journal article·2023-02-25Open access

Coupling RetinaFace and Depth Information to Filter False Positives

Loris Nanni, Sheryl Brahnam, Alessandra Lumini, Andrea Loreggia

Applied Sciences· Volume 13· Issue 5

Abstract

Face detection is an important problem in computer vision because it enables a wide range of applications, such as facial recognition and an analysis of human behavior. The problem is challenging because of the large variations in facial appearance across different individuals and lighting and pose conditions. One way to detect faces is to utilize a highly advanced face detection method, such as RetinaFace or YOLOv7, which uses deep learning techniques to achieve high accuracy in various datasets. However, even the best face detectors can produce false positives, which can lead to incorrect or unreliable results. In this paper, we propose a method for reducing false positives in face detection by using information from a depth map. A depth map is a two-dimensional representation of the distance of objects in an image from the camera. By using the depth information, the proposed method is able to better differentiate between true faces and false positives. The method proposed by the authors is tested on a dataset of 549 images, which includes 614 upright frontal faces. The outcomes of the evaluation demonstrate that the method effectively minimizes false positives without compromising the overall detection rate. These findings suggest that incorporating depth information can enhance the accuracy of face detection.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Face recognition and analysis · Video Surveillance and Tracking Methods · Face and Expression Recognition

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Information Engineering (DEI), University of Padova, 35131 Padova, Italy

Department of Information Technology and Cybersecurity, Missouri State University, Springfield, MO 65804, USA

Department of Computer Science and Engineering (DISI), University of Bologna, 47521 Cesena, Italy

Department of Information Engineering (DII), University of Brescia, 25123 Brescia, Italy

References (28)

Show source-provided references
1. Nanni, L., Brahnam, S., and Lumini, A. (2019). Face Detection Ensemble with Methods Using Depth Information to Filter False Positives. Sensors, 19.10.3390/s19235242 ↗
2. Face Alignment in Full Pose Range: A 3D Total Solution10.1109/TPAMI.2017.2778152 ↗
3. Taigman, Y., Yang, M., Ranzato, M., and Wolf, L. (2014, January 23–28). DeepFace: Closing the Gap to Human-Level Performance in Face Verification. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.220 ↗
4. Face detection techniques: A review10.1007/s10462-018-9650-2 ↗
5. Detecting faces in images: A survey10.1109/34.982883 ↗
6. Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., and Li, S.Z. (2017, January 22–29). S3fd: Shot Scale-Invariant Face Detector. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV).10.1109/ICCV.2017.30 ↗
7. Multi-task Cascaded Convolutional Neural Networks for Real-Time Dynamic Face Recognition Method10.1007/978-981-13-6508-9_8 ↗
8. Viola, P., and Jones, M. (2001, January 8–14). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, Kauai, HI, USA.
9. A Fast and Accurate Unconstrained Face Detector10.1109/TPAMI.2015.2448075 ↗
10. Markuš, N., Frljak, M., Pandžić, I.S., Ahlberg, J., and Forchheimer, R. (2014). Fast Localization of Facial Landmark Points. arXiv.10.20532/ccvw.2014.0001 ↗
11. Li, H., Lin, Z., Shen, X., Brandt, J., and Hua, G. (2015, January 7–12). A convolutional neural network cascade for face detection. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7299170 ↗
12. Farfade, S.S., Saberian, M., and Li, L.J. (2015, January 23–26). Multi-view face detection using Deep convolutional neural networks. Proceedings of the 5th ACM on International Conference on Multimedia Retrieva, Shanghai, China.10.1145/2671188.2749408 ↗
13. A Face Detection Method Based on Cascade Convolutional Neural Network10.1007/s11042-018-6995-0 ↗
14. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks10.1109/LSP.2016.2603342 ↗
15. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
16. Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020, January 14–19). Retinaface: Single-shot multi-level face localisation in the wild. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00525 ↗
17. Kinectfacedb: A kinect database for face recognition10.1109/TSMC.2014.2331215 ↗
18. Gupta, S., Castleman, K.R., Markey, M.K., and Bovik, A.C. (2010, January 23–25). Texas 3D Face Recognition Database. Proceedings of the 2010 IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI), Austin, TX, USA.10.1109/SSIAI.2010.5483908 ↗
19. Faltemier, T.C., Bowyer, K.W., and Flynn, P.J. (2007, January 27–29). Using a Multi-Instance Enrollment Representation to Improve 3D Face Recognition. Proceedings of the 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems, Crystal City, VA, USA.10.1109/BTAS.2007.4401928 ↗
20. Real-time human pose recognition in parts from single depth images10.1145/2398356.2398381 ↗
21. Mattheij, R., Postma, E., Van den Hurk, Y., and Spronck, P. (2012, January 25–26). Depth-based detection using Haar-like features. Proceedings of the Belgian/Netherlands Artificial Intelligence Conference, Maastricht, The Netherlands.
22. Signal, I. (2008). Signal Processing for Image Enhancement and Multimedia Processing, Springer.
23. Joint Depth and Color Camera Calibration with Distortion Correction10.1109/TPAMI.2012.125 ↗
24. Fusion of Geometry and Color Information for Scene Segmentation10.1109/JSTSP.2012.2194474 ↗
25. Mean shift: A robust approach toward feature space analysis10.1109/34.1000236 ↗
26. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.
27. Effective and precise face detection based on color and depth data10.1016/j.aci.2014.04.001 ↗
28. Fair comparison of skin detection approaches on publicly available datasets10.1016/j.eswa.2020.113677 ↗