This project investigates bias in automatic facial recognition (FR). Specifically, subjects are grouped into predefined subgroups based on gender, ethnicity, and age. We propose a novel image collection called Balanced Faces in the Wild (BFW), which is balanced across eight subgroups (i.e., 800 face images of 100 subjects, each with 25 face samples).

Categories:
85 Views

Deep facial features with identity generated from CelebA dataset using facenet network (128 real-valued features). Dataset contains: - full dataset- training dataset- validation datasetLink to CelebA dataset: http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html

Categories:
255 Views