Header menu link for other important links
Feature Based Transfer Learning for Kinship Verification
Published in Springer Science and Business Media Deutschland GmbH
Volume: 267
Pages: 395 - 400
Kinship verification based on facial images is a recent and challenging problem in computer vision and machine learning. It has many real-world potential applications including tracing of missing children cases, social media image analysis, and image annotation. The existing methods do not focus on probability distribution differences between kinship facial images; that is why the performance of these methods is poor. The deep learning methods required a large amount of data. Practically, parents and their children share common features. To take into account this transfer learning based framework is proposed. The extracted hand-crafted features are given to a transfer learning framework that transfers the knowledge acquired from facial images of parents to children and vice versa. We evaluated the proposed methods on standard kinship datasets and experimental results showed that the proposed method outperforms in terms of accuracy and computational efficiency as compared to state of art methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About the journal
JournalSmart Innovation, Systems and Technologies
PublisherSpringer Science and Business Media Deutschland GmbH
Open AccessNo