Skip to main content
SpringerLink
Log in

IDEA: A new dataset for image aesthetic scoring

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The aesthetic quality assessment of image is a challenging work in computer vision field. The recent research work used the deep convolutional neural network to evaluate the aesthetic quality of images. However, the score of image data sets has a strongly normal distribution, which makes the training of neural network easy to be over-fitting. In addition, traditional deep learning methods usually pre-process images, which destroy the original aesthetic features of the picture, so that the network can only learn some superficial aesthetic features. This paper presents a new data set what images distributed evenly for aesthetics (IDEA). This data set has less statistical characteristics, which is helpful for the neural network to learn the deeper features. We propose a new spatial aggregation perception neural network architecture which can control channel weights automatically. Our experiments in different data sets can prove the advantages and effectiveness of our method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Bianco S, Celona L, Napoletano P, et al. (2016) Predicting image aesthetics with deep learning[C]. In: International conference on advanced concepts for intelligent vision systems. Springer, Cham, pp 117–125

  2. Deng J, Dong W, Socher R, et al. (2009) Imagenet: a large-scale hierarchical image database[C]. In: CVPR 2009 IEEE conference on computer vision and pattern recognition, 2009. IEEE, pp 248–255

  3. Dong Z, Tian X (2015) Multi-level photo quality assessment with multi-view features[J]. Neurocomputing 168:308–319

    Article  Google Scholar 

  4. He K, Zhang X, Ren S, et al. (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition[C]. In: European conference on computer vision. Springer, Cham, pp 346–361

  5. He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  6. He L, Xu X, Lu H, et al. (2017) Unsupervised cross-modal retrieval through adversarial learning[C]. In: IEEE international conference on multimedia and expo. IEEE, pp 1153–1158

  7. Hou L, Yu C P, Samaras D (2016) Squared earth mover’s distance-based loss for training deep neural networks[J]. arXiv:1611.05916

  8. Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks[J]. arXiv:1709.01507

  9. Jia Y, Shelhamer E, Donahue J, et al. (2014) Caffe: convolutional architecture for fast feature embedding[C]. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675–678. ACM

  10. Jin B, Segovia M V O, Süsstrunk S (2016) Image aesthetic predictors based on weighted cnns[C]. In: 2016 IEEE international conference on image processing (ICIP). IEEE, pp 2291–2295

  11. Jin X, Chi J, Peng S, et al. (2016) Deep image aesthetics classification using inception modules and fine-tuning connected layer[C]. In: 2016 8th international conference on wireless communications signal processing (WCSP). IEEE, pp 1–6

  12. Jin X, Wu L, Song C, et al. (2017) Predicting aesthetic score distribution through cumulative Jensen-Shannon Divergence[C]. In: Proceedings of the 32th international conference of the America association for artificial intelligence (AAAI18), New Orleans, Louisiana, February 2-7, 2018

  13. Kao Y, He R, Huang K (2017) Deep aesthetic quality assessment with semantic information[J]. IEEE Trans Image Process 26(3):1482–1495

    Article  MathSciNet  Google Scholar 

  14. Kao Y, Huang K, Maybank S (2016) Hierarchical aesthetic quality assessment using deep convolutional neural networks[J]. Signal Process Image Commun 47:500–510

    Article  Google Scholar 

  15. Kao Y, Wang C, Huang K (2015) Visual aesthetic quality assessment with a regression model[C]. In: 2015 IEEE international conference on image processing (ICIP). IEEE, pp 1583–1587

  16. Karayev S, Trentacoste M, Han H, et al. (2013) Recognizing image style[J]. arXiv:1311.3715

  17. Ke Y, Tang X, Jing F (2006) The design of high-level features for photo quality assessment[C]. In: 2006 IEEE computer society conference on computer vision and pattern recognition, vol 1, pp 419–426. IEEE

  18. Kong S, Shen X, Lin Z, et al. (2016) Photo aesthetics ranking network with attributes and content adaptation[C]. In: European conference on computer vision. Springer, Cham, pp 662–679

  19. Lu X, Lin Z, Jin H, et al. (2014) Rapid: Rating pictorial aesthetics using deep learning[C]. In: Proceedings of the 22nd ACM international conference on multimedia. ACM, pp 457–466

  20. Lu X, Lin Z, Jin H, et al. (2015) Rating image aesthetics using deep learning[J]. IEEE Trans Multimed 17(11):2021–2034

    Article  Google Scholar 

  21. Lu X, Lin Z, Shen X, et al. (2015) Deep multi-patch aggregation network for image style, aesthetics, and quality estimation[C]. In: Proceedings of the IEEE international conference on computer vision, pp 990–998

  22. Lu H, Li Y, Mu S, et al. (2017) Motor anomaly detection for unmanned aerial vehicles using reinforcement learning[J]. IEEE internet of things journal

  23. Lu H, Li Y, Chen M, et al. (2017) Brain intelligence: go beyond artificial intelligence[J]. Mobile Networks and Applications, pp 1–8

  24. Lu H, Li B, Zhu J et al (2017) Wound intensity correction and segmentation with convolutional neural networks[J]. Concurr Computat Pract Exper 29(6):e3927

    Article  Google Scholar 

  25. Lu H, Li Y, Uemura T, et al. (2018) Low illumination underwater light field images reconstruction using deep convolutional neural networks[J]. Future Generation Computer Systems

  26. Ma S, Liu J, Chen CW (2017) A-lamp: adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment[J]. arXiv:1704.00248

  27. Mai L, Jin H, Liu F (2016) Composition-preserving deep photo aesthetics assessment[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 497–506

  28. Marchesotti L, Perronnin F, Larlus D, et al. (2011) Assessing the aesthetic quality of photographs using generic image descriptors[C]. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 1784–1791

  29. Murray N, Marchesotti L, Perronnin F (2012) A large-scale database for aesthetic visual analysis[C]. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR), pp 2408–2415. IEEE

  30. Serikawa S, Lu H (2014) Underwater image dehazing using joint trilateral filter[J]. Comput Electr Eng 40(1):41–50

    Article  Google Scholar 

  31. Wang W, Zhao M, Wang L, et al. (2016) A multi-scene deep learning model for image aesthetic evaluation[J]. Signal Process Image Commun 47:511–518

    Article  Google Scholar 

  32. Wang Z, Liu D, Chang S, et al. (2017) Image aesthetics assessment using Deep Chatterjee’s machine[C]. In: 2017 international joint conference on neural networks (IJCNN). IEEE, pp 941–948

  33. Wu O, Hu W, Gao J (2011) Learning to predict the perceived visual quality of photos[C]. In: 2011 IEEE international conference on computer vision (ICCV). IEEE, pp 225–232

  34. Xu X, He L, Lu H, et al. (2018) Deep adversarial metric learning for cross-modal retrieval[J]. World Wide Web-internet & Web Information Systems, pp 1–16

Download references

Acknowledgements

This work is partially supported by the National Natural Science Foundation of China (Grant Nos. 61772047, 61772513), the Science and Technology Project of the State Archives Administrator (Grant No. 2015-B-10), and the Fundamental Research Funds for the Central Universities (Grant No. 328201803, 328201801).

Author information

Authors and Affiliations

  1. Beijing Electronic Science and Technology Institute, Beijing, 100070, China

    Xin Jin, Le Wu, Geng Zhao, Xinghui Zhou, Xiaokun Zhang & Xiaodong Li

  2. CETC Big Data Research Institute Co.,Ltd., Guiyang, Guizhou, China

    Xin Jin

Authors
  1. Xin Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Le Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Geng Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xinghui Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaokun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiaodong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaodong Li.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jin, X., Wu, L., Zhao, G. et al. IDEA: A new dataset for image aesthetic scoring. Multimed Tools Appl 79, 14341–14355 (2020). https://doi.org/10.1007/s11042-018-6436-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6436-0

Keywords

Search

Navigation