Image recognition method based on convolutional neural network

The invention discloses an image recognition method based on a convolutional neural network. The method includes following steps: obtaining an original image; preprocessing the original image; inputting an output result of an upper layer to a sub-network in the convolutional neural network; inputting the output result of the upper layer to convolution layers and pooling layers alternately distributed in the convolutional neural network; inputting the output result of the upper layer to a full connection layer of the convolutional neural network; inputting the output result of the upper layer to a final layer of the convolutional neural network, namely the Softmax layer, to obtain the probability of the image belonging to each category; and determining an image classification result according to the probability of the image belonging to each category, and finally outputting the image classification result. According to the method, one sub-network structure is added to the classic convolutional neural network,