Image generation classification method based on convolution neural network
Using convolution neural network which though convolution and pooling extracting features of high dis-tinguish ability and then make fusion for classification of natural images and scanned documents.Experimental re-sults show that the classification accuracy of the proposed classification method is...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2016-09-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2016.00096 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530371547594752 |
|---|---|
| author | Qiao-ling LI Qing-xiao GUAN Xian-feng ZHAO |
| author_facet | Qiao-ling LI Qing-xiao GUAN Xian-feng ZHAO |
| author_sort | Qiao-ling LI |
| collection | DOAJ |
| description | Using convolution neural network which though convolution and pooling extracting features of high dis-tinguish ability and then make fusion for classification of natural images and scanned documents.Experimental re-sults show that the classification accuracy of the proposed classification method is more than 93% on the SKL image database.The model is highly robust to font sizes and image formats.Through contrast experiment validated that preprocessing of image has a positive effect on the accuracy of the model and the time cost on training. |
| format | Article |
| id | doaj-art-591c33ef1aa1452a83ee16d6e6a6acb1 |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2016-09-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-591c33ef1aa1452a83ee16d6e6a6acb12025-01-15T03:04:52ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2016-09-012404859548006Image generation classification method based on convolution neural networkQiao-ling LIQing-xiao GUANXian-feng ZHAOUsing convolution neural network which though convolution and pooling extracting features of high dis-tinguish ability and then make fusion for classification of natural images and scanned documents.Experimental re-sults show that the classification accuracy of the proposed classification method is more than 93% on the SKL image database.The model is highly robust to font sizes and image formats.Through contrast experiment validated that preprocessing of image has a positive effect on the accuracy of the model and the time cost on training.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2016.00096convolution neural networkimage generation modecontent pattern classificationmultimedia security |
| spellingShingle | Qiao-ling LI Qing-xiao GUAN Xian-feng ZHAO Image generation classification method based on convolution neural network 网络与信息安全学报 convolution neural network image generation mode content pattern classification multimedia security |
| title | Image generation classification method based on convolution neural network |
| title_full | Image generation classification method based on convolution neural network |
| title_fullStr | Image generation classification method based on convolution neural network |
| title_full_unstemmed | Image generation classification method based on convolution neural network |
| title_short | Image generation classification method based on convolution neural network |
| title_sort | image generation classification method based on convolution neural network |
| topic | convolution neural network image generation mode content pattern classification multimedia security |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2016.00096 |
| work_keys_str_mv | AT qiaolingli imagegenerationclassificationmethodbasedonconvolutionneuralnetwork AT qingxiaoguan imagegenerationclassificationmethodbasedonconvolutionneuralnetwork AT xianfengzhao imagegenerationclassificationmethodbasedonconvolutionneuralnetwork |