Kinship Verification

Kinship verification from facial images is a challenging problem in computer vision and research is going on in this area. In this system, we have used neighborhood repulsed metric learning (NRML) method for kinship verification. Motivated by the fact that interclass samples (without kinship relations) with higher similarity usually lie in a neighbourhood and are more easily misclassified than those with lower similarity. The proposed system uses this distance metric and classifies the test pair of images as kinship or nonkinship relation.