Skip to main content
SpringerLink
Log in

Photo classification based on the presence of diagonal line using pre-trained DCNN VGG16

  • 1200: Machine Vision Theory and Applications for Cyber Physical Systems
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The diagonal line is one of the important linear components in a photograph. It contributes significantly towards improving the aesthetic perception and rendering high scores by enhancing the sense of direction. Automatic detection of diagonal lines in a photograph can link to numerous real-time applications like on-site guidance to amateur photographers by finding the presence of diagonal lines, aesthetic evaluation of photographs in various photography competitions, searching similar photographs containing diagonal lines from any database without manual labelling, and so on. A deep dive into the related literature reveals that very rare research has been conducted in the mentioned area. This paper presents a novel VGG16 Deep Convolutional Neural Network (DCNN) based approach to find diagonal lines in a photograph. The proposed approach classifies digital photographs into two categories: photographs containing diagonal lines or not by the application of transfer learning. The proposed model is implemented on the ground truth dataset of 5,683 images and the satisfactory results have been achieved. The contribution of the paper is significant due to the fact that the existence of a similar classifier for digital photographs is zero in the literature. The proposed work also contributes towards the generation of the diagonal line image dataset called Diagonal-line Containing Image (DCI) which will be useful for future research in the domain.

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

Data Availability

Online at https://www.somadebnath.com/post/diagonal-line-containing-image-dataset-dci

Code availability

With the authors.

References

  1. Wang JZ, Li J, Gray RM, Wiederhold G (2001) Unsupervised multiresolution segmentation for images with low depth of field. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(1):85-90

  2. Zhang T, Nefs HT, Redi J, Heynderickx I (2014) aesthetic appeal of depth of field in photographs. pages 81-86

  3. Sheikh HR, Sabir MF, Bovik AC (2006) A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Transactions on image processing, 15(11):3440-3451

  4. Datta R, Joshi D, Li J, Wang  JZ (2006) Studying aesthetics in photographic images using a computational approach. Computer Vision-ECCV, pages 288-301 

  5. Suler J (2013) Photographic psychology: Image and psyche. http://truecenterpublishing.com/photopsy/psylines.htm/

  6. Elements of art. https://www.getty.edu/education/teachers/building_lessons/formal_analysis.html/.  Accessed: 2021-07-29

  7. Lan K, Sekiyama K (2015) Autonomous viewpoint selection of robots based on aesthetic composition evaluation of a photo. In 2015 IEEE Symposium Series on Computational Intelligence, pages 295-300. IEEE

  8. Islam MB, Kuan WL, Onn WC (2017) A survey of aesthetics-driven image recomposition. Multimedia tools and applications, Springer, 76:9517-9542

    Article  Google Scholar 

  9. Pramila A, Keskinarkaus A, Takala V, Seppanen T (2017) Extracting watermarks from printouts captured with wide angles using computational photography. Multimedia tools and applications, Springer, 76:16063-16084

  10. Datta R, Wang JZ (2010) Acquine: Aesthetic quality inference engine - real- time automatic rating of photo aesthetics. Proceedings of the International Conference on MIR, 4:421-424

  11. Lu X, Lin Z, Jin H, Yang J, Wang JZ (2014) Rapid: Rating pictorial aesthetics using deep learning". Proceedings of the 22nd ACM international conference on Multimedia, pages 457-466

  12. Mai L, Jin H, Liu F (2016) Composition-preserving deep photo aesthetics assessment". Proceedings of the IEEE conference on computer vision and pattern recognition, pages 497-506

  13. Wang W, Zhao M, Wang L, Huang J, Cai C, Xu X (2016) A multi-scene deep learning model for image aesthetic evaluation. Signal Processing: Image Communication, 47:511-518

  14. Wang W, Zhao W, Cai C, Huang J, Xu X, Li L (2015) An efficient image aesthetic analysis system using hadoop. Signal Processing: Image Communication, 39:499-508

  15. Zhang X, Gao X, Lu W, Yu Y, He L (2019) Fusion global and local deep representations with neural attention for aesthetic quality assessment. Signal Processing: Image Communication, 78:42-50

  16. Yang, J, Huang Z, Sim K, Lu W,  Liu K, Liu H (2019) No-reference image quality assessment focusing on human facial region". Signal Processing: Image Communication, 78:51-61

  17. Zhang C, Zhu C, Xu X, Liu Y, Xiao Y, Tillo T (2018) Visual aesthetic understanding: sample-specific aesthetic classification and deep activation map visualization". Signal Processing: Image Communication, 67:12-21

  18. Lu P, Peng XJ, Yu, J, Peng X (2019) Gated cnn for visual quality assessment based on color perception. Signal Processing: Image Communication, 72:105-112

  19. Jin X, Wu L, Li X, Zhang X, Chi I, Peng S, Ge S, Zhao G, Li S (2018) ILGNet: inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation. IET Computer Vision, 13(2):206-212

  20. Zhu X, Moh TS (2016) Assessing photograph aesthetic quality with color based descriptor. 2016 International Conference on High Performance Computing Simulation (HPCS), 8:222-229

  21. Nishiyama M, Okabe T, Sato I, Sato Y (2011) Aesthetic quality classification of photographs based on color harmony. IEEE CVPR, 8:33-40

  22. Moon P, Spencer DE (1944) Geometric formulation of classical color harmony. JOSA, 34(1):46-59

  23. Matsuda Y (1995) Color design. Asakura Shoten, 2(4):10

  24. Marchesotti L, Murray N, Perronnin F (2015) Discovering beautiful attributes for aesthetic image analysis. International journal of computer vision, Springer, 113:246-266

  25. Kao Y, Huang K, Maybank S (2016) Hierarchical aesthetic quality assessment using deep convolutional neural networks. Signal Processing: Image Communication, 47:500-510

  26. Li C, Chen T (2009) Aesthetic visual quality assessment of paintings. IEEE J. of Selected Topics in Signal Processing, 3:236-253

  27. Aydin T, Smolic A, Gross M (2014) Automated aesthetic analysis of photographic images. IEEE transactions on visualization and computer graphics, 21(1):31-42

  28. Su HH, Chen TW, Kao CC, Hsu WH, Chien SY (2012) Preference-aware view recommendation system for scenic photos based on bag-of-aesthetics-preserving features. IEEE Transactions on Multimedia, 14:833-843

  29. Bhattacharya S, Sukthankar R, Shah M (2010) A framework for photo-quality assessment and enhancement based on visual aesthetics". pages 271-280

  30. Lee H-J, Hong K-S, Kang H, Lee S (2017) Photo aesthetics analysis via dcnn feature encoding. IEEE Transactions on Multimedia, 19(8):1921-1932

  31. Tang X, Luo W, Wang X (2013) Content-based photo quality assessment. IEEE Transactions on Multimedia, 15:1930-1943

  32. Yeh M, Chuang C (2014) Assessing the aesthetic quality of photographs through group comparison. IEEE ICCE Conference, pages 91-92, 26-28 May

  33. Bishop A, Ciesielski V, Trist K (2014) Feature construction using genetic programming for classification of images by aesthetic value. series of Lecture notes in Computer Science, Springer, 8601:62-73

  34. Ni B, Xu M, Cheng B, Wang M, Yan S, Tian Q (2013) Learning to photograph: A compositional perspective. IEEE Transactions on Multimedia, 15:1138-1151

  35. Tian X, Dong Z, Yang K, Mei T (2015) Query-dependent aesthetic model with deep learning for photo quality assessment. IEEE Transactions on Multimedia, 17(11):2035-2048

  36. Kao Y, He R, Huang K (2017) Deep aesthetic quality assessment with semantic information. IEEE Trans.Image Process., 26:1482-1495

  37. Zhang J, Miao Y, Zhang J, Yu J (2020) Inkthetics: A comprehensive computational model for aesthetic evaluation of chinese ink paintings. IEEE Access

  38. Zhang T, Xie J, Zhou X, Choi C (2020) The effects of depth of Field on subjective evaluation of aesthetic appeal and image quality of photographs. IEEE Access, 8:13467-13475

  39. Zhang F, Wang M, Hu S (2013) Aesthetic image enhancement by dependence-aware object recomposition. IEEE Trans. Multimedia, 15:1480-1490

  40. Su H-H, Chen T-W, Kao C-C, Hsu WH, Chien S-Y (2011) Scenic photo quality assessment with bag of aesthetics-preserving features. pages 1213-1216

  41. Guo G, Wang H, Shen C, Yan Y, Mark Liao H-Y (2018) Automatic image cropping for visual aesthetic enhancement using deep neural networks and cascaded regression. IEEE Transactions on Multimedia, 20(8):2073-2085

  42. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition". arXiv preprint arXiv:1409.1556

  43. Zhang Z, Sabuncu MR (2018) Generalized cross entropy loss for training deep neural networks with noisy labels". In 32 Conference on Neural Information Processing Systems (NeurIPS)

Download references

Funding

No.

Author information

Authors and Affiliations

  1. Dept. of CSE, NIT Durgapur, Durgapur, India

    Soma Debnath & Suvamoy Changder

  2. Dr. B. C. Roy Engineering College Durgapur, Durgapur, India

    Ratnakirti Roy

Authors
  1. Soma Debnath
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ratnakirti Roy
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Suvamoy Changder
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Soma Debnath.

Ethics declarations

Conflicts of Interest/Competing Interests

No.

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

Debnath, S., Roy, R. & Changder, S. Photo classification based on the presence of diagonal line using pre-trained DCNN VGG16. Multimed Tools Appl 81, 22527–22548 (2022). https://doi.org/10.1007/s11042-021-11557-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11557-w

Keywords

Search

Navigation