一种应用于小样本人脸识别的2DLPP算法

2DLPP:A novel method for small sample size face recognition

LPP是一种局部特征提取算法,被广泛应用于模式识别中,然而在人脸识别中会遭遇小样本问题,为解决这个问题,提出了一种应用于人脸识别的二维LPP算法,直接对图像矩阵进行特征提取,既解决了传统LPP算法的小样本问题,又加快了特征提取速度。YALE人脸库和Extended Yale B人脸库上的实验结果表明2DPP具有较高的识别率,对光照、姿态的变化具有一定的鲁棒性。

LPP is a local feature extraction method,which can detect the intrinsic manifold structure of data,In face recognition,it often encounters the small sample size problem.To solve that,we propose a two-dimensional locality preserving projections（2DLPP） based directly on 2D image matrices for face recognition.Experiment on Yale and Extended YaleB face database show that 2DLPP achieves better face recognition performance than LPP.