Towards on-device face recognition in body-worn cameras

No Thumbnail Available
Almadan, Ali
Rattani, Ajita
Issue Date
Conference paper
Performance evaluation , Analytical models , Face recognition , Surveillance , Computational modeling , Biological system modeling , Cameras
Research Projects
Organizational Units
Journal Issue
Almadan, A., & Rattani, A. (2021). Towards on-device face recognition in body-worn cameras. Paper presented at the Proceedings - 9th International Workshop on Biometrics and Forensics, IWBF 2021, doi:10.1109/IWBF50991.2021.9465079

Face recognition technology related to recognizing identities is widely adopted in intelligence gathering, law enforcement, surveillance, and consumer applications. Recently, this technology has been ported to smartphones and body-worn cameras (BWC). Face recognition technology in body-worn cameras is used for surveillance, situational awareness, and keeping the officer safe. Only a handful of academic studies exist in face recognition using the body-worn camera. A recent study has assembled BWCFace facial image dataset acquired using a body-worn camera and evaluated the ResNet-50 model for face identification. However, for real-time inference in resource constraint body-worn cameras and privacy concerns involving facial images, on-device face recognition is required. To this end, this study evaluates lightweight MobileNet-V2, EfficientNet-BO, LightCNN-9 and LightCNN-29 models for face identification using body-worn camera. Experiments are performed on a publicly available BWCface dataset. The real-time inference is evaluated on three mobile devices. The comparative analysis is done with heavy-weight VGG-16 and ResNet-50 models along with six hand-crafted features to evaluate the trade-off between the performance and model size. Experimental results suggest the difference in maximum rank-l accuracy of lightweight LightCNN-29 over best-performing ResNet-50 is 1.85% and the reduction in model parameters is 23.49M. Most of the deep models obtained similar performances at rank-5 and rank-10. The inference time of LightCNNs is 2.1x faster than other models on mobile devices. The least performance difference of 14% is noted between LightCNN-29 and Local Phase Quantization (LPQ) descriptor at rank-l. In most of the experimental settings, lightweight LightCNN models offered the best trade-off between accuracy and the model size in comparison to most of the models.

Table of Contents
Click on the DOI link to access this conference paper at the publisher's website (may not be free).
Book Title
2021 IEEE International Workshop on Biometrics and Forensics (IWBF);
PubMed ID