Image Classification Based On Deep Convolutional Neural Network

Image classification based on deep Convolutional Neural Network(CNN)is one of the important applications of deep learning on image processing The advantage of CNN is that it can make convolution computation with pixels to extract features,which simulates the vision learning method of human brains,as the better choioe compared to normal method.And the weights sharing and pooling layer in CNN reduce the number of network parameters largely,which simplify the network structure and improve the learning efficiency.This thesis mainly focus on the network structure design and the parameters optimization.The convolutional neural network's dassification performance depends on network's layers and parameters.Howtodesign convolutional layers,the number of hidden layers and optimize the convolutional neural network parameters properly are very important parts in convolutional neural network applied research field.The most work in this thesis will be implemented on MXNetdeep leaning framework including model structure design and parameters optimization.Firstly,I will design several CNN models which contain different layers,and use cifar-10 dataset to train,test and optimize CNN.Testing results show that the deeper CNN model can achieve higher acurate rate on Cifar image dataset.The Multi-model's experimental results show that the network layer of depth influences network's performance.This thesis studies the structure and parameters optimization methods of network and tested on differant databases,and conclude some practical rules about how to apply deep learning intoimage dassification.Due to parameters playgreat roles in alike learning networks,it will be a better guide for solving some engineering problems.The conclusions can also be applied into some other deep networks.