Feature Fusion and NRML Metric Learning for Facial Kinship Verification

Features extracted from facial images are used in various fields such as kinship verification. The verification system determines the kin or non-kin relation between a pair of by analysing their features. In this research, different texture and color features have been along with metric learning method, to verify for four relations father-son, father-daughter, mother-son mother-daughter. First, fusing effective features, NRML generate discriminative feature vector, then SVM classifier relations. To measure accuracy proposed KinFaceW-I KinFaceW-II databases used. results evaluations show that fusion methods able improve performance system. addition approach, effect extraction image blocks whole is investigated presented. indicate block form, can be improving final