RECORD
Face Beneath the Ink: Synthetic Data and Tattoo Removal with Application to Face Recognition
Computer Vision and Pattern Recognition · Submitted 10 Feb 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Additionally, we show that it is possible to improve face recognition accuracy by using the proposed deep learning-based tattoo removal before extracting and comparing facial features.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Systems that analyse faces have seen significant improvements in recent years and are today used in numerous application scenarios. However, these systems have been found to be negatively affected by facial alterations such as tattoos. To better understand and mitigate the effect of facial tattoos in facial analysis systems, large datasets of images of individuals with and without tattoos are needed. To this end, we propose a generator for automatically adding realistic tattoos to facial images. Moreover, we demonstrate the feasibility of the generation by using a deep learning-based model for removing tattoos from face images. The experimental results show that it is possible to remove facial tattoos from real images without degrading the quality of the image. Additionally, we show that it is possible to improve face recognition accuracy by using the proposed deep learning-based tattoo removal before extracting and comparing facial features.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Systems that analyse faces have seen significant improvements in recent years and are today used in numerous application scenarios. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, these systems have been found to be negatively affected by facial alterations such as tattoos. | background 0.95 | 0.17 | 0.02 | asserted 1.00 |
| s2 | To better understand and mitigate the effect of facial tattoos in facial analysis systems, large datasets of images of individuals with and without tattoos are needed. | gap 0.96 | 0.07 | 0.04 | asserted 0.98 |
| s3 | To this end, we propose a generator for automatically adding realistic tattoos to facial images. | contribution 0.84 | 0.89 | 0.04 | asserted 0.95 |
| s4 | Moreover, we demonstrate the feasibility of the generation by using a deep learning-based model for removing tattoos from face images. | contribution 0.62 | 0.93 | 0.07 | asserted 0.99 |
| s5 | The experimental results show that it is possible to remove facial tattoos from real images without degrading the quality of the image. | result 1.00 | 0.94 | 0.27 | asserted 0.59 |
| s6 | Additionally, we show that it is possible to improve face recognition accuracy by using the proposed deep learning-based tattoo removal before extracting and comparing facial features. | result 0.98 | 0.95 | 0.52 | asserted 0.65 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Systems that analyse faces have seen significant improvements in recent years and are today used in numerous application scenarios. However, these systems have been found to be negatively affected by facial alterations such as tattoos. To better understand and mitigate the effect of facial tattoos in facial analysis systems, large datasets of images of individuals with and without tattoos are needed. To this end, we propose a generator for automatically adding realistic tattoos to facial images. Moreover, we demonstrate the feasibility of the generation by using a deep learning-based model for removing tattoos from face images. The experimental results show that it is possible to remove facial tattoos from real images without degrading the quality of the image. Additionally, we show that it is possible to improve face recognition accuracy by using the proposed deep learning-based tattoo removal before extracting and comparing facial features.
Human review
How the literature uses it
1 arXiv paper cite this in 2 sentences
What it cites
Uses the method or tool of 1 paper
-
The loss function is a combination of feature loss (perceptual loss) from [ref] , gram matrix style loss [ref] , and pixel (L1) loss.
A Neural Algorithm of Artistic Style · Models · 1.00
Cites as background 1 paper
-
In addition to the face, some research has also been conducted for other biometric modalities, fingerprint [ref] and iris [ref] .
SynCoLFinGer: Synthetic Contactless Fingerprint Generator · Synthetic Data Generation for Face Analysis · 0.85
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.