Face Recognition Method based on Feature Fusion and Convolutional Neural Network

10.6919/ICJE.202205_8(5).0068

Ting Gong；Xiaoqin Liu；Hejin Yuan

Convolutional Neural Network ； Feature Fusion ； Uniform Local Binary Pattern ； Face Recognition ； Sdresnetst-50 ； Loss Function

International Core Journal of Engineering

8卷5期（2022 / 05 / 01）

526 - 537

英文

In recent years, convolutional neural network has achieved good results in the field of face recognition, but it ignores the local features of face in feature extraction. Therefore, this paper proposes a method based on improved LBP and deep learning. In this method, the feature image extracted by ULBP operator is used to reduce the dimension of LDA data, and then combined with the original image as the input of SDResNetSt-50 network, which makes it more comprehensive to extract the features of face image. Among them, sdresnetst-50 network is a network that combines the features of the last three convolution layers of traditional ResNetSt-50 network, which enhances the ability of network feature expression; at the same time, it combines softmax with center loss function to shorten the data distance between peers, and further improves the recognition effect of face image. Experiments on CASIA-WebFace face dataset show that the proposed method achieves 98.75% recognition accuracy, which is superior to all other comparison algorithms, and proves the effectiveness and feasibility of the method.

1. CHEN Y, DAI X, LIU M, et al. Dynamic Convolution: Attention over Convolution Kernels[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2020: 11027–11036.
   連結：
2. HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, 2016-Decem: 770–778.
   連結：
3. KIM Y. Convolutional Neural Networks for Sentence Classification[J]. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 2014: 1746–1751.
   連結：
4. ARQUITECTURA E Y, INTRODUCCI T I, Xiaoxia He, et al. Small sample face recognition algorithm based on transfer learning model [J/OL]. Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, 2015, 53(9): 1689–1699.
5. MA X, ZHUANG W, FENG J. Loose Sparse Representation Based Undersampled Face Recognition with Auxiliary Dictionaries[J]. Moshi Shibie Yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2016, 29(5): 439–446.
6. Dong Yanhua, Zhang Shumei, Zhao Junli. Overview of occluded face recognition methods [J]. 2020.
7. VANSCHOREN J. Meta-Learning: A Survey[J/OL]. 2018: 1–29.
8. HILLIARD N, PHILLIPS L, HOWLAND S, et al. Few-Shot Learning with Metric-Agnostic Conditional Embeddings[J]. ArXiv, 2018.
9. XU J, TON J-F, KIM H, et al. MetaFun: Meta-Learning with Iterative Functional Updates[J/OL]. 2019.
10. CELLA L, LAZARIC A, PONTIL M. Meta-Learning with Stochastic Linear Bandits[J/OL]. 2020: 1–22.
11. CHEN W Y, WANG Y C F, LIU Y C, et al. A Closer Look at Few-Shot Classification[J]. 7th International Conference on Learning Representations, ICLR 2019, 2019(2018): 1–17.
12. HOSPEDALES T, ANTONIOU A, MICAELLI P, et al. Meta-Learning in Neural Networks: A Survey [J/OL]. 2020: 1–23.
13. NICHOL A, ACHIAM J, SCHULMAN J. On First-Order Meta-Learning Algorithms[J/OL]. 2018: 1–15.
14. FINN C, ABBEEL P, LEVINE S. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks[J]. 34th International Conference on Machine Learning, ICML 2017, 2017, 3: 1856–1868.