Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network
Deep learning technology is widely used in the field of number recognition.It constructs neural network model through deep learning technology,nonlinear transformation activation function in neurons,different activation functions with different parameter initialization strategies,trains MINIST handw...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-12-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-244.pdf |
| _version_ | 1797845152661766144 |
|---|---|
| author | FAN Ji-hui, TENG Shao-Hua, JIN Hong-Lin |
| author_facet | FAN Ji-hui, TENG Shao-Hua, JIN Hong-Lin |
| author_sort | FAN Ji-hui, TENG Shao-Hua, JIN Hong-Lin |
| collection | DOAJ |
| description | Deep learning technology is widely used in the field of number recognition.It constructs neural network model through deep learning technology,nonlinear transformation activation function in neurons,different activation functions with different parameter initialization strategies,trains MINIST handwritten data set,constructs analysis model and recognizes numbers in images,reduce the dimension of a large amount of data into a small amount of data,and ensure the effective retention of image features.Through the analysis of image data,adding the feature conversion process,using the gradient descent optimizer to build a network structure and reduce the dimension of data,which can effectively avoid over fitting.Cross-entropy verification is used to compile and train the model,and the output classification results are further analyzed.Through the <i>K</i>-nearest neighbor classification algorithm,KNN classifier is set to further improve the accuracy of classification and prediction.Through MNIST data set experiment,the recognition rate is about 96.2%.The <i>K</i>-nearest neighbor algorithm(KNN) is introduced into the output layer,combined with the full connection layer and softmax layer of traditional convolutional neural network(CNN).After cross verification,the recognition rate is 99.6%. |
| first_indexed | 2024-04-09T17:33:57Z |
| format | Article |
| id | doaj.art-b713cab3b2764ed9a0e5c5f51fe63d2f |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:57Z |
| publishDate | 2022-12-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-b713cab3b2764ed9a0e5c5f51fe63d2f2023-04-18T02:32:59ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-12-01491224424910.11896/jsjkx.211000179Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural NetworkFAN Ji-hui, TENG Shao-Hua, JIN Hong-Lin01 Graduate School,St.Paul University Philippines,Tuguegarao,Cagayan 3500,Philippines ;2 School of Computer Science and Engineering,Guangzhou Institute of Science and Technology,Guangzhou 510540,China ;3 School of Computer Science and Engineering,Guangdong University of Technology,Guangzhou 510006,ChinaDeep learning technology is widely used in the field of number recognition.It constructs neural network model through deep learning technology,nonlinear transformation activation function in neurons,different activation functions with different parameter initialization strategies,trains MINIST handwritten data set,constructs analysis model and recognizes numbers in images,reduce the dimension of a large amount of data into a small amount of data,and ensure the effective retention of image features.Through the analysis of image data,adding the feature conversion process,using the gradient descent optimizer to build a network structure and reduce the dimension of data,which can effectively avoid over fitting.Cross-entropy verification is used to compile and train the model,and the output classification results are further analyzed.Through the <i>K</i>-nearest neighbor classification algorithm,KNN classifier is set to further improve the accuracy of classification and prediction.Through MNIST data set experiment,the recognition rate is about 96.2%.The <i>K</i>-nearest neighbor algorithm(KNN) is introduced into the output layer,combined with the full connection layer and softmax layer of traditional convolutional neural network(CNN).After cross verification,the recognition rate is 99.6%.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-244.pdfdigital identification|<i>k</i> nearest neighbor algorithm|deep learning|convolutional neural network|cross entropy |
| spellingShingle | FAN Ji-hui, TENG Shao-Hua, JIN Hong-Lin Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network Jisuanji kexue digital identification|<i>k</i> nearest neighbor algorithm|deep learning|convolutional neural network|cross entropy |
| title | Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network |
| title_full | Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network |
| title_fullStr | Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network |
| title_full_unstemmed | Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network |
| title_short | Handwritten Numeral Recognition Based on Improved Sigmoid Convolutional Neural Network |
| title_sort | handwritten numeral recognition based on improved sigmoid convolutional neural network |
| topic | digital identification|<i>k</i> nearest neighbor algorithm|deep learning|convolutional neural network|cross entropy |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-12-244.pdf |
| work_keys_str_mv | AT fanjihuitengshaohuajinhonglin handwrittennumeralrecognitionbasedonimprovedsigmoidconvolutionalneuralnetwork |