Human ear recognition based on deep convolutional neural network
Ying Tian, Wang Shining, Wanxiang Li · 2018
In order to improve the recognition rate of human ear images, a human ear recognition algorithm based on deep convolutional neural network is proposed. Firstly, a deep network structure based on convolutional neural network is designed for human ear recognition problem. The optimal activation function is selected and Dropout technology is introduced in the final fully connected layer to prevent network over-fitting. The network model is trained by a large number of human ear image samples to determine the number of feature graphs, the setting of learning rate and other parameters in the network. In addition, human ear recognition test is conducted on the trained network model. The comparison experiment shows that the method is robust to light, rotation and occlusion, and the human ear recognition rate is obviously improved.