Abstract: As an important branch of pattern recognition,handwritten digit recognition is in an unprecedented upsurge,and con-volutional neural networks are also widely used in related research.In view of the problem that gradient explosion and gradient dispersion are prone to occur in the training process of handwritten digit recognition,which leads to low image recognition accuracy,a model embedded with convolutional block attention module(CBAM)is newly proposed for handwritten digit recognition.The CBAM is embedded in the convolutional neural network in order to screen out effective features from the channel and spatial dimensions respectively,suppress irrelevant features,enhance the expression ability of features,and improve the recognition accuracy of the model.In order to further improve the accuracy of network identification,the batch normalization(BN) algorithm is fully applied in the entire network architecture to speed up the model convergence,in this way,the anti-over-fitting ability of the model gets improved.The results of experiments which are conducted on the MNIST dataset show that the overall recognition accuracy of the embedded CBAM attention module network is up to 99.87%,and compared with some traditional convolutional neural network models,its recognition accuracy is significantly improved.

Key words: Handwritten digit recognition, Attention mechanism, Convolutional neural network, Deep learning