期刊文献+

基于数字媒体技术的交互式三维脸部表情动画合成方法研究 被引量:2

Research on Synthesis Method of Interactive 3D Facial Expression Animation Based on Digital Media Technology
下载PDF
导出
摘要 为了提高对脸部表情动画的合成能力,提出基于数字媒体技术的交互式三维脸部表情动画合成方法。首先,利用数字媒体技术构建三维脸部表情动画图像采集模型,在分析其中的三维信息特征后,对图像特征进行合成预处理;然后,结合模糊信息融合方法,实现对三维脸部表情信息的跟踪识别与视觉重建,最后,通过多维空间数据组合的方法完成交互式三维脸部表情动画合成。仿真结果表明,该方法得到的输出结果的视觉表达能力较好、特征辨识度较高。 In order to improve the ability of facial expression animation synthesis,synthesis method of interactive 3D facial expression animation based on digital media technology is proposed.Firstly,a 3D facial expression animation image acquisition model is constructed by digital media technology.After analyzing the 3D information features,the image features are synthesized and preprocessed.Then the fuzzy information fusion method is used to realize the tracking recognition and visual reconstruction of 3D facial expression information,and the interactive 3D facial expression animation synthesis is completed by the combination of multi-dimensional data.Simulation results show that the output have good visual expression ability and high feature identification with this method.
作者 张帅 Zhang Shuai(Chuzhou University,Chuzhou,Anhui 239000,China)
机构地区 滁州学院
出处 《黑龙江工业学院学报(综合版)》 2021年第11期74-78,共5页 Journal of Heilongjiang University of Technology(Comprehensive Edition)
基金 滁州学院科研启动基金项目(项目编号:2020qd31) 安徽省高校自然科学基金重点项目(项目编号:KJ2020A0717)。
关键词 数字媒体技术 交互式 三维脸部表情动画 图像合成 digital media technology interactivity 3D facial expression animation image synthesis
  • 相关文献

参考文献8

二级参考文献38

  • 1淦文燕,李德毅,王建民.一种基于数据场的层次聚类方法[J].电子学报,2006,34(2):258-262. 被引量:83
  • 2HE L, GAO F, HOU W, et al. Objective image quality assessment: A survey[J]. International Journal of Computer Mathematics, 2014, 91(11): 2374-2388. doi: 10.1080/ 00207160.2013.816415.
  • 3WANG Zand BOVIK A C. Reduced-and no-reference image quality assessment[J]. IEEE Signal Processing Magazine, 2011, 28(6): 29-40. doi: 10.1109/MSP.2011.942471.
  • 4HU A, ZHANG R, YIN D, et al. Image quality assessment using a SVD-based structural projection[J]. Signal Processing: Image Communication, 2014, 29(3): 293-302. doi: 10.1016/ j.image.2014.01.007.
  • 5HYVARINEN A, HURRI J, and HOYER P O. Natural Image Statistics: A Probabilistic Approach to Early Computational Vision[M]. US, Springer Science & Business Media, 2009, Chap 4. doi: 10.1007/978-1-84882-491-1.
  • 6HORE A and ZIOU D. Image quality metrics: PSNR vs. SSIM[C]. 2010 20th International Conference on Pattern Recognition (ICPR), Istanbul, Turkey, 2010: 2366-2369. doi: 10.1109/ICPR.2010.579.
  • 7GAO X, LU W, LI X, et al. Wavelet-based contourlet in quality evaluation of digital images[J]. Neurocomputing, 2008, 72(1): 378-385. doi: 10.1016/j.neucom.2007.12.031.
  • 8DING Y, DAI H, and WANG S. Image quality assessment scheme with topographic independent components analysis for sparse feature extraction[J]. Electronics Letters, 2014, 50(7): 509-510. doi: 10.1049/e1.2013.4298.
  • 9LUO C, WANG Y, DING Y, et al. Image quality assessment based on independent component analysis[C]. IEEE 2014 12th International Conference on. Signal Processing (ICSP), Hangzhou, China, 2014: 922-927. doi: 10.1109/ICOSP.2014. 7015139.
  • 10MANIKANDAN L C and SELVAKUMAR R K. A new survey on block matching algorithms in video coding[J]. International Journal of Engineering Research, 2014, 3(2): 121-125.

共引文献88

同被引文献16

引证文献2

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部