3D Face Model Estimation based on Similarity Transform using Differential Evolution Optimization

• DOI: 10.1016/j.procs.2015.06.072
• Publication Date: 2015-08-21T06:24:18Z
• Authors: K. Punnam Chandar; T. Satya Savithri
• Keywords: Differential Evolution; Similarity (geometry); Feature (linguistics)

3D Face model reconstruction from a single 2D image is fundamentally important for face recognition because the invariant to changes of viewpoint, illumination, background clutter and occlusions. In this paper, an efficient Reconstruction algorithm proposed based on multi-view images human similarity transform measurements. algorithm, pose depth estimation feature points respective considered as optimization problem solved using Differential Evolution optimization. Further different strategies differential evolution are used optimize results compared. Simple integration method improve accuracy structure face, when more than one non-frontal-view available. Furthermore, Pearson Linear Correlation computed show efficiency approach. Experimental Head Pose Bosphorus databases demonstrate feasibility methods.