(44-1) 16 * << * >> * Russian * English * Content * All Issues

Deep learning application for box-office evaluation of images

V.G. Efremtsev 1, N.G. Efremtsev 1, E.P. Teterin 2, P.E. Teterin 3, V.V. Gantsovsky 1

1 Independent researcher,
2 Kovrov State Technological Academy named after V.A.Degtyarev, Kovrov, Vladimir region, Russia;
3 National Research Nuclear University "MEPhI", Moscow, Russia

 PDF, 749 kB

DOI: 10.18287/2412-6179-CO-515

Pages: 127-132.

Full text of article: Russian language.

Abstract:
The possibility of application a convolutional neural network to assess the box-office effect of digital images is reviewed. We studied various conditions for sample preparation, optimizer algorithms, the number of pixels in the samples, the size of the training sample, color schemes, compression quality, and other photometric parameters in view of effect on training the neural network. Due to the proposed preliminary data preparation, the optimum of the architecture and hyperparameters of the neural network we achieved a classification accuracy of at least 98%.

Keywords:
deep learning, neural networks, image analysis.

Citation:
Efremtsev VG, Efremtsev NG, Teterin EP, Teterin PE, Gantsovsky VV. Deep learning application for box-office evaluation of images. Computer Optics 2020; 44(1): 127-132. DOI: 10.18287/2412-6179-CO-515.

Acknowledgements:
Authors thank for the support from National Research Nuclear University MEPhI in the framework of the Russian Academic Excellence Project (contract No. 02.a03.21.0005, 27.08.2013).

References:
  1. Aloufi S, Zhu S, El Saddik A. On the prediction of Flickr image popularity by analyzing heterogeneous social sensory data. Sensors 2017; 17: 631.
  2. Ellett J. New AI-based tools are transforming social media marketing 2017. Source: <https://www.forbes.com/sites/johnellett/2017/07/27/new-ai-based-tools-are-transforming-social-media-marketing/#7437b17669a2>.
  3. More V, Agrawal P. Study on aesthetic analysis of photographic images techniques to produce high dynamic range images. Int J Comp Applicat 2017; 159(8): 34-38.
  4. Talebi H, Milanfar P. NIMA: Neural image assessment // IEEE Trans Image Process2018; 27(8): 3998-4011.
  5. Lu X, Lin Z, Shen X, Mech R, Wang JZ. Deep multi-patch aggregation network for image style, aesthetics, and quality estimation. Proc IEEE Int Conf Comput Vis 2015: 990-998.
  6. Kang L, Ye P, Li Y, Doermann D. Convolutional neural networks for no-reference image quality assessment, in Proc IEEE Conf Comput Vis Pattern Recognit 2014: 1733-1740.
  7. Xue W, Zhang L, Mou X. Learning without human scores for blind image quality assessment. Proc IEEE Conf Comput Vis Pattern Recognit 2013: 995-1002.
  8. Nikonorov AV, Petrov MV, Bibikov SA, Kutikova VV, Morozov AA, Kazanskiy NL. Image restoration in diffractive optical systems using deep learning and deconvolution. Computer Optics 2017; 41(6): 875-887. DOI: 10.18287/2412-6179-2017-41-6-875-887.
  9. Rubio F, Flores MJ, Puerts JM. Drawing a baseline in aesthetic quality assessment. Proceedings of SPIE. – 2017. – Vol. 10696. – 106961M.
  10. Li Y, et al. Image aesthetic quality evaluation using convolution neural network embedded learning. Optoelectron Lett 2017; 13(6):·471-475.
  11. Murray N, Marchesotti L, Perronnin F. AVA: A large-scale database for aesthetic visual analysis. Proc IEEE Conf Comput Vis Pattern Recognit 2012: 2408-2415.
  12. Marchesotti L, Perronnin F, Larlus D, Csurka G. Assessing the aesthetic quality of photographs using generic image descriptors. ICCV 2011: 1784-1791.
  13. Rycarev IA, Kirsh DV, Kupriyanov AV. Clustering of media content from social networks using bigdata technology. Computer Optics 2018; 42(5): 921-927. DOI: 10.18287/2412-6179-2018-42-5- 921-927.
  14. Luo W, Wang X, Tang X. Content-based photo quality assessment. ICCV 2011: 2206-2213. DOI: 10.1109/ICCV.2011.6126498.
  15. Luo Y, Tang X. Photo and video quality evaluation: Focusing on the subject. ECCV 2008: 386-399. DOI: 10.1007/978-3-540-88690-7_29.
  16. Sharda R, Delen D. Predicting box-office success of motion pictures with neural networks. Expert Systems with Applications 2006; 30: 243-254.
  17. Ning X, et al. Rating prediction via generative convolutional neural networks based regression. Patt Recogn Lett 2018; In Press.
  18. Loureiro ALD, Miguéis VL, da Silva LFM. Exploring the use of deep neural networks for sales forecasting in fashion retail. Decision Support Systems 2018; 114: 81-93.
  19. The parallel dots image recognition service. Source: <https://www.paralleldots.com/object-recognizer>.
  20. EveryPixel aestetics service. Source: <https://www.everypixel.com/aesthetics>.
  21. Kim P. MATLAB deep learning: With machine learning, neural networks and artificial intelligence. Apress; 2017.
  22. Goodfellow I, Bengio Y, Courville A. Deep learning. MIT press, 2016.
  23. Raschka S. Python Machine Learning. Birmingham: Packt Publishing; 2015.
  24. Richert W, Coelho LP. Building machine learning systems with Python. Packt Publishing; 2013.
  25. Chollet F. Deep learning with Python. New York: Manning Publications; 2017.

 

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20