Palmprint recognition using directional line energy feature

Palm-lines, including the principal lines and wrinkles, can describe a palmprint clearly. This paper presents a novel approach of line feature extraction for palmprint recognition called the directional line energy feature (DLEF). The directional lines in different directions are first extracted using a set of directional line detectors. Then each directional line magnitude image is divided into several overlapped small grids and the magnitudes of the line points in these grids are used to compute the DLEF. A template-matching method based on Euclidean distance is adopted to measure the similarity of two DLEFs. Best results have been obtained when DLEFs with 6 different directions were employed. Accuracies of 97.92% and 97.5% are obtained by using the proposed approach in one-against-one matching and one-against-320 matching, respectively.