On Discriminant Orientation Extraction Using GridLDA of Line Orientation Maps for Palmprint Identification

In this paper, we propose a novel Discriminant Orientation Representation, called DORIR, for palmprint identification. To extract DORIR feature, we proposed the algorithm which includes two main steps: (1) Palm line orientation map computation and (2) Discriminant feature extraction of the orientation field. In the first step, positive orientation and negative orientation maps are proposed as the input of two dimensional linear discriminant analysis (2D-LDA) for computing the class-separability features. In the second step, the grid-sampling based 2DLDA, called Grid-LDA, is used to remove redundant information of orientation maps and form a discriminant representation more suitable for palmprint identification. The experimental results on the two public databases of Hong Kong Polytechnic University (PolyU) show that proposed technique provides a very robust orientation representation for recognition and gets the best performance in comparison with other approaches in literature.