Abstract
Deep neural network (DNN) has gone through more than forty years from the simulation stage to the embryonic stage, to the conception and the initial formation of the theory, until further simple applications. Firstly, deep convolution neural network is used to extract features, and then the extracted features are coded by Gaussian aggregation. Finally, the encoded features are input into the full connection layer to classify the image. The experiment in this paper focuses on the two-dimensional facial expression animation technology under DNN. This experiment mainly introduces the two important steps of image conversion, spatial mapping and resampling technology, as well as the detailed definition of the MPEG-4 standard. By using the feature points obtained in the experiment as the feature points set in the face definition parameters, in the deformation algorithm based on Delaunay triangulation, the inverse mapping technology and the quadratic linear interpolation technology are combined with the face and combined with facial animation. The parameter step can realize the conversion of facial expressions, and the generated facial expressions are more natural and delicate.The experimental data show that the facial animation parameters (FAP) as a complete set of basic facial movements can recognize the most subtle facial expressions under DNN. Change, different FAP combinations can form different facial expressions. The experimental results show that the 76 facial feature points located in the experiment have been tested for grid generation. When the segmentation threshold is larger, the merge method is closer to the sub-point insertion method; otherwise, it is closer to the divide and conquer method. When the threshold is 20, the algorithm belongs to the divide and conquer method; when the threshold is 80, the algorithm belongs to the point insertion method. Through research, this article finds that the innovation of DNN on the visual performance of animated films can provide more help for the production of sophisticated animation works, and can continuously improve the visual performance and cultural connotation of animated films.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Yang Z, Xiang D, Cheng Y (2020) VR panorama mosaic algorithm based on particle swarm optimization and mutual information. IEEE Access 99:1–1
Lee SH, Lee SJ (2017) Development of remote automatic panorama VR imaging rig systems using smartphones. Clust Comput 21(1):1–11
Lanier J, Euchner J (2019) What has gone wrong with the internet, and how we can fix it: an interview with jaron lanier. Research Technology Management 62(3):13–20
Theocharis S, Giaginis C, Alexandrou P et al (2016) Evaluation of cannabinoid CB1 and CB2 receptors expression in mobile tongue squamous cell carcinoma: associations with clinicopathological parameters and patients’ survival. Tumour Biol 37(3):3647–3656
Oyewunmi OA, Taleb AI, Haslam AJ et al (2016) On the use of SAFT-VR Mie for assessing large-glide fluorocarbon working-fluid mixtures in organic Rankine cycles. Appl Energy 163(2):263–282
Fuji K (2018) Esoteric symbolism in animated film storytelling. Chinese Semiotic Studies 14(3):347–370
Cui Q, Sun H, Li Y et al (2020) Efficient human motion recovery using bidirectional attention network. Neural Comput & Applic 32:10127–10142
Hsu FC, Hsiang TW (2018) Factors affecting color discrepancies of animated film characters. Journal of Interdisciplinary Mathematics 21(2):279–286
Pollard, Laura. (2014) When Marnie was there' an animated film, Studio Ghibli. Director: Hiromasa Yonebayashi, film written by Keiko Niwa, Hiromasa Yonebayashi Masashi Ando, released in UK 2016. Infant Observation, 2016, 19(3):255–258
Shibo S. (2018) Combination and research of two-dimensional animated short films and H5 viral marketing. IPPTA: Quarterly Journal of Indian Pulp and Paper Technical Association, 30(6):166–173.
Arevalo J, Solorio T, Montes-y-Gómez M et al (2020) Gated multimodal networks. Neural Comput & Applic 32:10209–10228
Owen HE, Halberstadt J, Carr EW et al (2016) Johnny depp, reconsidered: how category-relative processing fluency determines the appeal of gender ambiguity. PLoS ONE 11(2):e0146328
Tung VWS, Lee S, Hudson S (2019) The potential of anime for destination marketing: fantasies, otaku, and the kidult segment. Curr Issue Tour 22(11–15):1423–1436
Zheng Z, Zhang T, Yao J et al (2016) Flexible, transparent and ultra-broadband photodetector based on large-area WSe2 film for wearable devices. Nanotechnology 27(22):225501
Napoli G, Vergori L (2018) Influence of the extrinsic curvature on two-dimensional nematic films. Phys Rev E 97(5):052705
Xu Z, Cheng C, Sugumaran V (2020) Big data analytics of crime prevention and control based on image processing upon cloud computing. J Surveill Secur Saf 1:16–33
Gillett A, Waugh D, Lawrence J et al (2016) Laser surface modification for the prevention of biofouling by infection causing Escherichia Coli. J Laser Appl 28(2):022503
Fizza K, Banerjee A, Mitra K et al (2021) QoE in IoT: a vision, survey and future directions. Discov Internet Things 1:4
Deng Y, Ma Z, Ren F et al (2019) Improved photoelectric performance of DSSCs based on TiO2 nanorod array/Ni-doped TiO2 compact layer composites film. J Solid State Electrochem 23(11):3031–3041
Eshed E, Bamberger M, Katsman A (2016) A spinodal decomposition model for the prediction of the glass-forming ability of ternary mg alloys. Metall and Mater Trans A 47(1):209–221
Kuzlu M, Fair C, Guler O (2021) Role of Artificial Intelligence in the Internet of Things (IoT) cybersecurity. Discov Internet Things 1:7
Mimura T, Katayama K, Shimizu T et al (2016) Formation of (111) orientation-controlled ferroelectric orthorhombic HfO2 thin films from solid phase via annealing. Appl Phys Lett 109(5):052903
Cheng XQ, Konstas K, Doherty CM et al (2017) Hyper-cross-linked additives that impede aging and enhance permeability in thin polyacetylene films for organic solvent nanofiltration. ACS Appl Mater Interfaces 9(16):14401–14408
Xie Q, Wosu SN (2016) The Effect of TaC reinforcement on the oxidation resistance of CNTs/SiC CMCs. J Mater Eng Perform 25(3):874–883
Alam MS, Siddiq AM, Mandal AB (2016) Thermodynamic and micellization studies of a cationic gemini surfactant 16-6-16: Influence of ascorbic acid and temperature. Colloid J 78(1):9–14
Acknowledgements
This work was supported by the 2016 Hunan Province Philosophy and Social Science General Project "Regional Cultural Traits and Applied Research on Public Transport in Changzhutan Urban Agglomerations" (Project No. 16YBA119).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no potential competing interests in our paper. And all authors have seen the manuscript and approved to submit to your journal. We confirm that the content of the manuscript has not been published or submitted for publication elsewhere.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, P., Zhu, Y. & Cai, S. Innovative research on the visual performance of image two-dimensional animation film based on deep neural network. Neural Comput & Applic 34, 2719–2728 (2022). https://doi.org/10.1007/s00521-021-06140-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06140-1