Nearest Centroid Neighbor Based Sparse Representation Classification for Finger Vein Recognition

In this paper, an efficient finger vein recognition algorithm based on the combination of the nearest centroid neighbor and sparse representation classification techniques (
${k}$
NCN-SRC) is presented. The previously proposed recognition algorithms are mainly based on distance computation. In the proposed method, the distance, as well as the spatial distribution, are considered to achieve a better recognition rate. The proposed method consists of two stages: first, the
${k}$
nearest neighbors of the test sample are selected based on the nearest centroid neighbor, and then, in the second stage, based on the selected number of closest nearest centroid neighbors (
${k}$
), the test sample is classified by sparse representation. Findings from the proposed method
${k}$
NCN-SRC demonstrated an increased recognition rate. This improvement can be attributed to the selection of the train samples, where the train samples are selected by considering the spatial and distance distribution. In addition, the complexity of SRC is reduced by reducing the number of train samples for the classification of the test sample by sparse representation and the processing speed of the proposed algorithm is significantly improved in comparison with the conventional SRC which is due to the reduced number of training samples. It can be concluded that the
${k}$
NCN-SRC classification method is efficient for finger vein recognition. An increase in the recognition rate of
3.35%
,
9.07%
,
20.23%
, and
0.81%
is obtained for the proposed
${k}$
NCN-SRC method in comparison with the conventional SRC for the four tested public finger vein databases.