LDA algorithm and its application to face recognition

摘要: Linear Discriminant Analysis(LDA) is a linear feature extracting method using Fisher's criterion in face recognition.The main challenge of LDA that its transformation matrix can not be computed directly;consequently,the discriminant vectors become very complicated,for the cases when number training samples less than dimensionality space.In this paper,a new proposed modified criterion.Experiments are conducted ORL database to present superior performance method,particularly for small.