Street view image classification based on convolutional neural network

This paper utilizes the deep learning algorithm to classify the Street View images. We did some research to find the appropriate convolutional neural network model that suits the classification of the street view images. We firstly collected our own dataset. Based on the convolutional neural network model AlexNet and according to the characteristics the dataset mentioned above to adjust the model structure and training methods. Experiments utilize max-pooling as sampling model, set the number of samples for one iteration as 128 and randomly cropped the same picture out as different parts for the input model to train reaches good accuracy rate which is 93.6%. The experiment result have shown that the number of samples for one iteration can significantly enhance the training effect of the model we proposed in this paper. We conduct the experiment by randomly cropped the same picture out as different parts for the input model to train, in which way can solve the problem that the dataset we collected is comparatively small, it improve the effect of classification obviously.