Embedded Face Recognition System Based on Multi-task Convolutional Neural Network and LBP Features
Authors:
- 1 April 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 132-135
Abstract
Based on neural network and local binary pattern algorithm, this paper builds a lightweight artificial face recognition system on chip Firefly-RK3399, with high speed, strong robustness and high recognition accuracy. Our embedded artificial intelligent face recognition system mainly consists of face detection, feature extraction and recognition. Multi-task convolutional neural network (MTCNN) under the CaffeOnACL framework is utilized for face detection, and the local binary pattern (LBP) is applied as face recognition algorithm. Experiments illustrate that our artificial intelligent embedded face recognition system has high speed and accuracy, which is easy-carrying and of high commercial value as well.Keywords
This publication has 6 references indexed in Scilit:
- FaceHunter: A multi-task convolutional neural network based face detectorSignal Processing: Image Communication, 2016
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition2015
- Morphable Displacement Field Based Image Matching for Face Recognition across Pose2012
- Implementation and optimization of embedded Face Detection system2011
- A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification2001