Image generation classification method based on convolution neural network

Qiao-ling LI; Qing-xiao GUAN; Xian-feng ZHAO

doi:10.11959/j.issn.2096-109x.2016.00096

您当前的位置：

首页 >

文章列表页 >

Image generation classification method based on convolution neural network

academic paper | 更新时间：2024-06-03

- Image generation classification method based on convolution neural network
- Chinese Journal of Network and Information Security Vol. 2, Issue 9, Pages: 40-48(2016)
- 作者机构：
  
  1. 中国科学院信息工程研究所信息安全国家重点实验室，北京 100093
  2. 中国科学院大学，北京 100049
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2016.00096
  CLC： TP37
- Online First：2016-09，
  
  Published：15 September 2016
- 稿件说明：
移动端阅览
Qiao-ling LI, Qing-xiao GUAN, Xian-feng ZHAO. Image generation classification method based on convolution neural network[J]. Chinese Journal of Network and Information Security, 2016, 2(9): 40-48.
DOI：

Qiao-ling LI, Qing-xiao GUAN, Xian-feng ZHAO. Image generation classification method based on convolution neural network[J]. Chinese Journal of Network and Information Security, 2016, 2(9): 40-48. DOI： 10.11959/j.issn.2096-109x.2016.00096.

摘要

提出一种采用卷积神经网络对自然图像和文档扫描图像进行分类的方法，通过卷积和池化操作提取两类图像具有高区分度的特征，融合后得到分类判决结果。实验结果表明，所提出的分类方法在 SKL 图像库上分类精度超过93%。图像预处理对模型的精度以及模型训练收敛所需时间具有积极效果，经过图像预处理后训练的卷积神经网络模型对图像文字大小和图像格式顽健。

Abstract

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.

关键词

Keywords

references

WANG Y , MOULIN P . On discrimination between photorealistic and photographic images [C ] // IEEE International Conference on Acoustics Speech and Signal Processing . 2006 .

LYU S , FARID H . How realistic is photorealistic [J ] . IEEE Interna-tional Conference on Signal Processing , 2005 , 53 ( 2 ): 845 - 850 .

ZHU J Y , KRAHENBUHL P , SHECHTMAN E , et al . Learning a discriminative model for the perception of realism in composite images [C ] // IEEE International Conference on Computer Vision . 2015 : 3943 - 3951 .

KHANNA N , CHIU G T C , ALLEBACH J P , et al . Forensic tech-niques for classifying scanner,computer generated and digital cam-era images [C ] // IEEE International Conference on Acoustics,Speech and Signal Processing . 2008 : 1653 - 1656 .

MAHENDRAN A , VEDALDI A . Understanding deep image rep-resentations by inverting them [C ] // IEEE Conference on Computer Vision and Pattern Recognition . 2015 : 5188 - 5196 .

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

KUSSUL E , BAIDYK T , WUNSCH II D C . Permutation coding technique for image recognition system standard [M ] Neural Networks and Micromechanics . 2010 47 - 73 .

KAIMING H , XIANGYU Z , SHAOQING R , et al . Delving deep into rectifiers:surpassing human-level performance on imagenet classification [C ] // IEEE International Conference on Computer Vi-sion . 2015 : 1026 - 1034 .

NAIR V , HINTON G E . Rectified linear units improve restricted boltzmann machines [C ] // The 27th International Conference on Machine Learning . 2010 : 807 - 814 .

SRIVASTAVA N , HINTON G , KRIZHEVSKY A , et al . Dropout:a simple way to prevent neural networks from overfitting [J ] . The Journal of Machine Learning Research , 2014 , 15 ( 1 ): 1929 - 1958 .

SUTSKEVER I , MARTENS J , DAHL G , et al . On the importance of initialization and momentum in deep learning [C ] // The 30th In-ternational Conference on Machine Learning . 2013 : 1139 - 1147 .

JIA Y , SHELHAMER E , DONAHUE J , et al . Caffe:convolutional architecture for fast feature embedding [C ] // The ACM International Conference on Multimedia . 2014 : 675 - 678 .

Views

296

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Encrypted traffic classification method based on convolutional neural network

Research progress of digital image forensic techniques based on deep learning

Related Author

Rongna XIE

Zhuhong MA

Zongyu LI

Ye TIAN

Tong QIAO

Hongwei YAO

Binmin PAN

Ming XU

Related Institution

School of Cyberspace, Hangzhou Dianzi University

University of Technology of Troyes, Troyes

⁰