苏科华
Supervisor of Doctorate Candidates
Supervisor of Master's Candidates
E-Mail:
Date of Employment:2008-11-02
School/Department:计算机学院
Education Level:研究生毕业
Business Address:D203
Gender:Male
Contact Information:13517299596
Status:Employed
Discipline:Computer Applications Technology
Communications and Information Systems
Other specialties in Software Engineering
Cyberspace Security
Hits:
Impact Factor:2.0
DOI number:10.1002/cpe.4654
Affiliation of Author(s):WILEY
Journal:CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
Place of Publication:111 RIVER ST, HOBOKEN 07030-5774, NJ
Key Words:conformal mapping;harmonic energy;landmark constraints;non-linear diffusion;surface registration
Abstract:Recently, 3D facial datasets are more easily available, and at the same time, the research of 3D face becomes more and more important. One of the most important research fields is 3D face registration, which plays an important role in face recognition, face shape analysis, and face animation. However, one of the most challenging issues in 3D face registration is to obtain a unique mapping for faces with different expression and landmark constraints. In this paper, we propose a novel conformal mapping algorithm to deal with the 3D face registration. Besides, the calculation is about harmonic energy, which makes our method applicable to low-quality meshes. We begin with a harmonic mapping, then minimize the harmonic energy by a specific boundary condition on surfaces, and to obtain the conformal mapping, finally, we use a landmark-constrained surface registration algorithm to register faces. Numerical experiments on various surfaces demonstrate the efficiency and robustness of our method.
Co-author:Zhang Jialing,Li Yinghua
First Author:Qian Kun
Indexed by:Journal paper
Correspondence Author:Su Kehua
Document Type:J
Volume:30
Issue:22
ISSN No.:1532-0626
Translation or Not:no
Date of Publication:2018-11-15
Included Journals:SCI、EI
苏科华,男,武汉大学计算机学院教授、博导;武汉大学科技成果转化中心(技术转移中心)副主任。研究主要集中在最优传输(Optimal Transport)领域,它是研究概率测度间最优变换的一类优化问题。在计算机图形学、机器视觉、人工智能、医学图像处理等领域有着广泛的应用。本人主要研究最优传输的几何计算理论和高效算法,并将其应用于网格保测参数化、三维场景优化、智能烧伤评估和卫星互联网任务优化中。主持包括国家自然科学基金、中央军科委、航天5院、华为公司等20多个项目支持,发表论文50余篇,获批发明专利10余项。为CCF计算机辅助设计与图形学(CAD/CG)和虚拟现实与可视化(TCVRV)专委会的执行委员。