|
|
基于卷积神经网络的人脸表情识别算法
|
Abstract:
人脸表情识别是图像识别的一个重要领域。传统人脸表情识别主要基于人工提取特征，由于人脸表情丰富、背景复杂、差异范围大等问题，其存在算法鲁棒性较差、易受人脸身份信息干扰等问题，以及传统卷积神经网络易发生过拟合、梯度弥散、梯度爆炸等问题的现状，因此本文提出一种多层特征融合非反向传播稠密卷积神经网络的人脸表情识别算法。该算法应用了改进的HSIC (Hilbert-Schmidt Independence Criterion，希尔伯特–施密特独立性)-bottleneck来代替传统反向传播(Back Propagation, BP)，具有诸多独特的优点。在特征提取过程中，为了充分利用得到的特征图像，将卷积层稠密连接并引入attention机制，最终通过softmax分类器分类，得到分类结果。在FER2013数据集上进行了多次实验，与传统BP算法的卷积神经网络算法相比，不仅有效减轻过拟合现象，并且在模型收敛速度上更快、计算量更小、内存占用更小，证明了在人脸表情识别问题中非反向传播稠密卷积神经网络模型结构有效、提出的分类优化方法可行。
Facial expression recognition is an important field of image recognition. Traditional facial expression recognition is mainly based on manual extraction of features, which has the problems of poor algorithm robustness and susceptibility to interference by face identity information due to rich facial expressions, complex background and large range of differences, as well as the current situation that traditional convolutional neural networks are prone to overfitting, gradient dispersion and gradient explosion, etc. Therefore, this paper proposes a multilayer feature fusion using dense convolutional neural network without Back Propagation (BP) for face expression recognition algorithm. The algorithm applies a modified HSIC (Hilbert-Schmidt independence criterion)-bottleneck instead of the traditional BP, which has many unique advantages. In the feature extraction process, in order to make full use of the obtained feature images, the convolutional layers are densely connected and attention mechanism is introduced, and finally the classification results are obtained by the softmax classifier. Compared with the traditional BP algorithm of convolutional neural network algorithm, it not only effectively reduces the overfitting phenomenon, but also has faster model convergence, smaller computation and smaller memory consumption, which proves that the structure of non-back propagation dense convolutional neural network model is effective and the proposed classification optimization method is feasible in the face expression recognition problem.
| [1] | Mehrabiau, A. (1968) Communication without Words. Psychology Today, 2, 53-56. |
| [2] | Ekman, P. (1972) Universals and Cultural Differences in Facial Expressions of Emotion. Nebraska Symposium of Motivation, Vol. 19, 207-283. |
| [3] | Wan, S. and Aggarwal, J.K. (2013) A Scalable Metric Learning-Based Voting Method for Expression Recognition. 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), Shanghai, 22-26 April 2013, 1-8. |
| [4] | Ali, H., Hariharan, M., Yaacob, S., et al. (2015) Facial Emotion Recognition Using Empirical Mode Decomposition. Expert Systems with Applications, 42, 1261-1277. https://doi.org/10.1016/j.eswa.2014.08.049 |
| [5] | Liu, C. and Wechsler, H. (2002) Gabor Feature Based Classification Using the Enhanced Fisher Linear Discriminant Model for Face Recognition. IEEE Transactions on Image Processing, 11, 467-476.
https://doi.org/10.1109/TIP.2002.999679 |
| [6] | Shin, Y.S. (2006) Recognizing Facial Expressions with PCA and ICA onto Dimension of the Emotion. Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), Hong Kong, 17-19 August 2006, 916-922. https://doi.org/10.1007/11815921_101 |
| [7] | Lajevardi, S.M. and Hussain, Z.M. (2010) Emotion Recognition from Color Facial Images Based on Multilinear Image Analysis and Log-Gabor Filters. 2010 25th International Conference of Image and Vision Computing New Zealand (IVCNZ), Queenstown, 8-9 November 2010, 1-6. https://doi.org/10.1109/IVCNZ.2010.6148802 |
| [8] | Widrow, B., Greenblatt, A., Kim, Y., et al. (2013) The No-Prop Algorithm: A New Learning Algorithm for Multilayer Neural Networks. Neural Networks, 37, 180-186. https://doi.org/10.1016/j.neunet.2012.09.020 |
| [9] | Yosinski, J., Clune, J., Bengio, Y., et al. (2014) How Transferable Are Features in Deep Neural Networks? |
| [10] | Kleinberg, J.M. (1997) Two Algorithms for Nearest-Neighbor Search in High Dimensions. 29th ACM Symposium on Theory of Computing, El Paso, 4-6 May 1997, 599-608. https://doi.org/10.1145/258533.258653 |
| [11] | Ma, W.D.K., Lewis, J.P. and Kleijn, W.B. (2019) The HSIC Bottleneck: Deep Learning without Back-Propagation. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 5085-5092.
https://doi.org/10.1609/aaai.v34i04.5950 |
| [12] | Gretton, A., Bousquet, O., Smola, A., et al. (2005) Measuring Statistical Dependence with Hilbert-Schmidt Norms. Algorithmic Learning Theory, 16th International Conference, ALT 2005, Singapore, 8-11 October 2005, 63-77. |
| [13] | Talpur, N., Abdulkadir, S.J., Alhussian, H., et al. (2022) A Comprehensive Review of Deep Neuro-Fuzzy System Architectures and Their Optimization Methods. Neural Computing and Applications, 34, 1837-1875. |
| [14] | Lillicrap, T.P., Cownden, D., Tweed, D.B., et al. (2016) Random Synaptic Feedback Weights Support Error Backpropagation for Deep Learning. Nature Communications, 7, 13276. https://doi.org/10.1038/ncomms13276 |
| [15] | Xiao, W., Chen, H., Liao, Q., et al. (2018) Biologically-Plausible Learning Algorithms Can Scale to Large Datasets. |
| [16] | Grossberg, S. (1987) Competitive Learning: From Interactive Activation to Adaptive Resonance. Cognitive Science, 11, 23-63. https://doi.org/10.1111/j.1551-6708.1987.tb00862.x |
| [17] | Lillicrap, T.P., Cownden, D., Tweed, D.B., et al. (2014) Random Feedback Weights Support Learning in Deep Neural Networks. |
| [18] | Bengio, Y., Lee, D.H., Bornschein, J., et al. (2015) Towards Biologically Plausible Deep Learning. |
| [19] | Bach, F. (2022) Information Theory with Kernel Methods. IEEE Transactions on Information Theory, 69, 752-775. |
| [20] | Sun, Q., Li, J., Peng, H., et al. (2022) Graph Structure Learning with Variational Information Bottleneck. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 4165-4174. https://doi.org/10.1609/aaai.v36i4.20335 |
| [21] | Cong, S. and Zhou, Y. (2023) A Review of Convolutional Neural Network Architectures and Their Optimizations. Artificial Intelligence Review, 56, 1905-1969. https://doi.org/10.1007/s10462-022-10213-5 |
| [22] | Krizhevsky, A., Sutskever, I. and Hinton, G. (2012) ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. |
| [23] | Ioffe, S. and Szegedy, C. (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. |
| [24] | Szegedy, C., Vanhoucke, V., Ioffe, S., et al. (2016) Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 2818-2826.
https://doi.org/10.1109/CVPR.2016.308 |
