3D reconstruction of human face based on an improved seeds-growing algorithm

作者：Da, Feipeng^*; Sui, Yihuan

来源：Machine Vision and Applications, 2011, 22(5): 879-887.

DOI：10.1007/s00138-010-0278-8

• 3D reconstruction
• Stereo vision
• Control points
• Piecewise dynamic programming
• Two-step matching

An algorithm based on binocular stereo vision is proposed to generate 3D (three-dimensional) dense points cloud model of the human face. A two-step matching strategy from sparse to dense is developed. Firstly, an improved seeds-growing algorithm is utilized to acquire sparse matching of high confidence. Secondly, based on the control points method and piecewise dynamic programming, the dense matching is completed. Experimental results show that the proposed algorithm can produce smooth and dense 3D points cloud model of the human face.

• 出版日期2011-9
• 单位东南大学