Kinship verification via ear images: A comparative study

Abstract

Kinship verification is crucial in daily life, especially in the legal field. Nowadays, most kinship verification methods utilize the advantages of human DNA and facial features. However, these methods require a lot of complex procedures, so they are unsuitable for real-time application. Therefore, researchers started to propose other promising biometrics, and the human ear is one of the most potential. The human ear has long been recognized as a robust biometric trait, comparable to others, such as face, iris, and fingerprint. This paper proposes using ear images to identify human kinship based on several well-known deep-learning networks. Moreover, an ear image set is presented to tackle the lack of a kinship-annotated dataset.