Face recognition accuracy across demographics: Shining a light into the problem
We explore varying face recognition accuracy across demographic groups as a
phenomenon partly caused by differences in face illumination. We observe that for a …
phenomenon partly caused by differences in face illumination. We observe that for a …
Our deep cnn face matchers have developed achromatopsia
Modern deep CNN face matchers are trained on datasets containing" color" images. We
show that such matchers achieve essentially the same accuracy on color images when …
show that such matchers achieve essentially the same accuracy on color images when …
Beard segmentation and recognition bias
A person's facial hairstyle, such as presence and size of beard, can significantly impact face
recognition accuracy. There are publicly-available deep networks that achieve reasonable …
recognition accuracy. There are publicly-available deep networks that achieve reasonable …
Facial hair area in face recognition across demographics: Small size, big effect
Observed variations in face recognition accuracy across demographics, often viewed as"
bias", have motivated research into the causes of such variations. Variations in facial …
bias", have motivated research into the causes of such variations. Variations in facial …
Consistency and accuracy of celeba attribute values
We report the first systematic analysis of the experimental foundations of facial attribute
classification. Two annotators independently assigning attribute values shows that only 12 of …
classification. Two annotators independently assigning attribute values shows that only 12 of …
What Should Be Balanced in a" Balanced" Face Recognition Dataset?
The issue of demographic disparities in face recognition accuracy has attracted increasing
attention in recent years. Various face image datasets have been proposed as' …
attention in recent years. Various face image datasets have been proposed as' …
Hairmony: Fairness-aware hairstyle classification
We present a method for prediction of a person's hairstyle from a single image. Despite
growing use cases in user digitization and enrollment for virtual experiences, available …
growing use cases in user digitization and enrollment for virtual experiences, available …
Can the accuracy bias by facial hairstyle be reduced through balancing the training data?
Appearance of a face can be greatly altered by growing a beard and mustache. The facial
hairstyles in a pair of images can cause marked changes to the impostor distribution and the …
hairstyles in a pair of images can cause marked changes to the impostor distribution and the …
Impact of Blur and Resolution on Demographic Disparities in 1-to-Many Facial Identification
Most studies to date that have examined demographic variations in face recognition
accuracy have analyzed 1-to-1 matching accuracy, using images that could be described …
accuracy have analyzed 1-to-1 matching accuracy, using images that could be described …
Analyzing the Impact of Demographic and Operational Variables on 1-to-Many Face ID Search
Concerns related to the proliferation of automated face recognition technology with the intent
of solving or preventing crimes continue to mount. The technology being implicated in …
of solving or preventing crimes continue to mount. The technology being implicated in …