基于局部保持投影的人脸超分辨率方法研究

Research on Face Hallucination Based on Locality Preserving Projection

通常,人脸图像能够看作是嵌入到高维空间中的低维流形的点的集合。流形学习被用于很多降维方法中,局部保持投影(LPP)便是其中的一种。针对局部保持投影方法进行了研究,将局部保持投影算法融入到超分辨率方法中,并将其结合到人脸图像的复原上。介绍现有的基于LPP的人脸图像的超分辨率算法。

Generally face images may be visualized as points drawn on a low-dimensional manifold embedded in high-dimensional ambient space.Many dimensionality reduction techniques have been used to learn this manifold,LPP is one of them.Studies the theories of LPP,and applies it to super-resolution methods,combines it to face hallucinations.Introduces existing face hallucinations based LPP.