Abstract:Aiming at the problem that some offline handwrittenChinese characters are similar in shape and it is difficult to extract thefeature of characters and the recognition is not accurate

a convolutionalneural network and deep belief network fusion model is proposed Firstly

theconvolutional neural network and the deep belief network are trained on thedataset respectively It is found that the comprehensive TOP-2 accuracy of theboth can reach 99.33% Using the advantages of convolutional neural networks anddeep belief networks in image analysis

a fusion comparison strategy is adoptedto extract a classification result as accurately as possible in the TOP-2classification of the two to improve the recognition ability The experimentalresults show that the fusion model of convolutional neural network and deepbelief network has better recognition effect than convolutional neural networkand deep belief network