Pubface: Celebrity face identification based on deep learning

Sustainable Buildings and Cities

土木建筑工程

Ouanan, H.^1 ; Ouanan, M.^1 ; Aksasse, B.^1

Dept. of Computer Science, ASIA Team, M2I Laboratory, Faculty of Science and Techniques, Errachidia, Morocco^1

关键词: Deep convolutional neural networks;    Face identification;    Fine tuning;    Neural network algorithm;    Pose-invariant face recognition;    Public space;    Raspberry pi;    Real-time application;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/353/1/012022/pdf
DOI  :  10.1088/1757-899X/353/1/012022

学科分类：土木及结构工程学

来源: IOP

【 摘 要 】

In this paper, we describe a new real time application called PubFace, which allows to recognize celebrities in public spaces by employs a new pose invariant face recognition deep neural network algorithm with an extremely low error rate. To build this application, we make the following contributions: firstly, we build a novel dataset with over five million faces labelled. Secondly, we fine tuning the deep convolutional neural network (CNN) VGG-16 architecture on our new dataset that we have built. Finally, we deploy this model on the Raspberry Pi 3 model B using the OpenCv dnn module (OpenCV 3.3).