Digital Recognition Based on Improved LENET Convolution Neural Network

To promote the performance of LeNet-5 convolutional neural network, an improved LeNet-5 convolutional neural network was proposed. The improved neural network model was trained using MNIST character library. The effects on the performance of final recognition of the parameters of LeNet-5, including the different number of iterations, amounts of samples of each batch and the network learning rate were analyzed. The comparison of performances between Le-Net-5 and improved LeNet-5 was made. The results showed that the structure of improved network is simpler, the training parameters are fewer, the training time is shorter, the recognition rate is higher, the improved network can overcome the fitting phenomenon. The performance of the improved network is better that of traditional methods.

[1]  Jingjing Wang,et al.  Image retrieval and classification on deep convolutional SparkNet , 2016, 2016 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC).

[2]  Weihong Deng,et al.  Very deep convolutional neural network based image classification using small training sample size , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[3]  Xinbo Zhang,et al.  Handwritten Digit Recognition Based on Improved Learning Rate BP Algorithm , 2010, 2010 2nd International Conference on Information Engineering and Computer Science.

[4]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  U. Ravi Babu,et al.  Handwritten Digit Recognition Using Structural, Statistical Features and K-nearest Neighbor Classifier , 2014 .

[6]  A. Nagarjuna.  Handwritten Digit Recognition Using Structural , Statistical Features and K-nearest Neighbor Classifier , 2016 .

[7]  Stefan Wermter,et al.  A Multichannel Convolutional Neural Network for Hand Posture Recognition , 2014, ICANN.

[8]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[9]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[10]  D. Gorgevik,et al.  Handwritten Digit Recognition by Combining SVM Classifiers , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".