Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems
Face recognition is widely acknowledged to be a very complex visual task for both humans and computers. Previous studies which analyze robustness of facial recognition systems have revealed that the ability to recognize faces becomes worse as the blur levels of face images increases, and that natura...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/147313 |
| _version_ | 1826211744596361216 |
|---|---|
| author | Verma, Ashika |
| author2 | Sinha, Pawan |
| author_facet | Sinha, Pawan Verma, Ashika |
| author_sort | Verma, Ashika |
| collection | MIT |
| description | Face recognition is widely acknowledged to be a very complex visual task for both humans and computers. Previous studies which analyze robustness of facial recognition systems have revealed that the ability to recognize faces becomes worse as the blur levels of face images increases, and that naturalistic color is important for facial recognition at high blur levels. Additionally, previous studies of current state of the art face recognition technologies have found bias in face recognition amongst different races, resulting in a worse recognition performance for people of color. In this study, we evaluate the performance and robustness of a current state-of-the-art facial recognition neural network architecture (ResNet-101) trained on an augmented facial identity dataset (Augmented Casia Webface) and perform a thorough comparison between White, Black and East Asian identities. We created a full-color, a grayscale and many hue-shifted datasets and then Gaussian blurred each dataset at different intensities and compared how AI systems perform relative to humans and amongst the different races. |
| first_indexed | 2024-09-23T15:10:45Z |
| format | Thesis |
| id | mit-1721.1/147313 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T15:10:45Z |
| publishDate | 2023 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1473132023-01-20T03:11:22Z Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems Verma, Ashika Sinha, Pawan Keane, Kyle Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Face recognition is widely acknowledged to be a very complex visual task for both humans and computers. Previous studies which analyze robustness of facial recognition systems have revealed that the ability to recognize faces becomes worse as the blur levels of face images increases, and that naturalistic color is important for facial recognition at high blur levels. Additionally, previous studies of current state of the art face recognition technologies have found bias in face recognition amongst different races, resulting in a worse recognition performance for people of color. In this study, we evaluate the performance and robustness of a current state-of-the-art facial recognition neural network architecture (ResNet-101) trained on an augmented facial identity dataset (Augmented Casia Webface) and perform a thorough comparison between White, Black and East Asian identities. We created a full-color, a grayscale and many hue-shifted datasets and then Gaussian blurred each dataset at different intensities and compared how AI systems perform relative to humans and amongst the different races. M.Eng. 2023-01-19T18:44:50Z 2023-01-19T18:44:50Z 2022-09 2022-09-16T20:24:09.975Z Thesis https://hdl.handle.net/1721.1/147313 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Verma, Ashika Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title | Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title_full | Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title_fullStr | Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title_full_unstemmed | Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title_short | Transformation Tolerance and Demographic Robustness of Machine-based Face Recognition Systems |
| title_sort | transformation tolerance and demographic robustness of machine based face recognition systems |
| url | https://hdl.handle.net/1721.1/147313 |
| work_keys_str_mv | AT vermaashika transformationtoleranceanddemographicrobustnessofmachinebasedfacerecognitionsystems |