Abstract
Intelligent cartoon image generation is to generate an image corresponding to a given text through a certain pattern. However, the absent of proportion and position information of each objects directly affects the quality of output image. This paper focuses on the optimization of the layout based on MCMC method and Metropolis-Hastings Algorithm. The proportion and position of each cartoon characters compose into a state and optimized with Metropolis-Hasting method iteratively. Poisson image fusion method is used to make the images fusion area transition smooth to reduce synthetic trace. Experimental results show that the algorithm in this paper can generate cartoons images intelligently.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barnard K, Duygulu P, Forsyth D, De Freitas N, Blei DM, Jordan MI (2013) Matching words and pictures. Proc J Mach Learn Res 1107–1135
Fei-Fei L, Perona P (2005) A Bayesian hierarchical model for learning natural scene categories. In: IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society. https://doi.org/10.1109/CVPR
Meethon N, Huang HS, Speakman S et al (2013) Video annotation in a learning environment. Proc Am Soc Inform Sci Technol. https://doi.org/10.1002/meet.14504301175
Wang M, Hua XS, Hong R et al (2009) Unified video annotation via multigraph. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2009.2017400
Elliott D, Keller F (2013) Image description using visual dependency representations. In: Proceedings of EMNLP, pp 1292–1302
Gong Y, Wang L, Hodosh M, Hockenmaier J, Lazebnik S (2014) Improving image-sentence embeddings using large weakly annotated photo collections. 529–545. https://doi.org/10.1007/978-3-319-10593-2_35
Hastings WK (1970) Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57(1):97–109
Ping C, Ruo Xi X (2008) Metropolis-Hastings adaptive algorithm and its application. Syst Eng Theor Pract CNKI:SUN:XTLL.0. 15 January 2008
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, Y., Ying, D., Yin, K., Li, Z. (2021). Intelligent Cartoon Image Generation Based on Text Analysis and MCMC Algorithm. In: Zhao, P., Ye, Z., Xu, M., Yang, L., Zhang, L., Zhu, R. (eds) Advances in Graphic Communication, Printing and Packaging Technology and Materials. Lecture Notes in Electrical Engineering, vol 754. Springer, Singapore. https://doi.org/10.1007/978-981-16-0503-1_77
Download citation
DOI: https://doi.org/10.1007/978-981-16-0503-1_77
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0502-4
Online ISBN: 978-981-16-0503-1
eBook Packages: EngineeringEngineering (R0)