Skip to main content

Advertisement

Springer Nature Link
Log in

Social image aesthetic classification and optimization algorithm in machine learning

  • S.I.: Artificial Intelligence Technologies in Sports and Art Data Applications
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The popularity of digital cameras and social networks has greatly enriched people's spiritual life, and we can easily obtain massive amounts of digital photos. However, due to the lack of professional guidance and differences in aesthetic appreciation, the photos taken many photographers lack aesthetics. This article is dedicated to the research of image aesthetics, using computers to simulate human perception, and realize the evaluation or beautification of images in line with human aesthetics. In terms of image classification, this article examines the unique perception of human vision on images and proposes new aesthetic features. Combining visual features and semantic features, the SVM algorithm is utilized to build an aesthetic classifier. In the aspect of image optimization, this paper uses the detection of the main image area and the division line of the area and adjusts the main body size and position of the image according to common aesthetic rules, so as to realize the optimization adjustment of the composition of the social image. The experimental results show that the accuracy of social image classification is 97.7%, and the optimized and adjusted images are more aesthetic.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Zulli D, Liu M, Gehl R (2020) Rethinking the “social” in “social media”: insights into topology, abstraction, and scale on the Mastodon social network[J]. New Media Soc 22(7):1188–1205

    Article  Google Scholar 

  2. Liu W, Sidhu A, Beacom AM et al (2017) Social network theory [J]. The Int Encyclopedia Media Effects 1–12

  3. Caldelli R, Becarelli R, Amerini I (2017) Image origin classification based on social network provenance[J]. IEEE Trans Inf Foren Secur 12(6):1299–1308

    Article  Google Scholar 

  4. Ju C, Bibaut A, van der Laan M (2018) The relative performance of ensemble methods with deep convolutional neural networks for image classification[J]. J Appl Stat 45(15):2800–2818

    Article  MATH  Google Scholar 

  5. Forchtner B, Kølvraa C (2017) Extreme right images of radical authenticity: Multimodal aesthetics of history, nature, and gender roles in social media[J]. Eur J Cult Polit Sociol 4(3):252–281

    Article  Google Scholar 

  6. Sheng K, Dong W, Huang H et al (2021) Learning to assess visual aesthetics of food images[J]. Comput Visual Media 7(1):139–152

    Article  Google Scholar 

  7. Crolic C, Zheng Y, Hoegg JA et al (2019) The influence of product aesthetics on consumer inference making[J]. J Assoc Cons Res 4(4):398–408

    Google Scholar 

  8. Li L, Zhu H, Zhao S et al (2020) Personality-assisted multi-task learning for generic and personalized image aesthetics assessment[J]. IEEE Trans Image Process 29:3898–3910

    Article  MATH  Google Scholar 

  9. Armalaite J, Jarutiene M, Vasiliauskas A et al (2018) Smile aesthetics as perceived by dental students: a cross-sectional study[J]. BMC Oral Health 18(1):1–7

    Article  Google Scholar 

  10. Peng H, Li J, Hu H et al (2020) Creating a computable cognitive model of visual aesthetics for automatic aesthetics evaluation of robotic dance poses[J]. Symmetry 12(1):23

    Article  Google Scholar 

  11. Cui C, Yang W, Shi C et al (2020) Personalized image quality assessment with Social-Sensed aesthetic preference[J]. Inf Sci 512:780–794

    Article  Google Scholar 

  12. Li X, Li X, Zhang G et al (2020) A novel feature fusion method for computing image aesthetic quality[J]. IEEE Access 8:63043–63054

    Article  Google Scholar 

  13. Gibson N (2017) Therapeutic photography: enhancing patient communication[J]. J Kidney Care 2(1):46–47

    Article  Google Scholar 

  14. Zhao W, Zhao F, Wang D et al (2019) Defocus blur detection via multi-stream bottom-top-bottom network[J]. IEEE Trans Pattern Anal Mach Intell 42(8):1884–1897

    Article  Google Scholar 

  15. Satriano A, Heydari B, Guron N et al (2019) 3-Dimensional regional and global strain abnormalities in hypertrophic cardiomyopathy[J]. Int J Cardiovasc Imag 35(10):1913–1924

    Article  Google Scholar 

  16. Dayan S, Rivkin A, Sykes JM et al (2019) Aesthetic treatment positively impacts social perception: analysis of subjects from the HARMONY study[J]. Aesthet Surg J 39(12):1380–1389

    Article  Google Scholar 

  17. Lemarchand F (2018) Fundamental visual features for aesthetic classification of photographs across datasets[J]. Pattern Recogn Lett 112:9–17

    Article  Google Scholar 

  18. Lee JT, Lee C, Kim CS (2019) Property-specific aesthetic assessment with unsupervised aesthetic property discovery[J]. IEEE Access 7:114349–114362

    Article  Google Scholar 

  19. Godinez WJ, Hossain I, Lazic SE et al (2017) A multi-scale convolutional neural network for phenotyping high-content cellular images[J]. Bioinformatics 33(13):2010–2019

    Article  Google Scholar 

  20. Islam MB, Lai-Kuan W, Chee-Onn W (2017) A survey of aesthetics-driven image recomposition[J]. Multimed Tools Appl 76(7):9517–9542

    Article  Google Scholar 

  21. Guo G, Wang H, Shen C et al (2018) Automatic image cropping for visual aesthetic enhancement using deep neural networks and cascaded regression[J]. IEEE Trans Multimed 20(8):2073–2085

    Article  Google Scholar 

  22. Zhang X, Gao X, Lu W et al (2019) Fusion global and local deep representations with neural attention for aesthetic quality assessment[J]. Signal Process Image Commun 78:42–50

    Article  Google Scholar 

  23. Islam MB, Wong LK, Low KL et al (2018) Aesthetics-driven stereoscopic 3-D image recomposition with depth adaptation[J]. IEEE Trans Multimed 20(11):2964–2979

    Article  Google Scholar 

  24. Takimoto H, Omori F, Kanagawa A (2021) Image aesthetics assessment based on multi-stream CNN architecture and saliency features[J]. Appl Artif Intell 35(1):25–40

    Article  Google Scholar 

  25. Berg S, Kutra D, Kroeger T et al (2019) Ilastik: interactive machine learning for (bio) image analysis[J]. Nat Methods 16(12):1226–1232

    Article  Google Scholar 

  26. Huang S, Jin X, Jiang Q et al (2021) A fully-automatic image colorization scheme using improved CycleGAN with skip connections [J]. Multimedia Tools Appl 1–28

  27. Tewari A, Elgharib M, Bernard F et al (2020) Pie: Portrait image embedding for semantic control[J]. ACM Trans Graph (TOG) 39(6):1–14

    Article  Google Scholar 

  28. Miao H, Zhang Y, Wang D et al (2021) Multi-output learning based on multimodal GCN and co-attention for image aesthetics and emotion analysis [J]. Mathematics 9(12):1437

    Article  Google Scholar 

  29. Tsekouras GE, Rigos A, Chatzistamatis S et al (2021) A novel approach to image recoloring for color vision deficiency[J]. Sensors 21(8):2740

    Article  Google Scholar 

  30. Bari ASMH, Sieu B, Gavrilova ML (2020) AestheticNet: deep convolutional neural network for person identification from visual aesthetic[J]. Vis Comput 36(10):2395–2405

    Article  Google Scholar 

  31. Guo F, Li F, Nagamachi M et al (2020) Research on color optimization of tricolor product considering color harmony and users’ emotion[J]. Color Res Appl 45(1):156–171

    Article  Google Scholar 

  32. Brown ST, McCarthy IG, Diemer B et al (2020) Connecting the structure of dark matter haloes to the primordial power spectrum[J]. Mon Not R Astron Soc 495(4):4994–5013

    Article  Google Scholar 

  33. Ge E, Yang Y, Gang M et al (2020) Predicting human disease-associated circRNAs based on locality-constrained linear coding[J]. Genomics 112(2):1335–1342

    Article  Google Scholar 

  34. Asgarian Dehkordi R, Khosravi H (2020) Vehicle type recognition based on dimension estimation and bag of word classification[J]. J AI Data Min 8(3):427–438

    Google Scholar 

  35. Xue J, Chen J, Chen C et al (2020) Public discourse and sentiment during the COVID 19 pandemic: using latent Dirichlet allocation for topic modeling on Twitter[J]. PLoS ONE 15(9):e0239441

    Article  Google Scholar 

Download references

Acknowledgements

This paper is supported by Science Foundation of Ministry of Education of China (No. 20YJC860022).

Author information

Authors and Affiliations

  1. School of Art and Design, Zhengzhou University of Aeronautics, Zhengzhou, 450046, Henan, China

    Pan Luo

Authors
  1. Pan Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Pan Luo.

Ethics declarations

Conflict of interest

We declare that there is no conflict of interest.

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

Luo, P. Social image aesthetic classification and optimization algorithm in machine learning. Neural Comput & Applic 35, 4283–4293 (2023). https://doi.org/10.1007/s00521-022-07128-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07128-1

Keywords