Local SVD based NIR face retrieval

Abstract

From last decade, local descriptor such as Local Binary Pattern (LBP) is accepted as a very prominent feature descriptor for characterizing the images such as faces. The performance of such descriptors depends upon the local relationship of the image. The local relationship of the image can be utilized in more discriminative and robust way after some preprocessing as compared to the original image. The preprocessed images in the form of 4 sub-bands (i.e. S, U, V, and D sub-bands) are obtained by applying the Singular Value Decomposition (SVD) over the original image. The local descriptors are computed over these sub-bands (mainly S sub-band) and termed as the SVD based local descriptors. The performance of four local descriptors over SVD sub-bands are tested for near-infrared face retrieval using PolyU-NIR and CASIA-NIR face databases, and compared with the results obtained using descriptors without SVD sub-band. The experimental results confirm the superiority of using S sub-band of SVD in terms of performance of the local descriptors over NIR face databases.