Face recognition based on stretchy regression
Kar‐Ann Toh · 2016
In this paper, an asymmetric kernel is proposed for extracting sparse features from two-dimensional visual face images for identity recognition. Essentially, the kernel consists of an inner product of two vectors where one of them has been raised to power terms element-wise. The impact of such a power term is suppression of less influential features where only relevant ones are used for estimation. Our experiments on public data sets show encouraging results regarding the potential of such an asymmetric kernel.