An Identity Authentication Method Combining Liveness Detection and Face Recognition
In this study, an advanced Kinect sensor was adopted to acquire infrared radiation (IR) images for liveness detection. The proposed liveness detection method based on infrared radiation (IR) images can deal with face spoofs. Face pictures were acquired by a Kinect camera and converted into IR images...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/21/4733 |
| _version_ | 1798042159280029696 |
|---|---|
| author | Shuhua Liu Yu Song Mengyu Zhang Jianwei Zhao Shihao Yang Kun Hou |
| author_facet | Shuhua Liu Yu Song Mengyu Zhang Jianwei Zhao Shihao Yang Kun Hou |
| author_sort | Shuhua Liu |
| collection | DOAJ |
| description | In this study, an advanced Kinect sensor was adopted to acquire infrared radiation (IR) images for liveness detection. The proposed liveness detection method based on infrared radiation (IR) images can deal with face spoofs. Face pictures were acquired by a Kinect camera and converted into IR images. Feature extraction and classification were carried out by a deep neural network to distinguish between real individuals and face spoofs. IR images collected by the Kinect camera have depth information. Therefore, the IR pixels from live images have an evident hierarchical structure, while those from photos or videos have no evident hierarchical feature. Accordingly, two types of IR images were learned through the deep network to realize the identification of whether images were from live individuals. In comparison with other liveness detection cross-databases, our recognition accuracy was 99.8% and better than other algorithms. FaceNet is a face recognition model, and it is robust to occlusion, blur, illumination, and steering. We combined the liveness detection and FaceNet model for identity authentication. For improving the application of the authentication approach, we proposed two improved ways to run the FaceNet model. Experimental results showed that the combination of the proposed liveness detection and improved face recognition had a good recognition effect and can be used for identity authentication. |
| first_indexed | 2024-04-11T22:31:37Z |
| format | Article |
| id | doaj.art-f4b31dd5e9f04753b7d4cce40f320219 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:31:37Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f4b31dd5e9f04753b7d4cce40f3202192022-12-22T03:59:22ZengMDPI AGSensors1424-82202019-10-011921473310.3390/s19214733s19214733An Identity Authentication Method Combining Liveness Detection and Face RecognitionShuhua Liu0Yu Song1Mengyu Zhang2Jianwei Zhao3Shihao Yang4Kun Hou5School of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun 130117, ChinaIn this study, an advanced Kinect sensor was adopted to acquire infrared radiation (IR) images for liveness detection. The proposed liveness detection method based on infrared radiation (IR) images can deal with face spoofs. Face pictures were acquired by a Kinect camera and converted into IR images. Feature extraction and classification were carried out by a deep neural network to distinguish between real individuals and face spoofs. IR images collected by the Kinect camera have depth information. Therefore, the IR pixels from live images have an evident hierarchical structure, while those from photos or videos have no evident hierarchical feature. Accordingly, two types of IR images were learned through the deep network to realize the identification of whether images were from live individuals. In comparison with other liveness detection cross-databases, our recognition accuracy was 99.8% and better than other algorithms. FaceNet is a face recognition model, and it is robust to occlusion, blur, illumination, and steering. We combined the liveness detection and FaceNet model for identity authentication. For improving the application of the authentication approach, we proposed two improved ways to run the FaceNet model. Experimental results showed that the combination of the proposed liveness detection and improved face recognition had a good recognition effect and can be used for identity authentication.https://www.mdpi.com/1424-8220/19/21/4733liveness detectionkinect camerainfrared radiationdeep learningfacenet |
| spellingShingle | Shuhua Liu Yu Song Mengyu Zhang Jianwei Zhao Shihao Yang Kun Hou An Identity Authentication Method Combining Liveness Detection and Face Recognition Sensors liveness detection kinect camera infrared radiation deep learning facenet |
| title | An Identity Authentication Method Combining Liveness Detection and Face Recognition |
| title_full | An Identity Authentication Method Combining Liveness Detection and Face Recognition |
| title_fullStr | An Identity Authentication Method Combining Liveness Detection and Face Recognition |
| title_full_unstemmed | An Identity Authentication Method Combining Liveness Detection and Face Recognition |
| title_short | An Identity Authentication Method Combining Liveness Detection and Face Recognition |
| title_sort | identity authentication method combining liveness detection and face recognition |
| topic | liveness detection kinect camera infrared radiation deep learning facenet |
| url | https://www.mdpi.com/1424-8220/19/21/4733 |
| work_keys_str_mv | AT shuhualiu anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT yusong anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT mengyuzhang anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT jianweizhao anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT shihaoyang anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT kunhou anidentityauthenticationmethodcombininglivenessdetectionandfacerecognition AT shuhualiu identityauthenticationmethodcombininglivenessdetectionandfacerecognition AT yusong identityauthenticationmethodcombininglivenessdetectionandfacerecognition AT mengyuzhang identityauthenticationmethodcombininglivenessdetectionandfacerecognition AT jianweizhao identityauthenticationmethodcombininglivenessdetectionandfacerecognition AT shihaoyang identityauthenticationmethodcombininglivenessdetectionandfacerecognition AT kunhou identityauthenticationmethodcombininglivenessdetectionandfacerecognition |