Abstract
Recent years, the methods to combine artificial intelligence technology with 3D image processing technology has become a hub for research in packaging design. Traditional 3D images are mostly produced by professional equipment, but this method is small in scope and high in cost, which does not meet the needs of most people. To solve the above problems, this study combines the mean shift algorithm with the confidence propagation algorithm, and obtains the confidence propagation-mean shift algorithm. In addition, the Lucascanard-confidence factor optical flow algorithm is improved by introducing the confidence factor to the Lucascanard-confidence factor optical flow algorithm. The research continues to combine the confidence propagation-mean shift algorithm with the Lucaskarnad-confidence factor optical flow algorithm to extract parallax maps and then synthesize 3D images. The results show that the iteration times and iteration time of the confidence propagation-mean shift algorithm are 9 times and 97.05 s, respectively. The number of parallax templates and the number of regions is 6 and 43 respectively. The confidence propagation-mean shift algorithm has 4 iterations, 36.8 s iteration time, 14 parallax templates and 65 regions in the category of portrait images. The accuracy of foreground depth, background depth and depth are 99.72, 99.87 and 99.80%, respectively, for the Lucas Kanard-confidence factor optical flow algorithm. In summary, the two algorithms proposed in this study have excellent performance, which can extract parallax map well and generate 3D image accurately, owning certain promotion value in the field of product packaging design.
Similar content being viewed by others
Abbreviations
- MS:
-
Mean shift
- BP:
-
Belief propagation
- CF:
-
Confidence factor
- LK:
-
Lucas kanade
- WS:
-
Watershed segmentation
- KCS:
-
K-means clustering segmentation
References
Sharma, S., Verma, K., Hardaha, P.: Implementation of artificial intelligence in agriculture. J Comput Cogn Eng 2(2), 155–162 (2023)
Ding, M.: Application of visual elements in product paper packaging design: an example of the “squirrel” pattern. J. Intell. Syst. 31(1), 104–112 (2022)
Connolly, J.D.: Food packaging: design: food package design companies vs graphic design generalist. Packag Strateg News: World Lead Inf Sour Packag Technol Business Market 38(19), 8–10 (2020)
Daraei, B., Shojaee, S., Hamzehei-Javaran, S.: Thermo-mechanical analysis of functionally graded material beams using micropolar theory and higher-order unified formulation. Arch. Appl. Mech. 93(1), 109–128 (2022)
Windrum, P., Haynes, M., Thompson, P.: Breaking the mirror: interface innovation and market capture by Japanese professional camera firms, 1955–1974. Ind. Corp. Chang. 28(5), 1029–1056 (2019)
Sun, X., Hu, T., Ma, L., Jin, W.: The encryption and decryption technology with chaotic iris and compressed sensing based on computer-generated holography. J. Opt. 51(1), 124–132 (2022)
Jones, O., Stevenson, P.G., Hameka, S.C., Osborne, D.A., Taylor, P.D., Spencer, M.J.S.: Using 3D printing to visualize 2D chromatograms and NMR spectra for the classroom. J. Chem. Educ. 98(3), 1024–1030 (2021)
Huo, J., Yu, X.: Three-dimensional mechanical parts reconstruction technology based on two-dimensional image. Int. J. Adv. Rob. Syst. 17(2), 36–46 (2020)
Chen, F., Muhammad, K., Wang, S.H.: Three-dimensional reconstruction of CT image features based on multi-threaded deep learning calculation. Pattern Recogn. Lett. 136, 309–315 (2020)
Chen, Y., Zou, W., Sharma, A.: A detailed study on graphic design method based on 3D virtual vision technology. Recent Adv Electr Electron Eng (Formerly Recent Patents Electr Electron Eng) 14(6), 627–637 (2021)
Chao, H., Li, Y., Yao, W., Han, X., Wang, R.: Crystal-modeler: A tool for geometric analysis and three-dimensional modeling of crystal forms based on rectangular coordinates in space. Earth Sci. Inf. 16(1), 675–693 (2022)
Li, C., Monno, Y., Okutomi, M.: Pro-Cam SSfM: projector–camera system for structure and spectral reflectance from motion. Visual Comput 39(4), 1651–1666 (2022)
Shi, Q., Yin, S., Wang, K., Teng, L., Li, H.: Multichannel convolutional neural network-based fuzzy active contour model for medical image segmentation. Evol. Syst. 13(4), 535–549 (2022)
Liu, X., Zhang, Y., Jing, H., Wang, L., Zhao, S.: Ore image segmentation method using U-net and res_unet convolutional networks. RSC Adv. 10(16), 9396–9406 (2020)
Ji, Y., Jiang, X.: Active contour model for image segmentation based on salient fitting energy. Int. J. Inf. Commun. Technol. 19(2), 219–230 (2021)
Li, Y., Cao, G., Wang, T., Cui, Q., Wang, B.: A novel local region-based active contour model for image segmentation using Bayes theorem. Inf. Sci. 506, 443–456 (2020)
Biswas, S., Hazra, R.: Active contours driven by modified LoG energy term and optimised penalty term for image segmentation. IET Image Proc. 14(13), 3232–3242 (2020)
Li, X., Li, X., Yang, G.: A novelty harmony search algorithm of image segmentation for multilevel thresholding using learning experience and search space constraints. Multimed Tools Appl 82(1), 703–723 (2023)
Turčičová, M., Mandel, J., Eben, K.: Score matching filters for Gaussian Markov random fields with a linear model of the precision matrix. Found Data Sci 3(4), 793–824 (2021)
Shi, H., Ji, L., Liu, S., Wang, K., Hu, X.: Collusive anomalies detection based on collaborative markov random field. Intell Data Anal 26(6), 1469–1485 (2022)
Yang, S.: Face feature tracking algorithm of aerobics athletes based on Kalman filter and mean shift. Int J Biomet 14(3/4), 394–407 (2022)
Endo, K., Ambo, T., Saito, Y., Nonomura, T., Chen, L., Asai, K.: Proposal and verification of optical flow reformulation based on variational method for skin-friction-stress field estimation from unsteady oil film distribution. J. Visualization 2, 25 (2022)
Kikas, T., Inno, R., Ratnik, K., Rull, K., Laan, M.: C-allele of rs4769613 near FLT1 represents a high-confidence placental risk factor for preeclampsia. Hypertension 76(3), 884–891 (2020)
Funding
The research is supported by 2023 Shanghai Philosophy and social Science planning project, Research on innovation path and integration mechanism of high-quality development of Shanghai digital cultural creative industry under the background of artificial intelligence.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jin, X. Application of 3D image processing technology based on image segmentation in packaging design. Int J Interact Des Manuf (2023). https://doi.org/10.1007/s12008-023-01566-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12008-023-01566-4