Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5
Convolutional neural network (CNN) is a very important method in deep learning, which solves many complex pattern recognition problems. Fruitful results have been achieved in image recognition, speech recognition, and natural language processing. Compared with traditional neural network, convolution...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Computer Networks and Communications |
| Online Access: | http://dx.doi.org/10.1155/2022/1636203 |
| _version_ | 1826839051850743808 |
|---|---|
| author | Lijie Zhou Weihai Yu |
| author_facet | Lijie Zhou Weihai Yu |
| author_sort | Lijie Zhou |
| collection | DOAJ |
| description | Convolutional neural network (CNN) is a very important method in deep learning, which solves many complex pattern recognition problems. Fruitful results have been achieved in image recognition, speech recognition, and natural language processing. Compared with traditional neural network, convolutional weight sharing, sparse connection, and pooling operations in convolutional neural network greatly reduce the number of training parameters, reduce size of feature map, simplify network model, and improve training efficiency. Based on convolution operation, pooling operation, softmax classifier, and network optimization algorithm in improved convolutional neural network of LeNet-5, this paper conducts image recognition experiments on handwritten digits and face datasets, respectively. A method combining local binary pattern and convolutional neural network is proposed for face recognition research. Through experiments, it is found that adding LBP image information to improved convolutional neural network of LeNet-5 can improve accuracy of face recognition to 99.8%, which has important theoretical and practical significance. |
| first_indexed | 2024-04-11T19:30:46Z |
| format | Article |
| id | doaj.art-50baa961190e4437a55792140c6c33b9 |
| institution | Directory Open Access Journal |
| issn | 2090-715X |
| language | English |
| last_indexed | 2025-02-16T12:09:43Z |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Computer Networks and Communications |
| spelling | doaj.art-50baa961190e4437a55792140c6c33b92025-02-03T01:01:21ZengWileyJournal of Computer Networks and Communications2090-715X2022-01-01202210.1155/2022/1636203Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5Lijie Zhou0Weihai Yu1Yantai Vocational CollegeYantai Research Institute of Education ScienceConvolutional neural network (CNN) is a very important method in deep learning, which solves many complex pattern recognition problems. Fruitful results have been achieved in image recognition, speech recognition, and natural language processing. Compared with traditional neural network, convolutional weight sharing, sparse connection, and pooling operations in convolutional neural network greatly reduce the number of training parameters, reduce size of feature map, simplify network model, and improve training efficiency. Based on convolution operation, pooling operation, softmax classifier, and network optimization algorithm in improved convolutional neural network of LeNet-5, this paper conducts image recognition experiments on handwritten digits and face datasets, respectively. A method combining local binary pattern and convolutional neural network is proposed for face recognition research. Through experiments, it is found that adding LBP image information to improved convolutional neural network of LeNet-5 can improve accuracy of face recognition to 99.8%, which has important theoretical and practical significance.http://dx.doi.org/10.1155/2022/1636203 |
| spellingShingle | Lijie Zhou Weihai Yu Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 Journal of Computer Networks and Communications |
| title | Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 |
| title_full | Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 |
| title_fullStr | Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 |
| title_full_unstemmed | Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 |
| title_short | Improved Convolutional Neural Image Recognition Algorithm based on LeNet-5 |
| title_sort | improved convolutional neural image recognition algorithm based on lenet 5 |
| url | http://dx.doi.org/10.1155/2022/1636203 |
| work_keys_str_mv | AT lijiezhou improvedconvolutionalneuralimagerecognitionalgorithmbasedonlenet5 AT weihaiyu improvedconvolutionalneuralimagerecognitionalgorithmbasedonlenet5 |