SelfKin: Self Adjusted Deep Model For Kinship Verification

TL;DR

This paper introduces SelfKin, a self-learning deep model for kinship verification that achieves state-of-the-art results and reduces network size, advancing biometric and face recognition applications.

Contribution

We propose a novel self-learning deep model for kinship verification that outperforms existing methods and is more efficient in network size.

Findings

Wins the RFIW2018 and FG2018 kinship verification challenges.

Achieves state-of-the-art accuracy in kinship verification.

Reduces network size by 50% without performance loss.

Abstract

One of the unsolved challenges in the field of biometrics and face recognition is Kinship Verification. This problem aims to understand if two people are family-related and how (sisters, brothers, etc.) Solving this problem can give rise to varied tasks and applications. In the area of homeland security (HLS) it is crucial to auto-detect if the person questioned is related to a wanted suspect, In the field of biometrics, kinship-verification can help to discriminate between families by photos and in the field of predicting or fashion it can help to predict an older or younger model of people faces. Lately, and with the advanced deep learning technology, this problem has gained focus from the research community in matters of data and research. In this article, we propose using a Deep Learning approach for solving the Kinship-Verification problem. Further, we offer a novel self-learning deep model, which learns the essential features from different faces. We show that our model wins the Recognize Families In the Wild(RFIW2018,FG2018) challenge and obtains state-of-the-art results. Moreover, we show that our proposed model can reduce the size of the network by half without loss in performance.