Kinship Measurement on Salient Facial Features

Humans have the capability to recognize family members. Phrases such as "John has his father's nose" or "Joe has his mother's eyes" are quite common. Motivated by this, we consider the following question: Is it possible to develop a method to extract the salient familial traits in face images for kinship recognition? If this idea works, an instrument may be invented to measure familial relationships. This computational kinship measurement might have a large impact in real applications, such as child adoptions, trafficking/smuggling of children, and finding missing children. The novel problem is related to but very different from traditional face recognition. It is more challenging than a typical face recognition problem since we need to find subtle features that are reliable across a large span of ages (e.g., grandfather and grandson) and sex difference (e.g., mother and son). A recently developed descriptor, i.e., DAISY, is adapted to our problem to represent the salient features, and a dynamic scheme is developed to stochastically combine familial traits. Experiments are performed on a database to show that our new approach can perform reasonably well for kinship verification. The encouraging result may inspire further research on this emerging problem.