唐小煜, 王东, 林逸鑫, 李萍. 基于改进八度卷积算法的人脸表情识别[J]. 华南师范大学学报(自然科学版), 2023, 55(2): 116-123. DOI: 10.6054/j.jscnun.2023027
引用本文: 唐小煜, 王东, 林逸鑫, 李萍. 基于改进八度卷积算法的人脸表情识别[J]. 华南师范大学学报(自然科学版), 2023, 55(2): 116-123. DOI: 10.6054/j.jscnun.2023027
TANG Xiaoyu, WANG Dong, LIN Yixin, LI Ping. Facial Expression Recognition Based on Improved Octave Convolution Algorithm[J]. Journal of South China Normal University (Natural Science Edition), 2023, 55(2): 116-123. DOI: 10.6054/j.jscnun.2023027
Citation: TANG Xiaoyu, WANG Dong, LIN Yixin, LI Ping. Facial Expression Recognition Based on Improved Octave Convolution Algorithm[J]. Journal of South China Normal University (Natural Science Edition), 2023, 55(2): 116-123. DOI: 10.6054/j.jscnun.2023027

基于改进八度卷积算法的人脸表情识别

Facial Expression Recognition Based on Improved Octave Convolution Algorithm

  • 摘要: 针对目前人脸表情识别存在准确率不高、模型复杂和计算量大的问题,文章提出了一种基于八度卷积改进的人脸表情识别模型(OCNN):使用改进的八度卷积进行特征提取,提高对细节特征的提取效果,降低特征图的冗余,在不增加参数的同时减少运算量,以提高特征提取性能;利用DyReLU激活函数来增强模型的学习和表达能力;使用自适应平均池化下采样层代替全连接层,以减少参数;将模型在大规模数据集上进行预训练,并在FER2013、FERPlus、RAF-DB数据集上进行模型性能验证实验。实验结果表明:训练后的模型权重为10.4 MB,在人脸表情识别数据集FER2013、FERPlus和RAF-DB上的准确率分别达到73.53%、89.58%和88.50%;与目前诸模型相比,OCNN模型的准确性高且计算资源消耗低,充分证明了该模型的有效性。

     

    Abstract: Aiming at the problems of low accuracy, complex model and large amount of calculation in current facial expression recognition, an improved facial expression recognition method based on octave convolution was proposed in this paper. The improved octave convolution is used for feature extraction, which improves the extraction effect of detailed feature, decline the redundancy in the feature map, and reduce the amount of calculation without increa-sing the parameters, so as to improve the feature extraction performance; DyReLU activation function was used to enhance the learning and expression capabilities of the model. The parameters are reduced using an adaptive mean pooling downsampling layer instead of a fully connected layer; the model is pre-trained on a large dataset, and then the model performance verification experiment is performed on the FER2013, FERPlus and RAF-DB datasets. The experimental results show that the trained model weights is only 10.4 MB, and the accuracy of the model on the expression recognition datasets FER2013, FERPlus and RAF-DB are 73.53%, 89.58% and 88.50% respectively. Compared with many current models, the OCNN model had higher accuracy and lower computing resource consumption, which fully proved the effectiveness of this model.

     

/

返回文章
返回