A Facial Expression Recognition Based on Improved Convolutional Neural Network
| Autor: | Sai Zhang, Jiancheng Zou, Bailin Ge, Xiuling Cao |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Facial expression
Computer science business.industry Computer Science::Neural and Evolutionary Computation Feature extraction Activation function ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Overfitting Facial recognition system Regularization (mathematics) Convolutional neural network ComputingMethodologies_PATTERNRECOGNITION Facial expression recognition Computer Science::Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | 2019 IEEE International Conference of Intelligent Applied Systems on Engineering (ICIASE). |
| DOI: | 10.1109/iciase45644.2019.9074074 |
| Popis: | In order to solve the problems of low recognition rate and complex algorithm of traditional facial expression recognition methods, an improved facial expression recognition algorithm based on convolutional neural network (CNN) was proposed. The convolutional neural network uses batch regularization and ReLU activation function to solve the problem of gradient disappearance. The Dropout technology is introduced to solve the problem of network overfitting. Experimental results show that the improved convolutional neural network can improve the accuracy of face expression image recognition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|