Face anti-spoofing based on multi-model features
As face anti-spoofing is becoming a more and more popular technology, it is important to protect face recognition systems from the attack. There are many available face anti-spoofing benchmark datasets used for face anti-spoofing this recently. In this thesis, I firstly introduce some basic knowl...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143107 |
| _version_ | 1811678193379180544 |
|---|---|
| author | Lei, Han |
| author2 | Huang Guangbin |
| author_facet | Huang Guangbin Lei, Han |
| author_sort | Lei, Han |
| collection | NTU |
| description | As face anti-spoofing is becoming a more and more popular technology, it is important
to protect face recognition systems from the attack. There are many available face anti-spoofing
benchmark datasets used for face anti-spoofing this recently. In this thesis, I
firstly introduce some basic knowledge and developing history of face recognition
technology. At the moment, face recognition technology is wildly used in various
fields, such as railway security system, education and smart city construction.
However, face recognition systems currently are easy to be attacked by various of
methods, including photo attack, video clips and two dimension or three-dimension
mask, causing the recognition result more unreliable. In order to solve this problem,
face anti-spoofing becomes a hot topic. In this thesis, we describe various methods of
anti-spoofing methods, including Color Texture, Patch and Depth-Based CNNs, DMD
+ LBP, Pulse + texture, Deep Pulse and Depth, Micro-texture + SSD and De-Spoofing.
After that, we analyze and compare the numbers and characteristics of different face
anti-spoofing data sets. We do improvement to the multi-modal fusion method to better
combine these four chosen features: RGB, Depth, IR and HSV. They are modaldependent
features and are re-weighted in order to choose informative channel features
and at the same time suppress the useless ones. Finally, we conduct experiments on
CASIA-SURF which is current the most complete multi-modal dataset in the world.
The results show that the TPR of squeeze and excitation fusion method are 7.6%, 48.2%
and 39.0%, which is better than halfway fusion method with the FPR=0.01, 0.001 and
0.0001, respectively. |
| first_indexed | 2024-10-01T02:49:22Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/143107 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:49:22Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1431072023-07-04T16:59:54Z Face anti-spoofing based on multi-model features Lei, Han Huang Guangbin School of Electrical and Electronic Engineering EGBHuang@ntu.edu.sg Engineering::Electrical and electronic engineering As face anti-spoofing is becoming a more and more popular technology, it is important to protect face recognition systems from the attack. There are many available face anti-spoofing benchmark datasets used for face anti-spoofing this recently. In this thesis, I firstly introduce some basic knowledge and developing history of face recognition technology. At the moment, face recognition technology is wildly used in various fields, such as railway security system, education and smart city construction. However, face recognition systems currently are easy to be attacked by various of methods, including photo attack, video clips and two dimension or three-dimension mask, causing the recognition result more unreliable. In order to solve this problem, face anti-spoofing becomes a hot topic. In this thesis, we describe various methods of anti-spoofing methods, including Color Texture, Patch and Depth-Based CNNs, DMD + LBP, Pulse + texture, Deep Pulse and Depth, Micro-texture + SSD and De-Spoofing. After that, we analyze and compare the numbers and characteristics of different face anti-spoofing data sets. We do improvement to the multi-modal fusion method to better combine these four chosen features: RGB, Depth, IR and HSV. They are modaldependent features and are re-weighted in order to choose informative channel features and at the same time suppress the useless ones. Finally, we conduct experiments on CASIA-SURF which is current the most complete multi-modal dataset in the world. The results show that the TPR of squeeze and excitation fusion method are 7.6%, 48.2% and 39.0%, which is better than halfway fusion method with the FPR=0.01, 0.001 and 0.0001, respectively. Master of Science (Communications Engineering) 2020-08-03T06:05:29Z 2020-08-03T06:05:29Z 2020 Thesis-Master by Coursework https://hdl.handle.net/10356/143107 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Lei, Han Face anti-spoofing based on multi-model features |
| title | Face anti-spoofing based on multi-model features |
| title_full | Face anti-spoofing based on multi-model features |
| title_fullStr | Face anti-spoofing based on multi-model features |
| title_full_unstemmed | Face anti-spoofing based on multi-model features |
| title_short | Face anti-spoofing based on multi-model features |
| title_sort | face anti spoofing based on multi model features |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/143107 |
| work_keys_str_mv | AT leihan faceantispoofingbasedonmultimodelfeatures |