Abstract
We present a system for accurate real-time 3D face verification using a low-quality consumer depth camera. To verify the identity of a subject, we built a high-quality reference model offline by fitting a 3D morphable model to a sequence of low-quality depth images. At runtime, we compare the similarity between the reference model and a single depth image by aligning the model to the image and measuring differences between every point on the two facial surfaces. The model and the image will not match exactly due to sensor noise, occlusions, as well as changes in expression, hairstyle, and eye-wear; therefore, we leverage a data driven approach to determine whether or not the model and the image match. We train a random decision forest to verify the identity of a subject where the point-to-point distances between the reference model and the depth image are used as input features to the classifier. Our approach runs in real-time and is designed to continuously authenticate a user as he/she uses his/her device. In addition, our proposed method outperforms existing 2D and 3D face verification methods on a benchmark data set.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 71-79 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781538664810 |
| DOIs | |
| State | Published - Dec 13 2018 |
| Event | 15th Conference on Computer and Robot Vision, CRV 2018 - Toronto, Canada Duration: May 9 2018 → May 11 2018 |
Publication series
| Name | Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018 |
|---|
Conference
| Conference | 15th Conference on Computer and Robot Vision, CRV 2018 |
|---|---|
| Country | Canada |
| City | Toronto |
| Period | 5/9/18 → 5/11/18 |
Fingerprint
Keywords
- 3D Computer Vision
- Depth Cameras
- Face Recognition
- Face Verification
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Vision and Pattern Recognition
Cite this
Real-time 3D face verification with a consumer depth camera. / Meyer, Gregory; Do, Minh N.
Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 71-79 8575738 (Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Real-time 3D face verification with a consumer depth camera
AU - Meyer, Gregory
AU - Do, Minh N
PY - 2018/12/13
Y1 - 2018/12/13
N2 - We present a system for accurate real-time 3D face verification using a low-quality consumer depth camera. To verify the identity of a subject, we built a high-quality reference model offline by fitting a 3D morphable model to a sequence of low-quality depth images. At runtime, we compare the similarity between the reference model and a single depth image by aligning the model to the image and measuring differences between every point on the two facial surfaces. The model and the image will not match exactly due to sensor noise, occlusions, as well as changes in expression, hairstyle, and eye-wear; therefore, we leverage a data driven approach to determine whether or not the model and the image match. We train a random decision forest to verify the identity of a subject where the point-to-point distances between the reference model and the depth image are used as input features to the classifier. Our approach runs in real-time and is designed to continuously authenticate a user as he/she uses his/her device. In addition, our proposed method outperforms existing 2D and 3D face verification methods on a benchmark data set.
AB - We present a system for accurate real-time 3D face verification using a low-quality consumer depth camera. To verify the identity of a subject, we built a high-quality reference model offline by fitting a 3D morphable model to a sequence of low-quality depth images. At runtime, we compare the similarity between the reference model and a single depth image by aligning the model to the image and measuring differences between every point on the two facial surfaces. The model and the image will not match exactly due to sensor noise, occlusions, as well as changes in expression, hairstyle, and eye-wear; therefore, we leverage a data driven approach to determine whether or not the model and the image match. We train a random decision forest to verify the identity of a subject where the point-to-point distances between the reference model and the depth image are used as input features to the classifier. Our approach runs in real-time and is designed to continuously authenticate a user as he/she uses his/her device. In addition, our proposed method outperforms existing 2D and 3D face verification methods on a benchmark data set.
KW - 3D Computer Vision
KW - Depth Cameras
KW - Face Recognition
KW - Face Verification
UR - http://www.scopus.com/inward/record.url?scp=85060520302&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060520302&partnerID=8YFLogxK
U2 - 10.1109/CRV.2018.00020
DO - 10.1109/CRV.2018.00020
M3 - Conference contribution
T3 - Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018
SP - 71
EP - 79
BT - Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018
PB - Institute of Electrical and Electronics Engineers Inc.
ER -