基于稀疏表示与人脸结构的人脸幻构技术研究

Face Animation Technology Based on Sparse Representation and Face Structure

虽然基于稀疏表示的方法重构人脸图像有着样本库需求小的优点,同时对于平滑区域的恢复也有很好的效果,但是人脸成分以及轮廓边缘细节仍然较为模糊。为了解决这一问题,本文提出了结合稀疏表示的梯度估计边缘优化方法,该方法利用样本库中高分辨率的人脸成分以及边缘梯度统计空间对低分辨率输入人脸进行细节恢复和边缘锐化。实验结果表明,该方法对人脸图像结构的细节恢复有较为理想的表现效果。

Although the reconstruction of face images based on sparse representation has the advantages of small sample base and good effect on the recovery of the smooth region,the face composition and the outline edge details are still relatively vague.In order to solve this problem,this paper proposes a gradient estimation edge optimization method combined with sparse representation,which uses high resolution face components and edge gradient statistical space in sample database to restore and sharpen the edges of low resolution input faces.Experimental results show that this method has a satisfactory effect on detail restoration of face image structure.