Isaac Scientific Publishing

Frontiers in Signal Processing

Face Recognition Based on MTCNN and Convolutional Neural Network

Download PDF (1127.3 KB) PP. 37 - 42 Pub. Date: January 5, 2020

DOI: 10.22606/fsp.2020.41006

Author(s)

  • Hongchang Ku
    Southwest Minzu University, Key Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Chengdu, 610041, China
  • Wei Dong*
    Southwest Minzu University, Key Laboratory of Electronic and Information Engineering, State Ethnic Affairs Commission, Chengdu, 610041, China

Abstract

MTCNN is a face detection method based on deep learning, which is more robust to light, angle and facial expression changes in natural environment, and has better face detection effect. At the same time, the memory consumption is small, and real-time face detection can be realized. Therefore, a method based on MTCNN and improved convolution neural network is proposed in this paper. Firstly, MTCNN is used to detect and align faces. Then, the output image is used as the input data of the improved convolution network, and multi-level convolution training is carried out. Finally, the accuracy of the model is tested.

Keywords

MTCNN, face detection and alignment, convolutional neural network, face recognition.

References

[1] Zhang K, Zhang Z, Li Z, et al. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks[J]. IEEE Signal Processing Letters, 2016, 23(10):1499-1503.

[2] Xiang J, Zhu G. [IEEE 2017 4th International Conference on Information Science and Control Engineering (ICISCE) - Changsha (2017.7.21-2017.7.23)] 2017 4th International Conference on Information Science and Control Engineering (ICISCE) - Joint Face Detection and Facial Expression Recognition with MTCNN[C]// International Conference on Information Science & Control Engineering. IEEE Computer Society, 2017:424-427.

[3] Barkan O, Weill J, Wolf L, et al. Fast High Dimensional Vector Multiplication Face Recognition[C]// IEEE International Conference on Computer Vision. 2014.

[4] Bengio Y. Learning Deep Architectures for AI[J]. Foundations & Trends® in Machine Learning, 2009, 2(1):1-127.

[5] Qian Z, Ge S S, Mao Y, et al. Learning Saliency Features for Face Detection and Recognition Using Multi-task Network[J]. International Journal of Social Robotics, 2016, 8(5):1-12.

[6] Cao X, Wipf D, Fang W, et al. A Practical Transfer Learning Algorithm for Face Verification[C]// IEEE International Conference on Computer Vision. 2014.

[7] Chen D, Cao X, Wang L, et al. Bayesian Face Revisited: A Joint Formulation[C]// European Conference on Computer Vision. Springer, Berlin, Heidelberg, 2012.

[8] Chen D, Cao X, Wen F, et al. Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification[C]// Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013.

[9] Chopra S, Hadsell R, Lecun Y. Learning a Similarity Metric Discriminatively, with Application to Face Verification[C]// IEEE Computer Society Conference on Computer Vision & Pattern Recognition. 2005.

[10] Cui Z, Li W, Xu D, et al. Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild[C]// Computer Vision & Pattern Recognition. IEEE, 2013.

[11] Taigman Y, Yang M, Ranzato M, et al. DeepFace: Closing the Gap to Human-Level Performance in Face Verification[C]// Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2014.

[12] Lawrence S, Giles C L, Tsoi A C, et al. Face recognition: a convolutional neural-network approach[J]. IEEE Transactions on Neural Networks, 1997, 8(1):98-113.

[13] Gu J, Wang Z, Kuen J, et al. Recent Advances in Convolutional Neural Networks[J]. Computer Science, 2015.

[14] Schmidhuber J. Deep Learning in neural networks: An overview.[J]. Neural Netw, 2015, 61:85-117.

[15] Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014.

[16] Schroff F, Kalenichenko D, Philbin J. FaceNet: A unified embedding for face recognition and clustering[J]. 2015.