[13]	Tzortzis G, Likas A.The minmax k-means clustering algorithm[J]. Pattern Recognition (S0031-3203), 2014, 47(7): 2505-2516.
[14]	Luo W, Wang X, Tang X.Content-based photo quality assessment[C]// 2011 IEEE International Conference on Computer Vision (ICCV). USA: IEEE, 2011: 2206-2213.