Handwritten digit recognition based on conditional generative adversarial network

Ai-li WANG; Dong XUE; Hai-bin WU; Min-hui WANG

doi:10.37188/YJYXS20203512.1284

您当前的位置：

首页 >

文章列表页 >

Handwritten digit recognition based on conditional generative adversarial network

Image Processing | 更新时间：2020-12-04

- Handwritten digit recognition based on conditional generative adversarial network
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 12, Pages: 1284-1290(2020)
- 作者机构：
  
  哈尔滨理工大学测控技术与通信工程学院, 黑龙江哈尔滨 150080
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61671190)
- DOI：10.37188/YJYXS20203512.1284
  CLC： TP391
- Received：27 May 2020，
  
  Revised：14 August 2020，
  
  Accepted：14 August 2020，
  
  Published：2020-12
- 稿件说明：
移动端阅览
Ai-li WANG, Dong XUE, Hai-bin WU, et al. Handwritten digit recognition based on conditional generative adversarial network[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1284-1290.
DOI：

Ai-li WANG, Dong XUE, Hai-bin WU, et al. Handwritten digit recognition based on conditional generative adversarial network[J]. Chinese journal of liquid crystals and displays, 2020, 35(12): 1284-1290. DOI： 10.37188/YJYXS20203512.1284.

摘要

针对当训练样本不足时，传统深度学习算法在手写数字识别中会出现训练不稳定、识别精度较低等问题，提出了基于条件生成对抗网络的识别方法。首先，在条件生成对抗网络的基础上，利用生成器使用类别标签控制图像生成的优点，将生成器产生的图像样本作为训练数据，扩充数据集。同时，利用反卷积网络和卷积网络分别构成生成器和判别器的网络结构，去掉全连接层以提升模型稳定性。然后，引入条件批量归一化，利用它使用类别标签的优点，使网络学习更多的特征。最后，改进判别器为分类器，并提出新的损失函数，加快收敛速度，提高识别精度。实验结果表明，本文所提出的手写数字识别方法生成的图像质量更好，识别准确率更高，达到99.43%，为生成对抗网络及其变体在图像识别领域中的应用提供了参考。

Abstract

In order to solve the problem of unstable training and low recognition accuracy of traditional deep learning algorithm in handwritten digit recognition when training samples are insufficient

a recognition method based on conditional generative adversarial network is proposed. Firstly

on the basis of the conditional generative adversarial network

the generator of category labels is used to control image generation. The image samples generated by the generator are used to expand the training data set. At the same time

the deconvolution network and the convolutional network are used to construct the network structure of generator and discriminator respectively

and the full connection layer is removed to improve the stability of the model. Then

the conditional batch normalization is introduced. Taking advantage of its use of category labels to make the network learn more features. Finally

the discriminator is improved to be a classifier

and a novel loss function is proposed to speed up the convergence rate and improve the recognition accuracy. The experimental results show that the handwritten digit recognition method proposed in this paper has better image quality and higher recognition accuracy of 99.43%. This paper provides a reference for the application of generative adversarial network and its variants in the field of image recognition.

关键词

Keywords

references

郑欣 , 田博 , 李晶晶 . 基于YOLO模型的宫颈细胞簇团智能识别方法 . 液晶与显示 , 2018 . 33 ( 11 ): 965 - 971 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh .

X ZHENG , B TIAN , J J LI . Intelligent recognition method of cervical cell cluster based on YOLO model . Chinese Journal of Liquid Crystals and Displays , 2018 . 33 ( 11 ): 965 - 971 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1462781&Fpath=&index=-1&l=zh .

张万征 , 胡志坤 , 李小龙 . 基于LeNet-5的卷积神经图像识别算法 . 液晶与显示 , 2020 . 35 ( 5 ): 486 - 490 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1399065&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1399065&Fpath=&index=-1&l=zh .

W Z ZHANG , Z K HU , X L LI . Convolutional neural image recognition algorithm based on LeNet-5 . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 5 ): 486 - 490 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1399065&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1399065&Fpath=&index=-1&l=zh .

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al . Generative adversarial nets[C]// Proceedings of the 27 th International Conference on Neural Information Processing Systems . Cambridge: MIT Press, 2014, 3: 2672-2680.

RATLIFF L J, BURDEN S A, SASTRY S S. Characterization and computation of local Nash equilibria in continuous games[C]// Proceedings of the 51 st Annual Allerton Conference on Communication , Control , and Computing . Monticello, IL, USA: IEEE, 2013: 917-924.

L ZHU , Y S CHEN , P GHAMISI , 等 . Generative adversarial networks for hyperspectral image classification . IEEE Transactions on Geoscience and Remote Sensing , 2018 . 56 ( 9 ): 5046 - 5063 . DOI: 10.1109/TGRS.2018.2805286 http://doi.org/10.1109/TGRS.2018.2805286 .

刘坤 , 王典 , 荣梦学 . 基于半监督生成对抗网络X光图像分类算法 . 光学学报 , 2019 . 39 ( 8 ): 0810003 .

K LIU , D WANG , M X RONG . X-ray image classification algorithm based on semi-supervised generative adversarial networks . Acta Optica Sinica , 2019 . 39 ( 8 ): 0810003 .

杨旺功 , 淮永建 . 基于深度卷积生成对抗网络的花朵图像增强与分类 . 计算机科学 , 2020 . 47 ( 6 ): 176 - 179 .

W G YANG , Y J HUAI . Flower image enhancement and classification based on deep convolution generative adversarial network . Computer Science , 2020 . 47 ( 6 ): 176 - 179 .

Y KUANG , T LAN , X Q PENG , 等 . Unsupervised multi-discriminator generative adversarial network for Lung nodule malignancy classification . IEEE Access , 2020 . 8 77725 - 77734 . DOI: 10.1109/ACCESS.2020.2987961 http://doi.org/10.1109/ACCESS.2020.2987961 .

MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. arXiv : 1411.1784, 2014.

ZHANG H, GOODFELLOW I, METAXAS D, et al . Self-attention generative adversarial networks[EB/OL].[2019-06-14] . https://arxiv.org/pdf/1805.08318.pdf https://arxiv.org/pdf/1805.08318.pdf .

MIYATO T, KOYAMA M. CGANs with projection discriminator[EB/OL].[2018-08-15] . https://arxiv.org/pdf/1802.05637.pdf https://arxiv.org/pdf/1802.05637.pdf .

LOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32 nd International Conference on Machine Learning . Lille, France: PMLR, 2015: 448-456.

RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv : 1511.06434, 2015.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Cycle generative adversarial network guided by dual special attention mechanism

Related Author

Jun-ming LAO

Wu-jian YE

Yi-jun LIU

Kai-yi YUAN

劳俊明

叶武剑

LIU Yi-jun

袁凯奕

Related Institution

College of Information Engineering, Guangdong University of Technology

College of Integrated Circuit,Guangdong University of Technology

College of Information Engineering， Guangdong University of Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰