Research on image classification based on extreme learning machine and convolutional neural network

Abstract

In image classification and recognition, in order to obtain higher classification accuracy, it is necessary to extract more accurate and more expressive features of image semantic information. This paper proposes an improved image classification model based on convolutional neural network. By improving and optimizing AlexNet from both the network architecture and the internal structure, we can further improve the expression ability of features. By introducing the extreme learning machine in the full connection layer, not only the classification ability and classification time of the network are improved, but also the structure has better data processing ability.