Book ChapterDOI
FamilyGAN: Generating Kin Face Images Using Generative Adversarial Networks
Raunak Sinha,Mayank Vatsa,Richa Singh +2 more
- pp 297-311
Reads0
Chats0
TLDR
In this article, a GAN-based approach was proposed to generate kin-images using Generative Adversarial Learning (GAN) for multiple kin-relations, such as parent-child and siblings.Abstract:
Automatic kinship verification using face images involves analyzing features and computing similarities between two input images to establish kin-relationship. It has gained significant interest from the research community and several approaches including deep learning architectures are proposed. One of the law enforcement applications of kinship analysis involves predicting the kin image given an input image. In other words, the question posed here is: “given an input image, can we generate a kin-image?” This paper attempts to generate kin-images using Generative Adversarial Learning for multiple kin-relations. The proposed FamilyGAN model incorporates three information, kin-gender, kinship loss, and reconstruction loss, in a GAN model to generate kin images. FamilyGAN is the first model capable of generating kin-images for multiple relations such as parent-child and siblings from a single model. On the WVU Kinship Video database, the proposed model shows very promising results for generating kin images. Experimental results show 71.34% kinship verification accuracy using the images generated via FamilyGAN.read more
Citations
More filters
Journal ArticleDOI
Facial Kinship Verification: A Comprehensive Review and Outlook
TL;DR: A comprehensive review of the state-of-the-art methods for Facial Kinship Verification (FKV) can be found in this paper , where the authors identify gaps in current research and discuss potential future research directions.
Book ChapterDOI
KinStyle: A Strong Baseline Photorealistic Kinship Face Synthesis with an Optimized StyleGAN Encoder
Li-Chen Cheng,Shu-Chuan Hsu,Pin-Hua Lee,Hsiu-Chieh Lee,Chengzhi Lin,Jun-Cheng Chen,Chih-Yu Wang +6 more
TL;DR: In this paper , the authors leverage the pre-trained state-of-the-art face synthesis model, StyleGAN2, for kinship face synthesis, which can handle large age, gender and other attribute variations between the parents and their children.
References
More filters
Journal ArticleDOI
Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos
TL;DR: This research proposes a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm AutoEncoder (SMNAE), which introduces class-specific sparsity in the weight matrix.
Proceedings ArticleDOI
Kinshipgan: Synthesizing of Kinship Faces from Family Photos by Regularizing a Deep Face Network
Savas Ozkan,Akin Ozkan +1 more
TL;DR: A kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo and adapt cycle-domain transformation to attain a more stable results is proposed.
Book ChapterDOI
Kinship Identification Through Joint Learning Using Kinship Verification Ensembles
Wei Wang,Shaodi You,Theo Gevers +2 more
TL;DR: In this article, the context between different kinship types is considered in the context of kinship verification. But the authors do not consider the relation between different types of kinships.
Journal ArticleDOI
GANKIN: generating Kin faces using disentangled GAN
TL;DR: This study presents a new method to predict and generate a kin face using parents’ faces, i.e. Tri-subject prediction or two-to-one prediction by using a modular pipeline of unconditional smaller models.
Posted Content
SelfKin: Self Adjusted Deep Model For Kinship Verification.
Eran Dahan,Yosi Keller +1 more
TL;DR: A novel self-learning deep model, which learns the essential features from different faces, which wins the Recognize Families In the Wild challenge and obtains state-of-the-art results.
Related Papers (5)
Multi-scale deep relational reasoning for facial kinship verification
Haibin Yan,Chaohui Song +1 more