CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification

Abstract

Facial verification is a core problem studied by researchers in computer vision. Recently published one-to-one comparison models have successfully achieved accuracy results that surpass the abilities of humans. A natural extension to the one-to-one facial verification problem is a one-to-many classification. In this abstract, we present our exploration of different methods of performing one-to-many facial verification using low-resolution images. The CSEye model introduces a direct comparison between the features extracted from each of the candidate images and the suspect before performing the classification task. Initial experiments using 10-to-1 comparisons of faces from the Labelled Faces of the Wild dataset yield promising results.

Cite

Text

Dharamshi and Zou. "CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019933

Markdown

[Dharamshi and Zou. "CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/dharamshi2019aaai-cseye/) doi:10.1609/AAAI.V33I01.33019933

BibTeX

@inproceedings{dharamshi2019aaai-cseye,
  title     = {{CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification}},
  author    = {Dharamshi, Ameer and Zou, Rosie Yuyan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9933-9934},
  doi       = {10.1609/AAAI.V33I01.33019933},
  url       = {https://mlanthology.org/aaai/2019/dharamshi2019aaai-cseye/}
}