Towards computational models of kinship verification
By Ruogu Fang, Kevin D. Tang, Noah Snavely, Tsuhan Chen. 2010 IEEE International Conference on Image Processing, 2010
296 citations recorded by the source corpus.
We tackle the challenge of kinship verification using novel feature extraction and selection methods, automatically classifying pairs of face images as “related” or “unrelated” (in terms of kinship). First, we conducted a controlled online search to collect frontal face images of 150 pairs of public figures and celebrities, along with images of their parents or children. Next, we propose and evaluate a set of low-level image features for this classification problem. After selecting the most discriminative inherited facial features, we demonstrate a classification accuracy of 70.67% on a test set of image pairs using K-Nearest-Neighbors. Finally, we present an evaluation of human performance on this problem.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/a4dacc7845e29c436eaf5fa3efa24122618c74f0
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jie Zhou
- Jiwen Lu
- Christoffer Nellåker
- Andrew Zisserman
- Yap-Peng Tan
- Xiuzhuang Zhou
- Mitchell Dawson
- Trevor Darrell
In Computer Vision and Pattern Recognition
- Jie Zhou
- Jiwen Lu
- Dacheng Tao
- Andrew Zisserman
- Luc Van Gool
- Yi Yang
- Abhinav Kumar Gupta
- Xiaogang Wang
Citations in the corpus
- Neighborhood repulsed metric learning for kinship verification (2012, methodology): “[5] was the first attempt to tackle the challenge of kinship verification from facial images by using local facial feature extraction and selection.”
- From Same Photo: Cheating on Visual Kinship Challenges (2018, methodology): “Whereas on Cornell KinFace and TSKinFace, the best results were obtained by expanding the width and height of the images by 15%.”